A low-altitude aviation activity risk prediction method and device

Abstract

The application provides a low-altitude aviation activity risk prediction method and device, relates to the low-altitude aviation activity risk evaluation field, and comprises the following steps: preprocessing obtained low-altitude aviation activity flight data and knowledge data to obtain multi-source standard data; inputting the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein the low-altitude aviation activity risk analysis model is used for performing low-altitude aviation activity risk analysis in each dimension on the multi-source standard data; if it is determined that the low-altitude aviation activity risk is greater than a preset safety threshold based on the multi-dimensional risk factors, generating a low-altitude aviation activity safety trajectory according to adjusted multi-source standard data. The application can analyze the risks hidden in low-altitude aviation activities based on corresponding flight environment, equipment state and task type and the like of the low-altitude aviation activities, and generate a low-altitude aviation activity safety trajectory.

Description

Technical Field

[0001] This application relates to the field of low-altitude aviation activity risk assessment, specifically a method and apparatus for predicting low-altitude aviation activity risks. Background Technology

[0002] With the increasing prevalence of low-altitude aviation, the frequency and complexity of unmanned aerial vehicles (UAVs) operations have significantly increased. The deployment of UAVs has provided innovative implementation solutions for several technological fields, such as location-based swarm flight, geographic remote sensing mapping, and automated high-altitude cleaning equipment. This remote control mechanism based on ground terminals effectively eliminates the physical safety hazards posed by operators working in high-altitude environments. However, low-altitude flight operations have also given rise to new operational risks, including but not limited to: aircraft crashes caused by power or navigation system malfunctions, and spatial collisions with buildings or people on the ground due to trajectory errors.

[0003] Many regions have already mandated that low-altitude aviation activities must have corresponding risk mitigation mechanisms to ensure civil aviation and public safety. However, the current bottleneck in risk assessment processes lies in the difficulty for relevant agencies to assess the operational risks involved in each activity. Existing technologies can only estimate risk coefficients based on general risk assessment frameworks and actuarial models, but these frameworks often fail to fully consider risk factors directly related to low-altitude aviation, such as flight duration, activity nature, environmental conditions, and aircraft condition.

[0004] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section. Summary of the Invention

[0005] To address the problems in the existing technology, this application provides a method and apparatus for predicting the risks of low-altitude aviation activities. It can analyze the potential risks in low-altitude aviation activities based on data such as the flight environment, equipment status and mission type corresponding to the low-altitude aviation activities, and generate a safety trajectory for low-altitude aviation activities.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution: Firstly, this application provides a method for predicting the risks of low-altitude aviation activities, including: The acquired low-altitude aviation flight data and knowledge data are preprocessed to obtain multi-source standard data; The multi-source standard data is input into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein, the low-altitude aviation activity risk analysis model is used to perform low-altitude aviation activity risk analysis on the multi-source standard data in various dimensions. If the risk of low-altitude aviation activities is determined to be greater than the preset safety threshold based on the multi-dimensional risk factors, a low-altitude aviation activity safety trajectory is generated based on the adjusted multi-source standard data.

[0007] Furthermore, the preprocessing of the acquired low-altitude aviation flight data and knowledge data yields multi-source standard data, including: Anomaly and missing data are detected in the low-altitude aviation flight data and knowledge data to obtain abnormal data and missing data. After removing the abnormal data, the missing data is filled by linear interpolation to obtain complete data; The complete data is time-series aligned to obtain the multi-source standard data.

[0008] Furthermore, the low-altitude aviation activity risk analysis model includes a star-dimensional model, a sky-dimensional model, and a ground-dimensional model; the multi-dimensional risk factors include star-dimensional risk factors, sky-dimensional risk factors, and ground-dimensional risk factors; the process of inputting the multi-source standard data into the pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors includes: The satellite signal quality, number of locked satellites, and number of satellite signal interferences from the multi-source standard data are input into the star dimension model to obtain the star dimension risk factor; The rainfall, average wind speed, atmospheric relative humidity, dew point, average atmospheric temperature, and atmospheric visibility during low-altitude aviation activities from the multi-source standard data are input into the sky dimension model to obtain the sky dimension risk factor. By inputting the ground-level altitude of low-altitude aviation activities and the density of surrounding buildings from the multi-source standard data into the geodetic model, the geodetic risk factor is obtained.

[0009] Furthermore, the low-altitude aviation activity risk analysis model includes a dynamic dimension model, an aircraft dimension model, a time dimension model, a rule dimension model, and a scenario dimension model; the multi-dimensional risk factors include dynamic dimension risk factors, aircraft dimension risk factors, time dimension risk factors, rule dimension risk factors, and scenario dimension risk factors; the process of inputting the multi-source standard data into the pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors includes: Population density, traffic flow, driving speed and road conditions from the multi-source standard data are input into the dynamic dimension model to obtain the dynamic dimension risk factor; The aircraft weight, flight hours, number of past incidents, and emergency landing deployment capability from the multi-source standard data are input into the aircraft-dimensional model to obtain the aircraft-dimensional risk factor. The estimated flight duration and flight time period from the multi-source standard data are input into the time-dimensional model to obtain the time-dimensional risk factor; The compliance level in the multi-source standard data is input into the compliance dimension model to obtain the compliance dimension risk factor; The potential risks of the activities in the multi-source standard data are input into the scene dimension model to obtain the scene dimension risk factor.

[0010] Furthermore, the low-altitude aviation activity risk analysis model includes a human-dimensional model; the multi-dimensional risk factors include human-dimensional risk factors; by inputting the multi-source standard data into the pre-constructed low-altitude aviation activity risk analysis model, multi-dimensional risk factors are obtained, including: The human-dimensional risk factor is determined based on the operator's qualifications, flight hours, number of historical accidents, and the human-dimensional model in the multi-source standard data.

[0011] Furthermore, if the risk of low-altitude aviation activity is determined to be greater than a preset safety threshold based on the multi-dimensional risk factors, generating a low-altitude aviation activity safety trajectory based on the adjusted multi-source standard data includes: The total risk factor is calculated based on the multi-dimensional risk factors and their corresponding risk factor weights. Determine whether the risk of low-altitude aviation activities exceeds the safety threshold based on the total risk factor and the safety threshold. If so, adjust the variable parameters in the multi-source standard data; The low-altitude aviation activity safety trajectory is generated based on multi-source standard data containing the variable parameters.

[0012] Secondly, this application provides a low-altitude aviation activity risk prediction device, comprising: The standard data generation unit is used to preprocess the acquired low-altitude aviation flight data and knowledge data to obtain multi-source standard data. The risk factor generation unit is used to input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein, the low-altitude aviation activity risk analysis model is used to perform low-altitude aviation activity risk analysis on the multi-source standard data in various dimensions. The activity risk analysis unit is used to generate a low-altitude aviation activity safety trajectory based on the adjusted multi-source standard data if the risk of low-altitude aviation activity is determined to be greater than a preset safety threshold based on the multi-dimensional risk factors.

[0013] Thirdly, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the low-altitude aviation activity risk prediction method.

[0014] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the low-altitude aviation activity risk prediction method.

[0015] Fifthly, this application provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the low-altitude aviation activity risk prediction method.

[0016] To address the problems in the existing technology, the low-altitude aviation activity risk prediction method and apparatus provided in this application can accelerate the calculation of risk coefficients, fully automate the process without the need for traditional manual review procedures; establish objective, consistent and standardized algorithm parameters to accurately reflect the risks involved in each activity and reduce the subjectivity of human judgment; and generate low-altitude aviation activity safety trajectories based on risk analysis results. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is one of the flowcharts for the low-altitude aviation activity risk prediction method in the embodiments of this application; Figure 2 This is the second flowchart of the low-altitude aviation activity risk prediction method in the embodiments of this application (the complete route of data in the method). Figure 3 This is a schematic diagram of the forward linking process of an expert system based on a predefined rule set (i.e., "facts") in an embodiment of this application; Figure 4 This is a schematic diagram of the intelligent processing flow in the embodiments of this application; Figure 5 This is a flowchart illustrating the processing of risk factors across various dimensions in the embodiments of this application. Figure 6 This is a flowchart illustrating the processing of the total risk factor in an embodiment of this application; Figure 7 This is a flowchart illustrating the process of obtaining multi-source standard data in the embodiments of this application; Figure 8 This is one of the flowcharts for obtaining multi-dimensional risk factors in the embodiments of this application; Figure 9 This is a schematic diagram of the processing flow of star-dimensional risk factors in the embodiments of this application; Figure 10This is a schematic diagram of the processing flow of the risk factor of the sky dimension in the embodiments of this application; Figure 11 This is a schematic diagram illustrating the processing flow of the geodimensional risk factor in the embodiments of this application; Figure 12 This is the second flowchart for obtaining multi-dimensional risk factors in the embodiments of this application; Figure 13 This is a schematic diagram illustrating the processing flow of dynamic risk factors in the embodiments of this application; Figure 14 This is a schematic diagram illustrating the processing flow of machine-based risk factors in the embodiments of this application; Figure 15 This is a schematic diagram of the processing flow of time-dimensional risk factors in the embodiments of this application; Figure 16 This is a schematic diagram illustrating the processing flow of risk factors in the dimensional dimensions of this application. Figure 17 This is a schematic diagram of the processing flow of the mid-dimensional risk factor in the embodiments of this application; Figure 18 This is a schematic diagram illustrating the processing flow of human-dimensional risk factors in the embodiments of this application; Figure 19 This is a flowchart illustrating the generation of a low-altitude aviation activity safety trajectory in an embodiment of this application; Figure 20 This is a structural diagram of the low-altitude aviation activity risk prediction device in the embodiments of this application; Figure 21 This is a schematic diagram of the structure of the electronic device in the embodiments of this application; Figure 22 This is a flowchart of the SMS process in the embodiments of this application; Figure 23 This is a flowchart illustrating the generation of a low-altitude aviation activity safety trajectory in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0020] The information collected in the technical solution of this application is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation portals are provided for users to choose to authorize or refuse.

[0021] Provide users with corresponding operation entry points, allowing them to choose to agree to or reject the automated decision results; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0022] In one embodiment, see Figure 1 In order to analyze the potential risks in low-altitude aviation activities based on data such as the flight environment, equipment status, and mission type, and to generate a safe trajectory for low-altitude aviation activities, this application provides a method for predicting the risks of low-altitude aviation activities, including: S101: Preprocess the acquired low-altitude aviation activity flight data and knowledge data to obtain multi-source standard data; among which, low-altitude aviation activity flight data is also called low-altitude aviation flight data. S102: Input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein, the low-altitude aviation activity risk analysis model is used to perform low-altitude aviation activity risk analysis on the multi-source standard data in various dimensions. S103: If the risk of low-altitude aviation activities is determined to be greater than the preset safety threshold based on the multi-dimensional risk factors, a low-altitude aviation activity safety trajectory is generated based on the adjusted multi-source standard data.

[0023] It is understood that the embodiments of this application can be used to predict and determine the risks of low-altitude aviation activities, and when the risk of low-altitude aviation activities is determined to be greater than a preset safety threshold, a safe trajectory for low-altitude aviation activities is generated by adjusting the variable parameters in the multi-source standard data. This safe trajectory for low-altitude aviation activities can be used to guide drone operators and other relevant personnel in using drones for low-altitude aviation activities.

[0024] The method provided in this application can acquire low-altitude aviation activity flight data (referring to data corresponding to upcoming low-altitude aviation activities) and knowledge data (referring to data in a knowledge base). These can also be categorized as: real-time data, forecast data (e.g., weather forecast data), and knowledge data (also known as historical data in the knowledge base). The above data is preprocessed to form multi-source standard data, which is then input into a pre-constructed risk analysis model. This model assesses the activity risk from multiple dimensions and outputs multi-dimensional risk factors. If, based on these factors, the current risk exceeds a preset safety threshold, corresponding (hypothetical) adjustments are made to the multi-source standard data, and a low-altitude aviation activity safety trajectory is generated based on the adjusted data.

[0025] The above process can be understood as determining a relatively safe "low-altitude aviation activity trajectory," or low-altitude aviation activity safety trajectory, by continuously trying and adjusting multi-source standard data, thereby forming a relatively safe low-altitude aviation activity flight plan. The entire process realizes a closed loop from raw data to risk identification and then to safety decision-making, aiming to provide timely early warning of high-risk situations through quantitative analysis and to provide aircraft with feasible safe flight plans, thereby improving the safety and controllability of low-altitude aviation activities.

[0026] It should be noted that all of the above data was obtained and used only after authorization was obtained from the data recipient.

[0027] The aforementioned real-time data, forecast data (e.g., weather forecast data), and historical data may be derived from some public datasets, such as, but not limited to, weather conditions: such as wind speed, rainfall, visibility, etc.

[0028] Historical data may include, but is not limited to, operator flight records or accident records; real-time data may be provided by users (mainly operators) and sensors, such as the drone's altitude above the ground, the distance between the drone and nearby buildings, and interference from the Global Navigation Satellite System.

[0029] Given that some data, such as weather data, may affect calculation results due to blank or incomplete information, the data will be preprocessed before being transmitted to the low-altitude aviation activity risk analysis model. This preprocessing includes, but is not limited to, removing blank or incomplete information. Furthermore, this unstructured data will be converted into a multi-source standard data format, making it easy for humans and computers to read and integrate into other systems.

[0030] The algorithm (the method provided in this application) can be implemented based on an expert system. This system contains at least a knowledge base of risk assessment domain expertise and past prediction results, presented in the form of a set of conditional rules. The inference engine processes these rules, historical results, and input data to infer for each condition and outputs the inference results to a Human-Machine Interface (HMI) for display. It can also be stored in the knowledge base for future inference purposes.

[0031] Figure 2 This represents the complete path of the data within the algorithm. Figure 3This diagram illustrates the forward linking process of an expert system based on a predefined set of rules (i.e., "facts"). Data is acquired from three sources: real-time data, predicted data, and knowledge data. The received data undergoes preprocessing—filtering out blank or incomplete invalid data and converting the filtered data to a standardized format, which also serves as the raw data. After receiving the preprocessed data, the system analyzes and infers, with its internal process including calculating the dimensional risk factors and total risk factors of the activity (detailed below). The raw data and analysis results are stored in a knowledge base; a low-altitude aviation activity safety trajectory is generated; additionally, the analysis results are displayed on a human-machine interface for end-user interaction.

[0032] Other artificial intelligence (AI) methods, including but not limited to artificial neural networks (ANNs) and fuzzy logic, will also serve as auxiliary tools for the algorithm. This aims to achieve automatic learning from the large datasets collected from the aforementioned sources to further improve the accuracy and objectivity of risk predictions, while handling fuzzy values ​​that traditional expert systems might struggle with due to their use of strict true / false logic (such as Boolean values ​​1 or 0). Candidate ANNs include recurrent neural networks (RNNs) and multilayer perceptrons (MLPs).

[0033] The risk analysis model for low-altitude aviation activities includes the following dimensions: satellite, weather, ground, motion, UAVs, time, regulations, scenario, and personnel. It employs a method similar to the Safety Management System (SMS) commonly used in the civil aviation industry, combined with an expert system, to predict the risks of low-altitude aviation activities. Total Risk Factor F total By measuring the risk contributed by each dimension, the overall operation is determined to be safe, risky but acceptable, or dangerous:

[0034] In the formula, w i and F i The first i The weights and risk factors for each dimension are defined, with the weights used to control the contribution of each dimension. F total The value ranges from 0 to 1, where 0 represents no or low risk; the higher the value, the higher the risk. A preset safety threshold can then be used to determine whether the risk exceeds the threshold range.

[0035] Figure 4This describes the processing flow of the artificial intelligence algorithm. Preprocessed data (i.e., raw data) is input into nine dimensions to calculate each risk factor; the risk factors of each dimension are received and the total risk factor of low-altitude aviation activities is calculated; the raw data and analysis results are stored in the knowledge base, and the analysis results are output to the human-machine interface. Figure 5 This describes the processing flow for dimensional risk factors. It receives preprocessed data; extracts relevant parameters for the dimension to be calculated from the data; performs preprocessing to filter out effective parameters; processes the parameters and analyzes the risk of that dimension using dimensional formulas, SMS, and an expert system; and inputs the analysis results into the overall risk factor calculation.

[0036] Figure 6 The process for handling the overall risk factor is as follows: Nine risk factors are input; each factor is incorporated into the overall risk factor formula, SMS, and expert system for processing and analysis of the overall risk of low-altitude aviation activities; raw data and analysis results are stored in the knowledge base, and the analysis results are output to the human-machine interface.

[0037] Figure 6 The processing flow of the total risk factor in F total Similarly, risk factors in each dimension F i The general formula for measuring the influence of each parameter is as follows:

[0038] in, P j For each parameter, f j ( This is used to assess the risk caused by this parameter, while w j Weights are assigned to each parameter to control their contribution, and the sum of all weights must equal 1. Each F i The value and F total Similarly, they all range from 0 to 1, with 0 representing no or low risk; the higher the value, the higher the risk.

[0039] It should be noted that the generation process of the low-altitude aviation activity safety trajectory is as follows: The low-altitude aviation activity risk analysis model outputs multi-dimensional risk factors and generates a total risk factor. This total risk factor is then assessed by a risk assessment system similar to the Safety Management System (SMS) commonly used in the civil aviation industry to determine the level of risk for the activity. The SMS sets different risk levels based on multiple preset safety ranges, for example, "high" is 0.8 to 1, "medium" is 0.4 to 0.79, and "low" is 0 to 0.39. Then, the SMS categorizes the total risk factor into one of these levels. If the risk is low or medium, the total risk factor and its corresponding current flight trajectory are output to the human-machine interface for display; if the risk is high, the multi-source standard data is further adjusted to generate the corresponding low-altitude aviation activity safety trajectory. The process of generating the low-altitude aviation activity safety trajectory is a recursive reasoning process. Finally, the low-altitude aviation activity safety trajectory and the corresponding total risk factor are output to the human-machine interface for display.

[0040] The steps of recursive reasoning are as follows: 1. Within the predefined flight range or trajectory range (starting and ending points), a three-dimensional path search algorithm, such as 3D A... The search algorithm finds multiple flight paths that are different from the original ones.

[0041] 2. Within each trajectory: Allow modification of the parameters input to the model (i.e., variable parameters in multi-source standard data) through the human-computer interface, and then the model recalculates the multi-dimensional risk factors and the total risk factor.

[0042] 3. Display the total risk factors and corresponding flight trajectories to the human-machine interface, and ask whether to continue the reasoning process: Yes: Repeat step 2.

[0043] No: The reasoning process is complete.

[0044] See the SMS flowchart. Figure 22 As shown.

[0045] See the flowchart for generating a safe trajectory for low-altitude aviation activities. Figure 23 As shown.

[0046] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can accelerate the calculation of risk coefficients, fully automate the process without the need for traditional manual review procedures, establish objective, consistent and standardized algorithm parameters to accurately reflect the risks involved in each activity and reduce the subjectivity of human judgment, and generate low-altitude aviation activity safety trajectories based on risk analysis results.

[0047] In one embodiment, see Figure 7 The preprocessing of the acquired low-altitude aviation activity flight data and knowledge data yields multi-source standard data, including: S701: Perform anomaly detection on the low-altitude aviation activity flight data and knowledge data to obtain abnormal data and missing data; S702: After removing the abnormal data, perform linear interpolation to fill in the missing data to obtain complete data; S703: Perform time-series alignment on the complete data to obtain the multi-source standard data.

[0048] Understandably, processing low-altitude aviation activity data requires, first, joint anomaly and missing data detection of real-time streaming data and historical archives in a knowledge base. This involves accurately identifying outliers caused by sensor drift, communication packet loss, or recording errors through statistical thresholds, mutation tests, and business logic rules, while also marking missing time points caused by sampling interruptions or storage failures. Next, after removing identified outliers, linear interpolation is used to fill in the missing time periods. This method estimates reasonable values ​​based on the linear trend of adjacent valid values ​​before and after the missing point, smoothly patching short-term gaps while avoiding overfitting errors, thus obtaining a continuous and complete data sequence. Finally, the patched complete data is resampled and aligned according to a unified time base (e.g., millisecond-level timestamps) to ensure strict correspondence between data from different sources and frequencies on the same timeline, eliminating time delay offsets and sampling asynchrony issues. The final output is a multi-source standard dataset with consistency, comparability, and high availability, laying the data foundation for subsequent risk analysis and track generation.

[0049] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can preprocess the acquired low-altitude aviation activity flight data and knowledge data to obtain multi-source standard data.

[0050] In one embodiment, see Figure 8 The low-altitude aviation activity risk analysis model includes a star-dimensional model, a sky-dimensional model, and a ground-dimensional model; the multi-dimensional risk factors include star-dimensional risk factors, sky-dimensional risk factors, and ground-dimensional risk factors; the multi-source standard data is input into the pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors, including: S801: Input the satellite signal quality, number of locked satellites, and number of satellite signal interferences from the multi-source standard data into the star dimension model to obtain the star dimension risk factor; S802: Input the rainfall, average wind speed, atmospheric relative humidity, dew point, average atmospheric temperature and atmospheric visibility during low-altitude aviation activities from the multi-source standard data into the sky dimension model to obtain the sky dimension risk factor; S803: Input the ground clearance of low-altitude aviation activities and the density of surrounding buildings from the multi-source standard data into the geodetic model to obtain the geodetic risk factor.

[0051] It is understood that the embodiments of this application analyze star-dimensional risk, celestial risk and terrestrial risk, and generate star-dimensional risk factors, celestial risk factors and terrestrial risk factors respectively.

[0052] See Figure 9 Star-dimensional risk analysis: "star F satellite "Measure the operational risks associated with a satellite navigation system (GNSS), such as GNSS signal quality (expressed as horizontal HDOP and vertical accuracy attenuation factor VDOP, respectively) and the number of satellites successfully locked by the UAV." n satellites and GNSS interference (defined as the number of times GNSS signals are interfered with or interrupted for more than 30 minutes). n downtime express).

[0053]

[0054] n satellites Based on knowledge data, this represents the number of satellites that the UAV has locked onto. It is negatively correlated with the probability of an accident. Therefore, the fewer satellites that have been locked onto, the worse the positioning stability and navigation safety of the UAV, and the higher the possibility of track deviation, obstacle avoidance failure, or loss of control accidents. f nsatellites ( n satellites (Also represented as) f ( n satellites This measure is used to assess the impact of the number of locked satellites on the risk of star dimension; the more satellites locked, the lower the risk. w nsatellites Decide f ( n satellites The degree of impact on star-dimensional risk is indicated by a higher numerical value, which represents a greater degree of impact and higher risk, and vice versa; an example is as follows:

[0055] HDOP, derived from knowledge data, is a horizontal GNSS signal accuracy attenuation factor; it is positively correlated with the probability of accidents. Therefore, a higher HDOP indicates lower reliability of the UAV's horizontal positioning, further compressing the navigation safety boundary and significantly increasing the risk of track drift, obstacle collisions, and loss of flight control. fHDOP (HDOP) (also referred to as) g (HDOP) is used to measure the impact of HDOP on star dimension risk; the higher the value, the higher the risk. w HDOP Decide g The degree of influence of (HDOP) on star dimension risk is as follows: a higher value indicates a greater influence and higher risk, and vice versa; an example is as follows:

[0056] VDOP, derived from knowledge data, is a vertical GNSS signal accuracy attenuation factor. Similar to HDOP, it is positively correlated with the probability of accidents. Therefore, the higher the VDOP, the worse the UAV's altitude positioning accuracy and vertical navigation safety, and the higher the possibility of abnormal descent, collision, or loss of control accidents. f VDOP (VDOP) (can be represented as) h (VDOP) is used to measure the impact of VDOP on star dimension risk; w VDOP Decide h The degree of influence of (VDOP) on star dimension risk is as follows: a higher value indicates a greater influence and higher risk, and vice versa; an example is as follows:

[0057] n downtime Based on knowledge data, this refers to the number of times GNSS signals are interfered with or interrupted for more than 30 minutes: it is positively correlated with the probability of accidents. Therefore, the more times this occurs, the worse the navigation safety and positioning stability of the UAV will be, and the higher the possibility of accidents such as yaw, loss of control or abnormal landing will occur. f ndowntime ( n downtime (represented as) k ( n downtime The number of times a risk level is measured affects the risk level of the star dimension; the more times a risk level is measured, the higher the risk level is. w ndowntime Decide k ( n downtime The degree of impact on star-dimensional risk is indicated by a higher numerical value, which represents a greater degree of impact and higher risk, and vice versa; an example is as follows:

[0058] See Figure 10 Risk analysis by Tianweidu: "sky F meteorology "Measure the risks of activities associated with the weather, such as rainfall." R Average wind speed Relative humidity (RH) and dew point and average (air) Temperature, and the number of hours (RV) during which visibility decreases.

[0059]

[0060] R Data from publicly available weather datasets, showing daily rainfall, shows a positive correlation with the risk of drone hardware failure and the degree of environmental perception interference. Therefore, higher rainfall significantly increases the probability of rainwater infiltration causing short circuits in motors and electronic components. At the same time, raindrops can severely interfere with lenses and sensors, and alter the aerodynamic characteristics of propellers, leading to an increased risk of attitude instability in the flight control system. f R ( R (Also represented as) f ( R This is used to measure the impact of rainfall on astronomical risk; the higher the rainfall, the higher the risk. w R Decide f ( R The degree of impact on the risk of the celestial dimension; a higher value indicates a greater degree of impact and a higher risk, and vice versa. D For use in calculation f ( R Number of days required; d One of the days is used to indicate the rainfall on that day, i.e. R ( d Its implementation examples are as follows: Based on publicly available weather datasets, daily wind speeds show a positive correlation with flight path deviation errors and environmental collision risks. Therefore, higher wind speeds significantly increase the likelihood of drones drifting due to crosswinds and wind shear. When near buildings or in narrow airspace, strong winds not only reduce the reaction time of obstacle avoidance systems but also greatly increase the probability of pushing drones towards physical obstacles, leading to devastating collisions. (represented as) g ( The impact of wind speed on celestial risk is measured; higher wind speeds result in higher risks. Decide g ( The degree of impact on the risk of the celestial dimension; a higher value indicates a greater degree of impact and a higher risk, and vice versa. D For use in calculation g ( Number of days required; d One of the days, used to indicate the wind speed on a particular day, i.e. ( d Its implementation examples are as follows: dew , The data comes from publicly available weather datasets, which show the average dew point temperature and the average temperature. The difference between these two temperatures is positively correlated with the environmental meteorological risk level and the probability of system failure. Therefore, the smaller the difference between the average temperature and the dew point temperature (when the air is close to saturation), the more likely the flight environment will experience low visibility and dense fog, leading to condensation on the drone's obstacle avoidance sensors and electronic components. This reduces the system's environmental perception and collision avoidance capabilities. At the same time, extreme temperature differences will severely weaken battery life and motor efficiency, reducing flight mission safety and exposing the drone to a very high risk of power exhaustion and loss of control crashes in emergency situations. f dew, ( dew , (represented as) h ( dew , The difference between the two measures the impact of temperature on celestial risk (expressed as...). The smaller the value, the higher the risk; , Decide h ( dew , The degree of impact on the risk of the celestial dimension; a higher value indicates a greater degree of impact and a higher risk, and vice versa. D For use in calculation h ( dew , Number of days required; d One of the days, used to mark a certain day Δ , that is, Δ ( d Its implementation examples are as follows:

[0061] RH and RV are derived from publicly available weather datasets, representing relative humidity and hours of reduced visibility, respectively. They are positively correlated with accident probability and flight environment risk. Therefore, higher relative humidity and longer hours of reduced visibility indicate a more unfavorable flight environment for drones to maintain stable perception and safe operation, thereby increasing the risk of collisions, loss of control, and abnormal landings. f RH, RV (RH, RV) (represented as) k (RH, RV) measures the impact of both on the risk of visibility at different times; the higher the humidity and the longer the duration of reduced visibility, the higher the risk. w RH, RV Decide k (RH, RV) represents the degree of impact on the risk of the celestial dimension. A higher value indicates a greater degree of impact and a higher risk, and vice versa. D For use in calculation k Number of days required (RH, RV); d One of the days is used to identify the RH and RV of a certain day, i.e., RH( d ) and RV ( d Its implementation examples are as follows:

[0062] See Figure 11 Geographic risk analysis: "land F ground "Measure the activity risks associated with ground features, such as UAV height." h and the building density around the UAV. D building .

[0063]

[0064] h Data from the knowledge base shows that the UAV's Above Ground Level (AGL) at each point along its route is positively correlated with its fall kinetic energy and the severity of its ground impact. Therefore, the higher the flight altitude, the longer the freefall acceleration time experienced by the UAV when it loses power or suffers structural failure, resulting in a greater terminal velocity and impact kinetic energy upon reaching the ground, thus significantly increasing the risk of secondary damage to personnel and facilities on the ground. f h ( h (represented as) f ( h The AGL (Advanced Geometric Scale) is used to measure the impact of AGL on dimensional risk; a higher AGL indicates a higher risk. w h Decidef ( h The degree of impact on the risk of dimensionality; a higher value indicates a greater degree of impact and a higher risk, and vice versa. n It is the number of points on the route; i Let this be one of the points used to label the AGL at a certain point, that is... ; h max and h min These represent the highest and lowest AGL values ​​for the overall route; an example is as follows:

[0065] D building Data from a publicly available dataset on building density distribution within the UAV's flight path shows a positive correlation between building density and the overall risk and probability of accidents in low-altitude flight environments. Therefore, higher building density not only places UAVs under more stringent physical obstacle avoidance requirements and limited emergency landing space, but also makes them highly susceptible to signal obstruction and urban turbulence, leading to a decrease in system safety. This significantly increases the risk of in-flight instability or collisions with buildings, classifying the airspace as a high-risk operating environment. f Dbuilding ( D building (represented as) g ( D building This measures the impact of building density on latitudinal risk; higher building density results in higher risk. w Dbuilding Decide g ( D building The degree of impact on latitudinal risks is indicated by a higher numerical value, signifying a greater impact and higher risk, and vice versa. Examples are as follows:

[0066] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors.

[0067] In one embodiment, see Figure 12 The low-altitude aviation activity risk analysis model includes a dynamic dimension model, an aircraft dimension model, a time dimension model, a rule dimension model, and a scenario dimension model; the multi-dimensional risk factors include dynamic dimension risk factors, aircraft dimension risk factors, time dimension risk factors, rule dimension risk factors, and scenario dimension risk factors; the multi-source standard data is input into the pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors, including: S1201: Input the population density, traffic flow, driving speed and road conditions from the multi-source standard data into the dynamic dimension model to obtain the dynamic dimension risk factor; S1202: Input the fuselage weight, flight hours, number of past accidents, and emergency landing deployment capability from the multi-source standard data into the aircraft dimension model to obtain the aircraft dimension risk factor; S1203: Input the expected flight duration and flight time period from the multi-source standard data into the time dimension model to obtain the time dimension risk factor; S1204: Input the compliance level in the multi-source standard data into the compliance dimension model to obtain the compliance dimension risk factor; S1205: Input the potential risks of the activity nature in the multi-source standard data into the scene dimension model to obtain the scene dimension risk factor.

[0068] It is understood that the embodiments of this application analyze dynamic dimension risk, machine dimension risk, time dimension risk, rule dimension risk and scenario dimension risk, and generate dynamic dimension risk factors, machine dimension risk factors, time dimension risk factors, rule dimension risk factors and scenario dimension risk factors respectively.

[0069] See Figure 13 Dynamic risk analysis: "move F movement "Measure the activity risks associated with land, sea, and air transportation, such as population density." D population Traffic flow, vehicle speed, and road conditions (collectively referred to as...) T ).

[0070]

[0071] D population The data comes from a publicly available population density distribution dataset, which shows the population density within the UAV's flight range. This data is positively correlated with the probability of injury or death to people on the ground and the severity of accidents. The higher the population density within the flight range, the greater the probability that the UAV's trajectory will collide with unprotected people on the ground when it experiences power failure or goes out of control and crashes, thus increasing the risk of injury or death. f Dpopulation (represented as) f ( D population This measures the impact of population density on dynamic risk; higher density generally equates to higher risk. w Dpopulation Decide f ( Dpopulation The degree of impact on dynamic dimension risk is indicated by a higher numerical value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0072] T The data comes from a publicly available traffic condition dataset, which shows that regional traffic usage is positively correlated with the risk of secondary ground accidents and the complexity of emergency response. Therefore, the higher the level of regional traffic usage, the higher the likelihood that a UAV will physically collide with ground vehicles, block existing traffic flow, or interfere with ground rescue and recovery operations if it loses control, makes an emergency landing, or crashes. f T ( T (represented as) g ( T The impact of regional traffic usage on dynamic risk is measured; the higher the usage level, the higher the risk. w T Decide g ( T The degree of impact on dynamic dimension risk is indicated by a higher numerical value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0073] See Figure 14 Machine-based risk analysis: "machine F UAV Measuring the risks associated with UAV activities, such as the weight of the aircraft. W Flight hours H UAV UAV battery usage hours H battery Number of past accidents n incidents and emergency landing deployment capabilities E .

[0074]

[0075] W According to knowledge data, this refers to the weight of the UAV (if the activity type requires a payload, its weight needs to be added): it is positively correlated with the probability of an accident. Therefore, if the weight is greater, not only will the aerodynamic control during flight become more difficult, but once loss of control occurs, the kinetic energy it carries will be greater, and the substantial damage and severity of the accident will also increase significantly. f W ( W (represented as) f ( WThe impact of UAV weight on dimensional risk is measured; the greater the weight, the higher the risk. w W Decide f ( W The degree of impact on machine-level risk is indicated by a higher numerical value, signifying a greater impact and higher risk, and vice versa. An example is as follows:

[0076] H UAV According to knowledge data, the age of the UAV is positively correlated with the probability of accidents. The older the UAV is, the more likely it is to enter the wear-out phase of its equipment life cycle. The aging of various components and the mechanical fatigue effect combine to significantly increase the possibility of in-flight instability or fatal failure. f HUAV ( H UAV (represented as) g ( H UAV The impact of aircraft age on aircraft-related risks is measured; the older the aircraft, the higher the relative risk. w HUAV Decide g ( H UAV The degree of impact on machine-level risks is indicated by a higher value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0077] H battery According to knowledge data, the age of a UAV battery is positively correlated with the probability of an accident. Therefore, the older the battery, the worse its usable capacity, discharge stability, and continuous power supply capability. This makes the UAV more prone to insufficient range, transient voltage anomalies, or insufficient power support during flight, thereby increasing the risk of loss of control, forced landing, or crash. f Hbattery ( H battery (represented as) h ( H battery This measures the impact of battery age on machine-level risks; the older the battery, the higher the risk. w Hbattery Decide h ( H battery The degree of impact on machine-level risks is indicated by a higher value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0078] n incidents The data comes from knowledge data, which shows the number of past accidents involving UAVs. It is positively correlated with the accident probability. If a UAV has had multiple accidents in the past, it indicates that there may be inherent defects in the underlying hardware of the device, or that the overall structure has become less resistant to disturbances due to multiple abnormal impacts. Its power output and flight control attitude are more likely to be abnormal during flight, thus increasing the future failure rate. f nincidents ( n incidents (represented as) k ( n incidents This measures the impact of the number of accidents on the risk level; the more accidents, the higher the risk. w nincidents Decide k ( n incidents The degree of impact on machine-level risks is indicated by a higher value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0079] E Based on knowledge data, the UAV's emergency landing deployment capability is represented by 0 (no) or 1 (yes): it is negatively correlated with the overall destructive power of a crash. If it possesses emergency landing deployment capability ( E =1), which can effectively slow down the descent speed during a sudden fall, not only protecting the core payload and fuselage, but also significantly reducing secondary physical damage to the environment. f E ( E (represented as) m ( E Measuring the impact of parachute deployment capability on aircraft-level risks. E =0 indicates low risk. E =1 indicates high risk; w E Decide m ( E The degree of impact on machine-level risks is indicated by a higher value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0080] See Figure 15 Time-based risk analysis: "hour F time"Measure the risks associated with the timing of the flight, such as the expected flight duration Δ" t and flight time d (During the day or at night).

[0081]

[0082] d Based on knowledge data, specifically UAV flight times (measured in 24-hour timeframes): these times are positively correlated with accident probability, meaning the probability of accidents occurring at night should be higher than during the day due to poorer lighting conditions. d ( d (represented as) f ( d The risk of different flight times is measured. For example, if the activity is carried out at night, the risk is 1 (high), and if it is carried out during the day, the risk is 0 (low). w d Decide f ( d The degree of impact on time-related risks is indicated by a higher numerical value, signifying a greater impact and higher risk, and vice versa. An example is shown below:

[0083] Δ t Based on knowledge data, which is the flight duration during the activity (measured in hours): it is positively correlated with the probability of accidents. Therefore, the longer the flight duration, the greater the risk of system degradation and exposure to complex external environments that accumulate over time, and the higher the possibility of flight failure or attitude instability. f Δt (Δ t (represented as) g (Δ t This measures the impact of flight duration on temporal risk; the longer the flight, the higher the risk. w Δt Decide g (Δ t The degree of impact on time-related risks is indicated by a higher numerical value, signifying a greater impact and higher risk, and vice versa. An example is shown below:

[0084] See Figure 16 Risk analysis across regulatory dimensions: "regulation F regulations"Measure the risks associated with activities that are close to violating relevant regulations. For example, the algorithm will check whether the UAV is near a No-fly Zone (NFZ) and whether the UAV's speed is close to or exceeds the prescribed flight speed." C A set of regulations governing flight areas; k Used to indicate one of the regulations C ( k )(Right now r n )and w k This is used to assess the extent of non-compliance in low-altitude aviation distance activities; f C(k) ( C ( k )) Measurement C One of the regulations r n The further away from non-compliance, the higher the risk. w k Decide f C(k) ( C ( k The degree of impact on regulatory risk is indicated by a higher numerical value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0085] Taking the two regulations mentioned above as examples: r 1 is C One of the regulations states whether UAVs are near NFZ. p UAV This indicates one point on the UAV's flight path. p NFZ This represents a point on the edge of NFZ. f C(1) ( C (1)) (represented as f r1 ( r 1, p UAV , p NFZ ) ) Measure whether the distance between two points exceeds the upper limit. d critical,r1 If it is present, it is 1, which means high risk; otherwise, it is not. w 1. Decision f C(1) ( C(1) The degree of impact on the risk of regulatory dimensions. A higher value indicates a greater degree of impact and a higher risk, and vice versa. An example is as follows:

[0086] r 2 indicates whether the UAV was speeding. v UAV Indicates UAV flight speed, v critical,r2 Indicates the upper limit of flight speed. f C(2) ( C (2)) (represented as f r 2( r 2, v UAV ) ) Measurement v UAV Has it exceeded v critical,r2 If present, the value is 1, indicating high risk; w 2 Decisions f r2 ( r 2, v UAV The degree of impact on regulatory risk is indicated by a higher numerical value, which represents a greater degree of impact and higher risk, and vice versa. An example is shown below:

[0087] See Figure 17 Scene-dimensional risk analysis: "scene F scenarios "Measure the risks associated with the nature of the activity, such as whether the purpose of the activity is tourism, surveying, or drone performance, because each type of activity involves different risk levels and types." S This is a set of potential sub-risks that may occur in specific activity types. Actual activity types include sightseeing, photography, surveying, drone performances, drone racing, and exterior wall cleaning. Potential sub-risks include the number of manual adjustments to the UAV during flight, changes in the physical characteristics of the UAV during flight, and the type of payload carried (e.g., high-value and perishable goods). n for S The number of potential sub-risks; m Used to represent one of the potential sub-risks, i.e. S ( m ), until S ( n ); f S(m) ( S (m )) Measurement S ( m The more dangerous the type or potential sub-wind side, the higher the risk. w m Decide f S(m) ( S ( m The degree of impact of the scene dimension risk; a higher value indicates a greater degree of impact and higher risk, and vice versa.

[0088] The embodiments are as follows:

[0089] S This data, derived from knowledge data, represents a set of potential sub-risks for a specific type of activity. For example, freight transportation. s For example, one potential sub-risk includes the number of times the UAV needs to be manually adjusted during flight. n adjust Type of payload carried L (For example, perishable goods are represented by 1; high-value goods are represented by 2; and highly dangerous goods such as chemical substances are represented by 3). n adjust It is positively correlated with the probability of accidents. If the flight route or status of the UAV is adjusted multiple times during the flight, the possibility of anomalies or accidents during the flight mission is higher. f S(1) ( S (1)) (represented as f s1,nadjust ( s 1, n adjust )) To measure the impact of the number of manual adjustments to UAVs on scene dimensional risk, while n threshold,s1 The maximum number of attempts can be manually adjusted. Once exceeded, this potential risk will be set to 1, indicating a high risk. L It is positively correlated with the level of risk; the more valuable or dangerous the goods are, the greater the chance of them being lost or involved in an accident. f S(2) ( S (2)) (represented as f s2,L ( s 2, L )) Measure the impact of cargo type on scene dimension risk; w 1 and w 2. Decide separately f s1, nadjust ( s 1, n adjust ) and f s2 , L ( s 2 , L The degree of impact of the scene dimension risk is indicated by a higher value, which represents a greater degree of impact and higher risk, and vice versa; an example is as follows:

[0090] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors.

[0091] In one embodiment, the low-altitude aviation activity risk analysis model includes a human-dimensional model; the multi-dimensional risk factors include human-dimensional risk factors; the step of inputting the multi-source standard data into the pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors includes: The human-dimensional risk factor is determined based on the operator's qualifications, flight hours, number of historical accidents, and the human-dimensional model in the multi-source standard data.

[0092] It is understood that the embodiments of this application analyze human-dimensional risks and generate human-dimensional risk factors.

[0093] See Figure 18 Human-based risk analysis: "people F man "Measure the risks associated with human resources activities, such as operator qualifications and certifications." Q ,age A Flight hours H man Number of past claims n claims And whether the activity involves stunts or dangerous flying maneuvers. M .

[0094]

[0095] Q It comes from knowledge data, which is a collection of checks to see if operators have regional official certification qualifications. Q ( n This is one of the qualifications, such as an advanced drone pilot certificate. Q =1, otherwise Q=0: All qualifications are positively correlated with the probability of an accident. If an operator operates this type of UAV without an advanced UAV pilot certificate, the probability of an accident should be higher, and vice versa. f Q (Q) (represented as) f ( Q )) Measure the impact of operator-acquired or unacquired certifications on human-dimensional risk; w Q Decide f ( Q The degree of impact on human-level risk; a higher value indicates a greater degree of impact and higher risk, and vice versa. Q |for Q Size; n Used to identify one of the qualifications. Q ( n ), until Q (| Q |); its implementation is as follows:

[0096] M Based on knowledge data, this is an activity hazard assessment value: it is positively correlated with the probability of an accident, meaning the more dangerous the actions, the higher the probability of an accident; if the activity involves stunts or dangerous actions, then... M =1, otherwise M =0. f M ( M (represented as) g ( M ) ) To measure the impact of risk level on human-dimensional risk; w M Decide g ( M The degree of impact on human-level risks; a higher value indicates a greater degree of impact and higher risk, and vice versa. Examples are as follows:

[0097] n claims The data comes from knowledge data, which shows the number of claims an operator has made in the past: the number of claims is positively correlated with the probability of an accident, so the more claims an operator has made, the higher the probability of an accident occurring in the future, and the greater the likelihood of being classified as a high-risk individual. f nclaims ( n claims (represented as) h ( n claims )) Measure the impact of frequency on human-dimensional risk; wnclaims Decide h ( n claims The degree of impact on human-level risks; a higher value indicates a greater degree of impact and higher risk, and vice versa. Examples are as follows:

[0098] H man Based on knowledge data, this refers to the operator's UAV flight hours: the number of hours is positively correlated with the probability of an accident. Therefore, the longer the flight hours, the higher the operator's emergency response capability should be, and the lower the risk of operational accidents during the activity should be. f Hman ( H man (represented as) k ( H man ) ) Measure the impact of duration on human-dimensional risk; w Hman Decide k ( H man The degree of impact on human-level risks; a higher value indicates a greater degree of impact and higher risk, and vice versa. Examples are as follows:

[0099] A According to knowledge data, the operator's age is positively correlated with the probability of accidents when the age is outside a certain range (such as outside the range of 23 to 65 years old as shown in the formula below). If the age is low, the operator's ability to respond to emergencies may be low, and the probability of accidents may be high. f A ( A (represented as) m ( A )) To measure the impact of age on individual risk; w A Decide m ( A The degree of impact on human-level risks; a higher value indicates a greater degree of impact and higher risk, and vice versa. Examples are as follows:

[0100] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors.

[0101] In one embodiment, see Figure 19The generation of low-altitude aviation activity safety trajectories based on the multi-dimensional risk factors includes: S1901: Calculate the total risk factor based on the multi-dimensional risk factors and their corresponding risk factor weights; S1902: Determine whether the risk of low-altitude aviation activities is greater than the safety threshold based on the total risk factor and the safety threshold; S1903: If so, adjust the active data in the multi-source standard data; S1904: Generate the low-altitude aviation activity safety trajectory based on multi-source standard data containing the active data.

[0102] It is understood that the embodiments of this application utilize AI technology to analyze the risk value of low-altitude drone flight activities. This allows for continuous optimization of the risk identification model based on input data, and automatic identification of potential risk patterns hidden in data such as flight environment, equipment status, and mission type. Compared to the current assessment process that relies on manual verification of flight data item by item, this algorithm can automatically process multi-dimensional input data, significantly simplifying the assessment process, improving the efficiency of risk assessment, and enhancing the accuracy of risk prediction through continuous training mechanisms using machine learning.

[0103] Furthermore, the expert system used by the algorithm calculates flight risks through a predefined set of rules, and can output human-readable decision results. This makes the entire assessment logic fully traceable, and allows direct access to the specific rule paths on which the algorithm derived each risk decision, thereby effectively meeting the technical requirements of regulatory agencies for transparency in automated decision-making.

[0104] Specifically, after obtaining multi-dimensional risk factors, a weighted summation is performed based on the weights of each factor to calculate the total risk factor, which serves as a quantitative indicator of the overall risk level of low-altitude aviation activities. Then, this total risk factor is compared with a preset safety threshold. If the current risk exceeds the threshold, an adjustment mechanism is triggered to correct the active data (parameters that can be actively adjusted by the system or operator) in the multi-source standard data to reduce the risk. Finally, based on the complete standard dataset containing the adjusted active data, a safe trajectory for low-altitude aviation activities is regenerated. This process achieves a progressive decision-making closed loop from risk quantification and threshold judgment to parameter optimization and trajectory reconstruction, ensuring that feasible and safe flight plans can be output in a timely manner under high-risk scenarios.

[0105] This algorithm can also be integrated as a technical module into downstream applications of the low-altitude aviation risk scoring system, providing accurate, objective and consistent numerical data for scenarios that require the output of risk quantification results.

[0106] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can generate a low-altitude aviation activity safety trajectory based on the multi-dimensional risk factors.

[0107] Based on the same inventive concept, this application also provides a low-altitude aviation activity risk prediction device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of the low-altitude aviation activity risk prediction device in solving the problem is similar to that of the low-altitude aviation activity risk prediction method, the implementation of the low-altitude aviation activity risk prediction device can refer to the implementation of the software performance benchmark determination method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0108] In one embodiment, see Figure 20 In order to analyze the potential risks in low-altitude aviation activities based on data such as the flight environment, equipment status, and mission type, and to generate a safe trajectory for low-altitude aviation activities, this application provides a low-altitude aviation activity risk prediction device, comprising: The standard data generation unit 2001 is used to preprocess the acquired low-altitude aviation activity flight data and knowledge data to obtain multi-source standard data. The risk factor generation unit 2002 is used to input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors. The activity risk analysis unit 2003 is used to generate a low-altitude aviation activity safety trajectory based on the multi-dimensional risk factors.

[0109] From a hardware perspective, in order to analyze the potential risks in low-altitude aviation activities based on data such as the flight environment, equipment status, and mission type corresponding to low-altitude aviation activities, and to generate a safe trajectory for low-altitude aviation activities, this application provides an embodiment of an electronic device for implementing all or part of the aforementioned low-altitude aviation activity risk prediction method. The electronic device specifically includes the following components: The system comprises a processor, a memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to transmit information between the low-altitude aviation activity risk prediction device and core business systems, user terminals, and related databases and other related equipment; the logic controller can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the logic controller can be implemented with reference to the embodiments of the low-altitude aviation activity risk prediction method and the low-altitude aviation activity risk prediction device in the embodiments, the content of which is incorporated herein, and repeated details will not be described again.

[0110] It is understood that the user terminal may include smartphones, tablet computers, network set-top boxes, portable computers, desktop computers, personal digital assistants (PDAs), in-vehicle devices, smart wearable devices, etc. Among these, the smart wearable devices may include smart glasses, smartwatches, smart bracelets, etc.

[0111] In practical applications, parts of the low-altitude aviation activity risk prediction method can be executed on the electronic device side as described above, or all operations can be completed in the client device. The choice can be made based on the processing power of the client device and the limitations of the user's usage scenario. This application does not impose any limitations on this. If all operations are completed in the client device, the client device may further include a processor.

[0112] The aforementioned client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission. The server may include a server on the task scheduling center side; in other implementation scenarios, it may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a distributed server structure.

[0113] Figure 21 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 21 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 21 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0114] In one embodiment, the low-altitude aviation activity risk prediction method function can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control: S101: Preprocess the acquired low-altitude aviation activity flight data and knowledge data to obtain multi-source standard data; S102: Input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein, the low-altitude aviation activity risk analysis model is used to perform low-altitude aviation activity risk analysis on the multi-source standard data in various dimensions. S103: If the risk of low-altitude aviation activities is determined to be greater than the preset safety threshold based on the multi-dimensional risk factors, a low-altitude aviation activity safety trajectory is generated based on the adjusted multi-source standard data.

[0115] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can accelerate the calculation of risk coefficients, fully automate the process without the need for traditional manual review procedures, establish objective, consistent and standardized algorithm parameters to accurately reflect the risks involved in each activity and reduce the subjectivity of human judgment, and generate low-altitude aviation activity safety trajectories based on risk analysis results.

[0116] In another embodiment, the low-altitude aviation activity risk prediction device can be configured separately from the central processing unit 9100. For example, the low-altitude aviation activity risk prediction device can be configured as a chip connected to the central processing unit 9100, and the function of the low-altitude aviation activity risk prediction method can be realized through the control of the central processing unit.

[0117] like Figure 21 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 21 All components shown; in addition, the electronic device 9600 may also include Figure 21 For components not shown, please refer to existing technologies.

[0118] like Figure 21 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device, which receives inputs and controls the operation of various components of the electronic device 9600.

[0119] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0120] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input device. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0121] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0122] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0123] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which is the same as in a conventional mobile communication terminal.

[0124] Based on different communication technologies, multiple communication modules 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is also coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored sound via the speaker 9131.

[0125] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the low-altitude aviation activity risk prediction method with a server or client as the execution subject in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the low-altitude aviation activity risk prediction method with a server or client as the execution subject in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: S101: Preprocess the acquired low-altitude aviation activity flight data and knowledge data to obtain multi-source standard data; S102: Input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein, the low-altitude aviation activity risk analysis model is used to perform low-altitude aviation activity risk analysis on the multi-source standard data in various dimensions. S103: If the risk of low-altitude aviation activities is determined to be greater than the preset safety threshold based on the multi-dimensional risk factors, a low-altitude aviation activity safety trajectory is generated based on the adjusted multi-source standard data.

[0126] As can be seen from the above description, the low-altitude aviation activity risk prediction method provided in this application can accelerate the calculation of risk coefficients, fully automate the process without the need for traditional manual review procedures, establish objective, consistent and standardized algorithm parameters to accurately reflect the risks involved in each activity and reduce the subjectivity of human judgment, and generate low-altitude aviation activity safety trajectories based on risk analysis results.

[0127] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0130] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0131] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for predicting the risks of low-altitude aviation activities, characterized in that, include: The acquired low-altitude aviation flight data and knowledge data are preprocessed to obtain multi-source standard data; The multi-source standard data is input into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein, the low-altitude aviation activity risk analysis model is used to perform low-altitude aviation activity risk analysis on the multi-source standard data in various dimensions. If the risk of low-altitude aviation activities is determined to be greater than the preset safety threshold based on the multi-dimensional risk factors, a low-altitude aviation activity safety trajectory is generated based on the adjusted multi-source standard data.

2. The method for predicting the risk of low-altitude aviation activities according to claim 1, characterized in that, The preprocessing of the acquired low-altitude flight data and knowledge data yields multi-source standard data, including: Anomaly and missing data are detected in the low-altitude aviation flight data and knowledge data to obtain abnormal data and missing data. After removing the abnormal data, the missing data is filled by linear interpolation to obtain complete data; The complete data is time-series aligned to obtain the multi-source standard data.

3. The method for predicting the risk of low-altitude aviation activities according to claim 1, characterized in that, The low-altitude aviation activity risk analysis model includes a star-dimensional model, a sky-dimensional model, and a ground-dimensional model; the multi-dimensional risk factors include star-dimensional risk factors, sky-dimensional risk factors, and ground-dimensional risk factors; the process of inputting the multi-source standard data into the pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors includes: The satellite signal quality, number of locked satellites, and number of satellite signal interferences from the multi-source standard data are input into the star dimension model to obtain the star dimension risk factor; The rainfall, average wind speed, atmospheric relative humidity, dew point, average atmospheric temperature, and atmospheric visibility during low-altitude aviation activities from the multi-source standard data are input into the sky dimension model to obtain the sky dimension risk factor. By inputting the ground-level altitude of low-altitude aviation activities and the density of surrounding buildings from the multi-source standard data into the geodetic model, the geodetic risk factor is obtained.

4. The method for predicting the risk of low-altitude aviation activities according to claim 1, characterized in that, The low-altitude aviation activity risk analysis model includes a dynamic dimension model, an aircraft dimension model, a time dimension model, a rule dimension model, and a scenario dimension model; the multi-dimensional risk factors include dynamic dimension risk factors, aircraft dimension risk factors, time dimension risk factors, rule dimension risk factors, and scenario dimension risk factors. The process involves inputting the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors, including: Population density, traffic flow, driving speed and road conditions from the multi-source standard data are input into the dynamic dimension model to obtain the dynamic dimension risk factor; The aircraft weight, flight hours, number of past incidents, and emergency landing deployment capability from the multi-source standard data are input into the aircraft-dimensional model to obtain the aircraft-dimensional risk factor. The estimated flight duration and flight time period from the multi-source standard data are input into the time-dimensional model to obtain the time-dimensional risk factor; The compliance level in the multi-source standard data is input into the compliance dimension model to obtain the compliance dimension risk factor; The potential risks of the activities in the multi-source standard data are input into the scene dimension model to obtain the scene dimension risk factor.

5. The method for predicting the risk of low-altitude aviation activities according to claim 1, characterized in that, The low-altitude aviation activity risk analysis model includes a human-dimensional model; the multi-dimensional risk factors include human-dimensional risk factors; the process of inputting the multi-source standard data into the pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors includes: The human-dimensional risk factor is determined based on the operator's qualifications, flight hours, number of historical accidents, and the human-dimensional model in the multi-source standard data.

6. The method for predicting the risk of low-altitude aviation activities according to claim 1, characterized in that, If the risk of low-altitude aviation activity is determined to be greater than a preset safety threshold based on the multi-dimensional risk factors, a low-altitude aviation activity safety trajectory is generated based on the adjusted multi-source standard data, including: The total risk factor is calculated based on the multi-dimensional risk factors and their corresponding risk factor weights. Determine whether the risk of low-altitude aviation activities exceeds the safety threshold based on the total risk factor and the safety threshold. If so, adjust the variable parameters in the multi-source standard data; The low-altitude aviation activity safety trajectory is generated based on multi-source standard data containing the variable parameters.

7. A low-altitude aviation activity risk prediction device, characterized in that, include: The standard data generation unit is used to preprocess the acquired low-altitude aviation flight data and knowledge data to obtain multi-source standard data. The risk factor generation unit is used to input the multi-source standard data into a pre-constructed low-altitude aviation activity risk analysis model to obtain multi-dimensional risk factors; wherein, the low-altitude aviation activity risk analysis model is used to perform low-altitude aviation activity risk analysis on the multi-source standard data in various dimensions. The activity risk analysis unit is used to generate a low-altitude aviation activity safety trajectory based on the adjusted multi-source standard data if the risk of low-altitude aviation activity is determined to be greater than a preset safety threshold based on the multi-dimensional risk factors.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the low-altitude aviation activity risk prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the low-altitude aviation activity risk prediction method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the low-altitude aviation activity risk prediction method according to any one of claims 1 to 6.

Images