Method and system for sky path planning design based on artificial intelligence algorithm

Abstract

The invention discloses a sky path planning design method and system based on an artificial intelligence algorithm, and relates to the technical field of unmanned aerial vehicles, and the technical scheme is characterized by comprising the following steps: obtaining environment data of a flight area of an unmanned aerial vehicle, and obtaining environment condition data of the flight area according to the environment data; setting a sub-planning area of the unmanned aerial vehicle according to the environmental condition data, and setting a planning parameter and a planning weight corresponding to the sub-planning area; real-time monitoring parameters of the sub-planning areas are collected, and sub-area planning coefficients of the sub-planning areas are obtained according to the real-time monitoring parameters, the planning parameters and the planning weights; performing comparative analysis on the sub-region planning coefficient and a preset planning coefficient threshold to obtain a first high-risk sub-planning region; obtaining a first high-risk area factor corresponding to the first high-risk sub-planning area; and obtaining the influence area factor of the first high-risk area factor according to the area correlation model, so that the unmanned aerial vehicle can actively avoid the path during planning, and is prevented from falling into a high-risk environment.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and more specifically, to a method and system for air route planning and design based on artificial intelligence algorithms. Background Technology

[0002] With the increasingly widespread application of drones, flight path planning and design have become a crucial link in ensuring the efficient and safe execution of drone missions. Traditional planning methods are ill-suited to the complex and ever-changing flight environment. Due to the constant changes in terrain, weather, and obstacles, simple preset paths cannot respond flexibly. Traditional methods often focus on risks in the current area, ignoring the cross-regional transmission of risks. For example, if a certain area is at high risk due to obstacles, its impact may be transmitted to surrounding areas through airflow and terrain. Traditional planning fails to identify such transmission risks, thus easily leading drones into unknown high-risk environments. Summary of the Invention

[0003] In view of the shortcomings of existing technologies, the purpose of this invention is to provide a method and system for planning and designing skyways based on artificial intelligence algorithms.

[0004] To achieve the above objectives, the present invention provides the following technical solution: A method for planning and designing sky roads based on artificial intelligence algorithms, comprising the following steps: Acquire environmental data of the drone's flight area, and obtain environmental condition data of the flight area based on the environmental data; set sub-planning areas for the drone based on the environmental condition data, and set the corresponding planning parameters and planning weights for the sub-planning areas; Real-time monitoring parameters of the sub-planning area are collected, and the sub-area planning coefficient of the sub-planning area is obtained based on the real-time monitoring parameters, planning parameters and planning weights; the sub-area planning coefficient is compared and analyzed with the preset planning coefficient threshold to obtain the first high-risk sub-planning area. Obtain the first high-risk area factor corresponding to the first high-risk sub-planning area; obtain the influence area factor of the first high-risk area factor based on the regional correlation model; and obtain the risk impact coefficient of the first high-risk area factor on the influence area factor based on the regional correlation model. The comprehensive planning coefficient of the influencing factors is obtained by subtracting the risk impact coefficient and the sub-regional planning coefficient. The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first and second high-risk regional factors. The optimal sky route planning path for UAVs is generated based on the sky route planning evaluation coefficient.

[0005] Preferably, the method further includes the following steps: Generate regional factors based on the sub-planning areas of the UAV flight area; Obtain the regional association paths of the sub-planning area; Generate factor correlation channels and channel influence coefficients between regional factors based on regional correlation paths; A regional correlation model is constructed based on regional factors, factor correlation channels, and channel influence coefficients.

[0006] Preferably, obtaining environmental condition data for the flight area based on environmental data specifically includes the following steps: Establish environmental classification standards; Based on environmental classification standards and environmental data, the environmental types included in the drone flight area and the area proportion of each environmental type are obtained. The environmental type and the area percentage corresponding to the environmental type constitute the environmental status data.

[0007] Preferably, the sub-planning area of ​​the UAV is set based on environmental condition data, and the planning parameters and planning weights corresponding to the sub-planning area are set, specifically including the following steps: Sub-planning areas for drones are set up based on environmental type and the area proportion corresponding to the environmental type; Set the planning parameters and planning weights for the sub-planning areas according to the environmental type.

[0008] Preferably, the sub-regional planning coefficient of the sub-planning area is obtained based on real-time monitoring parameters, planning parameters, and planning weights, specifically including the following steps: The parameter deviation values ​​corresponding to the sub-planning areas are obtained based on real-time monitoring parameters and planning parameters; The sub-region planning coefficient is obtained by weighting and summing the parameter deviation values ​​corresponding to the sub-planning areas based on the planning weights.

[0009] Preferably, the first high-risk sub-planning area is obtained by comparing and analyzing the sub-region planning coefficient with a preset planning coefficient threshold, specifically including the following steps: If the planning coefficient of a sub-region is greater than or equal to the preset planning coefficient threshold, the planning risk of the sub-region is judged to be normal. If the planning coefficient of a sub-region is less than the preset planning coefficient threshold, the planning risk of the sub-region is judged to be abnormal, and the sub-region is marked as the first high-risk sub-region.

[0010] Preferably, the generation of factor correlation channels and channel influence coefficients between regional factors based on regional correlation paths specifically includes the following steps: Based on the regional association path, the adjacent sub-planning regions of the sub-planning region are obtained, and the path connectivity, path length and path environment complexity between the sub-planning region and the adjacent sub-planning regions are obtained; Based on the path connectivity, the factor pointing identifiers of the regional factors and the adjacent regional factors are obtained. Each regional factor has a factor pointing identifier. Based on the factor pointing identifiers, factor association channels between the regional factors and the adjacent regional factors are generated. The coefficients of the first channel corresponding to the factor-related channel are obtained based on the preset length influence weight and path length. Set an environment complexity set, which includes a preset complexity level and a level influence coefficient; Obtain the actual complexity level corresponding to the path environment complexity of the sub-planning area and the adjacent sub-planning area, compare the actual complexity level with the preset complexity level of the environment complexity set to obtain the preset complexity level corresponding to the actual complexity level, and record the level influence coefficient corresponding to the preset complexity level as the second channel coefficient. Set the weights for the first channel and the second channel; based on the weights and coefficients of the first channel, the weights and coefficients of the second channel, and the coefficients of the second channel, obtain the channel influence coefficients corresponding to the factor-related channels.

[0011] Preferably, the influence area factor of the first high-risk area factor is obtained based on the regional correlation model, and the risk impact coefficient of the first high-risk area factor on the influence area factor is obtained based on the regional correlation model, specifically including the following steps: Obtain the factor pointing identifier of the first high-risk area factor; Based on the factor pointing identifier, the target factor correlation channel of the first high-risk area factor is obtained; Based on the target factor correlation channel, the influence area factor corresponding to the first high-risk area factor is obtained; Obtain the factor correlation channel between the first high-risk area factor and the affected area factor, and mark the channel influence coefficient corresponding to the factor correlation channel as the target channel influence coefficient; The risk impact coefficient of the first high-risk area factor on the influencing area factor is obtained based on the target channel impact coefficient and the sub-region planning coefficient corresponding to the first high-risk area factor.

[0012] Preferably, the comprehensive planning coefficient of the influencing regional factors is compared and analyzed with a preset planning coefficient threshold to obtain the second high-risk regional factor; the air route planning evaluation coefficient of the UAV flight area is obtained based on the first and second high-risk regional factors, specifically including the following steps: If the comprehensive planning coefficient of the influencing regional factor is less than the preset planning coefficient threshold, the planning risk of the influencing regional factor is judged to be high, and the influencing regional factor is marked as the second highest risk regional factor. Obtain the first risk percentage corresponding to the first highest risk region factor in the regional correlation model; obtain the second risk percentage corresponding to the second highest risk region factor in the regional correlation model; A first risk weight and a second risk weight are set, and the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first risk weight and the first risk ratio, the second risk weight and the second risk ratio.

[0013] The system for planning and designing highways based on artificial intelligence algorithms includes: The first acquisition module acquires environmental data of the UAV's flight area, obtains environmental condition data of the flight area based on the environmental data, sets sub-planning areas for the UAV based on the environmental condition data, and sets the corresponding planning parameters and planning weights for the sub-planning areas. Data Acquisition and Comparison Module: Collects real-time monitoring parameters of the sub-planning area, and obtains the sub-region planning coefficient of the sub-planning area based on the real-time monitoring parameters, planning parameters, and planning weights; compares and analyzes the sub-region planning coefficient with the preset planning coefficient threshold to obtain the first high-risk sub-planning area; The second acquisition module: acquires the first high-risk area factor corresponding to the first high-risk sub-planning area; obtains the influence area factor of the first high-risk area factor based on the regional correlation model; and obtains the risk impact coefficient of the first high-risk area factor on the influence area factor based on the regional correlation model. Calculation module: The difference between the risk impact coefficient and the sub-region planning coefficient is processed to obtain the comprehensive planning coefficient of the factors affecting the region; Comparison and analysis module: The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first and second high-risk regional factors. Generation module: Generates the optimal skyway planning path for the UAV based on the skyway planning evaluation coefficient.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This invention acquires environmental data of the UAV flight area and sets sub-planning areas, planning parameters, and weights based on the environmental conditions, enabling the planning to fit the actual environment. For example, in flight areas with a mix of mountainous and plain areas, obstacle avoidance parameters and high weights are set for the complex terrain of mountainous areas, while parameters are adjusted for the open environment of plain areas, improving flight safety and reducing the risk of collisions with obstacles due to environmental mismatch. In terms of risk identification and early warning, the first high-risk sub-planning area is identified using sub-region planning coefficients, and the risk transmission markers for the second high-risk area are discovered through a regional correlation model, constructing a multi-level risk prevention and control network. By predicting the transmission of high temperature and strong wind risks to surrounding areas, the affected second high-risk area is marked in advance, allowing the UAV to actively avoid high-risk environments when planning its path, thereby ensuring flight safety and mission continuity. Attached Figure Description

[0015] Figure 1 A schematic diagram illustrating the skyway planning and design method based on artificial intelligence algorithms proposed in this invention; Figure 2 This is a schematic diagram illustrating the steps involved in obtaining the risk impact coefficient in the skyway planning and design method based on artificial intelligence algorithms proposed in this invention. Figure 3 This is a schematic diagram of the system modules for the skyway planning and design based on artificial intelligence algorithms proposed in this invention. Detailed Implementation

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0018] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0019] Reference Figures 1-3 As shown.

[0020] The embodiments further illustrate the method and system for skyway planning and design based on artificial intelligence algorithms proposed in this invention.

[0021] A method for planning and designing sky roads based on artificial intelligence algorithms, comprising the following steps: Acquire environmental data of the drone's flight area, and obtain environmental condition data of the flight area based on the environmental data; set sub-planning areas for the drone based on the environmental condition data, and set the corresponding planning parameters and planning weights for the sub-planning areas; Real-time monitoring parameters of the sub-planning area are collected, and the sub-area planning coefficient of the sub-planning area is obtained based on the real-time monitoring parameters, planning parameters and planning weights; the sub-area planning coefficient is compared and analyzed with the preset planning coefficient threshold to obtain the first high-risk sub-planning area. Obtain the first high-risk area factor corresponding to the first high-risk sub-planning area; obtain the influence area factor of the first high-risk area factor based on the regional correlation model; and obtain the risk impact coefficient of the first high-risk area factor on the influence area factor based on the regional correlation model. The comprehensive planning coefficient of the influencing factors is obtained by subtracting the risk impact coefficient and the sub-regional planning coefficient. The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first and second high-risk regional factors. The optimal sky route planning path for UAVs is generated based on the sky route planning evaluation coefficient.

[0022] By acquiring environmental data of the drone's flight area, the environmental conditions of the flight area are determined, such as terrain features, weather conditions, and obstacle distribution. Based on the environmental conditions, the entire flight area is rationally divided into several sub-planning areas, and planning parameters and planning weights are assigned to each sub-area. The planning parameters specify the standards that must be followed for flight in that area, such as the safe altitude under specific terrain conditions; the planning weights reflect the degree of impact of different parameters on flight risks.

[0023] Real-time monitoring parameters of the sub-planning area are collected. These parameters reflect the environmental status of the sub-planning area, such as real-time wind speed and changes in temporary obstacles. Based on the real-time monitoring parameters, planning parameters, and planning weights, the sub-area planning coefficient is obtained. The sub-area planning coefficient is a quantitative representation of the sub-area risk. The lower the sub-area planning coefficient, the higher the risk. The sub-area planning coefficient is compared with a preset planning coefficient threshold. If the sub-area planning coefficient is lower than the preset planning coefficient threshold, it indicates that the risk of the sub-area exceeds the normal acceptable range, and it is marked as the first high-risk sub-planning area.

[0024] Obtain the highest-risk regional factor corresponding to the highest-risk sub-planning area. Use a regional correlation model to identify which other regional factors this high-risk regional factor will affect, thus determining the scope of risk transmission and identifying the influencing regional factors. Simultaneously, calculate the risk impact coefficient of the highest-risk regional factor on these influencing regional factors using the regional correlation model.

[0025] The comprehensive planning coefficient of the influencing region factors is obtained by subtracting the risk impact coefficient and the sub-regional planning coefficient. The comprehensive planning coefficient integrates the original risk and the transmitted risk, and more comprehensively reflects the risk status of the affected region.

[0026] Based on the first and second highest-risk area factors, the air route planning evaluation coefficients for the UAV flight area are obtained. Taking into account the risks and environmental characteristics of each area, the optimal air route planning path for the UAV is planned. This path enables the UAV to efficiently complete its flight mission while ensuring flight safety, providing a solution for UAV flight planning.

[0027] It also includes the following steps: Generate regional factors based on the sub-planning areas of the UAV flight area; Obtain the regional association paths of the sub-planning area; Generate factor correlation channels and channel influence coefficients between regional factors based on regional correlation paths; A regional correlation model is constructed based on regional factors, factor correlation channels, and channel influence coefficients.

[0028] Key information is extracted from the environmental characteristics, spatial attributes, and functional positioning of each sub-planning area, and this information is integrated to generate regional factors.

[0029] Obtain the regional connection paths of the sub-planning areas. These paths reflect the spatial connectivity and functional interaction relationships of the sub-planning areas. For example, some sub-planning areas have direct geographical connection paths due to their proximity, while others have indirect functional connection paths due to airflow and signal factors.

[0030] Then, factor correlation channels and channel influence coefficients are generated based on the regional correlation paths. Factor correlation channels define the transmission of influence between regional factors, such as risk transmission and environmental impact transmission; the channel influence coefficient quantifies the degree of this transmission. Because different correlation paths have varying path lengths, regional environmental complexity, and correlation strength, their ability to transmit influence also differs. Each factor correlation channel receives a corresponding influence coefficient; a larger coefficient indicates a stronger influence transmitted through that channel.

[0031] A regional correlation model is constructed by integrating regional factors, factor correlation channels, and channel influence coefficients. Regional factors are nodes in the network, factor correlation channels are lines connecting the nodes, and channel influence coefficients indicate the magnitude of influence on these lines. When analyzing the impact of a high-risk regional factor on other regions, the scope and intensity of risk transmission are calculated using the pre-defined correlation channels and influence coefficients in the model.

[0032] The environmental condition data of the flight area is obtained based on environmental data, specifically including the following steps: Establish environmental classification standards; Based on environmental classification standards and environmental data, the environmental types included in the drone flight area and the area proportion of each environmental type are obtained. Among them, the environmental type and the area percentage corresponding to the environmental type constitute the environmental status data.

[0033] This application first establishes environmental classification standards. This requires combining the actual needs of drone flight with consideration of terrain, weather, and obstacle distribution to classify different environmental types, such as dividing terrain into plains, mountains, and water areas, and weather into sunny, cloudy, windy, and rainy weather.

[0034] The environmental data of the UAV flight area is processed according to the established environmental classification standards. The environmental data includes various environmental information within the flight area, such as terrain elevation data, meteorological monitoring data, and ground feature distribution data. It determines which preset environmental type each data segment belongs to and calculates the area percentage of each environmental type within the entire UAV flight area. For example, it calculates the percentage of the flight area occupied by plains and mountains, thus obtaining the environmental types included in the UAV flight area and the corresponding area percentage for each type.

[0035] Environmental type and its corresponding area proportion together constitute the environmental status data. This set of data comprehensively and clearly depicts the environmental composition of the drone flight area. Considering the impact of different environmental types on flight allows the planning to be more in line with actual environmental conditions, ensuring the safety and rationality of drone flights.

[0036] Based on environmental data, sub-planning areas for the drone are set, and corresponding planning parameters and weights are set for each sub-planning area. This includes the following steps: Sub-planning areas for drones are set up based on environmental type and the area proportion corresponding to the environmental type; Set the planning parameters and planning weights for the sub-planning areas according to the environmental type.

[0037] The environmental type in this application determines the basic flight conditions of the region. Different environments, such as mountains, plains, and water, impose vastly different restrictions and requirements on UAV flights. The area proportion corresponding to each environmental type reflects the distribution scale of each type of environment within the entire flight area. During planning, the flight area is broken down into sub-planning areas. For example, if the flight area has a large proportion of mountainous environments and complex terrain, a mountainous sub-planning area is defined based on the distribution range and characteristics of the mountainous environment; if the plains environment has a moderate proportion and open terrain, a plains sub-planning area is defined accordingly. This method ensures that each sub-planning area focuses on similar environmental types.

[0038] Different environmental types have unique flight-influencing factors. Mountainous environments focus on terrain undulation and obstacle avoidance, while plains environments focus on weather changes and signal interference. Therefore, planning parameters are customized for each sub-planning area based on the characteristics of the environmental type. For example, obstacle avoidance distance parameters and safe altitude adjustment ranges are set for mountainous sub-planning areas; suitable wind speed tolerance parameters and flight path curvature parameters are set for plains sub-planning areas. Planning weights are indicators that measure the degree of impact of different planning parameters on flight risk and efficiency. For example, obstacle avoidance-related parameters have higher weights in mountainous sub-planning areas because the risk of obstacle avoidance failure is greater; in plains areas, weather has a more prominent impact on flight, so weather-related parameters have higher weights. By setting corresponding planning parameters and weights for each sub-planning area, the planning is made more closely aligned with actual flight needs.

[0039] The sub-region planning coefficients for sub-planning areas are obtained based on real-time monitoring parameters, planning parameters, and planning weights, specifically including the following steps: The parameter deviation values ​​corresponding to the sub-planning areas are obtained based on real-time monitoring parameters and planning parameters; The sub-region planning coefficient is obtained by weighting and summing the parameter deviation values ​​corresponding to the sub-planning areas based on the planning weights.

[0040] Planning parameters are flight condition standards set for sub-planning areas based on environmental types. For example, planning parameters for a mountainous sub-planning area include a specific altitude range and obstacle avoidance distance. Real-time monitoring parameters are real-time environmental data of the sub-planning area collected by various sensors during actual drone flight, such as actual altitude and actual obstacle spacing. The difference between the real-time monitoring parameters and the planning parameters is calculated to obtain the parameter deviation value. This directly reflects the degree of deviation between the actual environment and the ideal planning conditions. For example, if the planning parameters require an obstacle avoidance distance of 5 meters, and the real-time monitoring shows an obstacle spacing of 3 meters, then the obstacle avoidance parameter deviation value is -2 meters. This method quantifies the difference in each planning parameter.

[0041] The planning weights reflect the relative importance of different planning parameters in influencing flight risk. Obstacle avoidance parameters have a greater impact on flight safety, resulting in higher weights. These deviation values ​​are weighted and accumulated according to their respective planning weights. For example, the weight for an obstacle avoidance parameter deviation is 0.6, the weight for an altitude parameter deviation is 0.3, and the weight for other parameters is 0.1. Each deviation value is multiplied by its corresponding deviation value, and then summed to obtain the sub-region planning coefficient. The sub-region planning coefficient comprehensively considers the actual deviations of all planning parameters and the degree of influence of different deviations. A higher coefficient indicates a greater deviation between the actual flight conditions in the sub-planning area and the ideal plan, providing a quantitative basis for subsequent identification of high-risk areas and optimization of planning paths.

[0042] The first high-risk sub-planning area is determined by comparing and analyzing the planning coefficients of the sub-area with preset planning coefficient thresholds. This process includes the following steps: If the planning coefficient of a sub-region is greater than or equal to the preset planning coefficient threshold, the planning risk of the sub-region is judged to be normal. If the planning coefficient of a sub-region is less than the preset planning coefficient threshold, the planning risk of the sub-region is judged to be abnormal, and the sub-region is marked as the first high-risk sub-region.

[0043] The preset planning coefficient threshold is a critical value determined based on a large amount of historical flight data, safety standards, and environmental risk assessment. When the sub-region planning coefficient is greater than or equal to this threshold, it means that the deviation between the actual flight conditions and the planning expectations is within a reasonable and safe range. If it is lower than the threshold, it means that the deviation is too large, that is, the risk exceeds the normal acceptable level.

[0044] The sub-region planning coefficient is compared with a preset planning coefficient threshold. When the sub-region planning coefficient is greater than or equal to the preset planning coefficient threshold, it indicates that the deviation between the actual flight conditions and planning parameters in the sub-planning area is within a safe and reasonable range. That is, fluctuations in various environmental factors and flight parameters do not pose a threat to flight safety.

[0045] When the planning coefficient for a sub-region is less than the preset planning coefficient threshold, it indicates that the deviation between the actual flight conditions and the planned expectations exceeds the safe and reasonable boundary. Therefore, the sub-planning region has a high potential risk, which may be due to sudden environmental changes causing excessive deviation between real-time monitoring parameters and planning parameters, or it may be that the planning parameters themselves are not adapted to the complex environment. Based on this, the planning risk of this sub-planning region is judged to be abnormal, and therefore it is marked as the highest-risk sub-planning region.

[0046] The generation of factor correlation channels and channel influence coefficients between regional factors based on regional correlation paths includes the following steps: Based on the regional association path, the adjacent sub-planning regions of the sub-planning region are obtained, and the path connectivity, path length and path environment complexity between the sub-planning region and the adjacent sub-planning regions are obtained; Based on the path connectivity, the factor pointing identifiers of regional factors and adjacent regional factors are obtained. All regional factors have factor pointing identifiers. Based on the factor pointing identifiers, factor association channels between regional factors and adjacent regional factors are generated. The coefficients of the first channel corresponding to the factor-related channel are obtained based on the preset length influence weight and path length. Set an environment complexity set, which includes a preset complexity level and a level influence coefficient; Obtain the actual complexity level corresponding to the path environment complexity of the sub-planning area and the adjacent sub-planning area, compare the actual complexity level with the preset complexity level of the environment complexity set to obtain the preset complexity level corresponding to the actual complexity level, and record the level influence coefficient corresponding to the preset complexity level as the second channel coefficient. Set the weights for the first channel and the second channel; based on the weights and coefficients of the first channel, the weights and coefficients of the second channel, and the coefficients of the second channel, obtain the channel influence coefficients corresponding to the factor-related channels.

[0047] This application determines the adjacent sub-planning areas of a sub-planning area based on the regional association path, and obtains the path connectivity, path length, and path environmental complexity between the sub-planning area and the adjacent sub-planning areas; the path length reflects the distance span between areas in spatial association; the path environmental complexity includes terrain, weather, and obstacles, which interfere with the smoothness of the transmission of influence between areas.

[0048] Based on path connectivity, factor association channels are constructed between regional factors and adjacent regional factors. Each sub-planning region corresponds to a regional factor, and the factor carries a directional identifier to clearly indicate the direction of influence transmission. This extends the connection between regions from the physical path level to the channel level of factor interaction in the model.

[0049] Based on path connectivity, factor orientation markers are determined for regional factors and adjacent regional factors, thus indicating the direction of influence transmission, such as risk transmission from regional factor A to regional factor B. Factor correlation channels between regional factors and adjacent regional factors are constructed based on these orientation markers.

[0050] The first channel coefficient is obtained using a preset length influence weight and path length. The length influence weight is determined based on historical data and reflects the degree to which path length weakens the influence transmission. The longer the path, the easier it is for the influence transmission to be weakened. The first channel coefficient reflects this weakening effect; for example, this coefficient may be relatively small when the path is very long, indicating that the channel's ability to transmit influence is weak. An environmental complexity set is set to divide environmental complexity into different preset levels, each level corresponding to a level influence coefficient. The higher the level, the stronger the interference of the environment on the influence transmission. The actual environmental complexity level of the paths in the sub-planning area and adjacent areas is obtained. The actual complexity level is compared with the preset complexity level in the environmental complexity set to obtain the preset complexity level corresponding to the actual complexity level. The influence coefficient of this level is marked as the second channel coefficient. If the actual environment is complex mountainous terrain, it corresponds to the preset high complexity level, that is, the second channel coefficient is large, thus indicating that the environment has a strong effect on the influence transmission.

[0051] First and second channel weights are set, reflecting the relative importance of path length and environmental complexity in influencing channel capability. The first and second channel coefficients are then weighted according to these weights to obtain the final channel influence coefficient. The channel influence coefficient comprehensively reflects the role of path length and environment in influence transmission, quantifying the ability of factor-related channels to transmit influence.

[0052] Suppose there are two adjacent sub-planning areas, one plain and the other mountainous, directly connected by a path. The path length is 10 kilometers. Based on the preset length influence weight, the first channel coefficient is calculated to be 0.6. The path from the mountainous area to the plain has higher environmental complexity, corresponding to a preset high complexity level, with a level influence coefficient of 0.8, meaning the second channel coefficient is 0.8. If the first channel weight is set to 0.4 and the second channel weight to 0.6, then the channel influence coefficient is 0.4 × 0.6 + 0.6 × 0.8 = 0.72. This coefficient represents the comprehensive ability of the inter-factor transmission influence between the mountainous and plain areas.

[0053] Based on the regional correlation model, the influencing regional factor of the first high-risk regional factor is obtained, and the risk impact coefficient of the first high-risk regional factor on the influencing regional factor is obtained based on the regional correlation model. The specific steps include: Obtain the factor pointing identifier of the first high-risk area factor; Based on the factor pointing identifier, the target factor correlation channel of the first high-risk area factor is obtained; Based on the target factor correlation channel, the influence area factor corresponding to the first high-risk area factor is obtained; Obtain the factor correlation channel between the first high-risk area factor and the affected area factor, and mark the channel influence coefficient corresponding to the factor correlation channel as the target channel influence coefficient; The risk impact coefficient of the first high-risk area factor on the influencing area factor is obtained based on the target channel impact coefficient and the sub-region planning coefficient corresponding to the first high-risk area factor.

[0054] Obtain the factor pointing identifier for the highest-risk area factor. This identifier includes the risk transmission direction and correlation priority. Based on the pointing identifier, use a depth-first search to filter out the correlation channels of the target factor: these channels have a clear risk transmission orientation.

[0055] For example, if a mountainous sub-planning area becomes the highest-risk area factor due to strong winds, and its factor indicates that the risk is preferentially transmitted to the plains sub-planning area in the southeast direction, then the target factor correlation channel is the transmission path from the mountains to the plains.

[0056] By leveraging the topological relationships of the target factor association channels, the influencing regional factors are located in reverse; that is, the risk transmission of the first high-risk regional factor covers the corresponding regional factors in other sub-planning areas. These factors are associated with the first high-risk regional factor through the target channel.

[0057] For example, by using the target channel from mountains to plains, the plain factor corresponding to the plain sub-planning area is identified as the influencing regional factor, thus clarifying the target of risk transmission.

[0058] We obtain the factor correlation channel between the highest-risk area factor and the affected area factor, and extract the corresponding channel influence coefficient. This coefficient characterizes the strength of risk transmission from the highest-risk area factor to the affected area factor; the higher the coefficient, the more significant the risk transmission impact.

[0059] The risk impact coefficient is calculated by combining the influence coefficient of the fusion channel with the sub-regional planning coefficient of the first high-risk area factor. This is done using the formula... The risk impact coefficient R is calculated, where C is the channel impact coefficient and P is the sub-regional planning coefficient of the first high-risk area factor. This coefficient quantifies the risk transmission intensity of the first high-risk area factor to the influencing area factor. The higher the original risk and the stronger the channel transmission capacity, the larger the risk impact coefficient, and the higher the potential risk of the influencing area factor.

[0060] The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; based on the first and second high-risk regional factors, the air route planning evaluation coefficient of the UAV flight area is obtained, specifically including the following steps: If the comprehensive planning coefficient of the influencing regional factor is less than the preset planning coefficient threshold, the planning risk of the influencing regional factor is judged to be high, and the influencing regional factor is marked as the second highest risk regional factor. Obtain the first risk percentage corresponding to the first highest risk region factor in the regional correlation model; obtain the second risk percentage corresponding to the second highest risk region factor in the regional correlation model; A first risk weight and a second risk weight are set, and the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first risk weight and the first risk ratio, the second risk weight and the second risk ratio.

[0061] This application compares the comprehensive planning coefficient of the regional factor with the preset planning coefficient threshold. If the comprehensive planning coefficient is less than the preset planning coefficient threshold, it is determined that the planning risk is high and marked as the second highest risk regional factor.

[0062] For example, the comprehensive planning coefficient of the plain sub-planning area is 0.3, and the preset planning coefficient threshold is 0.5, indicating that the risk exceeds the acceptable range after being transmitted by the high-risk factor of the mountainous area, and it is marked as the second highest risk area factor.

[0063] The first risk percentage represents the proportion of the highest-risk area factor in the overall Tianlu planning risk, while the second risk percentage represents the proportion of the second-highest-risk area factor in the overall risk. The first risk weight emphasizes the actual risk impact of the highest-risk area factor, while the second risk weight emphasizes the transmitted risk impact of the second-highest-risk area factor. The combination of weights and percentages reflects the differentiated impact of fundamental and transmitted risks in actual planning.

[0064] The evaluation coefficient for the Skyway planning is obtained by weighted calculation, which integrates the risk proportion and the weight value: (using the formula...) The evaluation coefficient E for the Tianlu planning was calculated, where w1 is the first risk weight and R1 is the proportion of the first risk; w2 is the second risk weight and R2 is the proportion of the second risk. The evaluation coefficient for the Tianlu planning quantifies the overall impact of risk sources and transmitted risks in the Tianlu planning. The higher the coefficient, the greater the planning risk.

[0065] The system for planning and designing highways based on artificial intelligence algorithms includes: The first acquisition module acquires environmental data of the UAV's flight area, obtains environmental condition data of the flight area based on the environmental data, sets sub-planning areas for the UAV based on the environmental condition data, and sets the corresponding planning parameters and planning weights for the sub-planning areas. Data Acquisition and Comparison Module: Collects real-time monitoring parameters of the sub-planning area, and obtains the sub-region planning coefficient of the sub-planning area based on the real-time monitoring parameters, planning parameters, and planning weights; compares and analyzes the sub-region planning coefficient with the preset planning coefficient threshold to obtain the first high-risk sub-planning area; The second acquisition module: acquires the first high-risk area factor corresponding to the first high-risk sub-planning area; obtains the influence area factor of the first high-risk area factor based on the regional correlation model; and obtains the risk impact coefficient of the first high-risk area factor on the influence area factor based on the regional correlation model. Calculation module: The difference between the risk impact coefficient and the sub-region planning coefficient is processed to obtain the comprehensive planning coefficient of the factors affecting the region; Comparison and analysis module: The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first and second high-risk regional factors. Generation module: Generates the optimal skyway planning path for the UAV based on the skyway planning evaluation coefficient.

[0066] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for planning and designing skyways based on artificial intelligence algorithms, characterized in that: The method includes the following steps: Acquire environmental data of the drone's flight area, and obtain environmental condition data of the flight area based on the environmental data; set sub-planning areas for the drone based on the environmental condition data, and set the corresponding planning parameters and planning weights for the sub-planning areas; Real-time monitoring parameters of the sub-planning area are collected, and the sub-area planning coefficient of the sub-planning area is obtained based on the real-time monitoring parameters, planning parameters and planning weights; the sub-area planning coefficient is compared and analyzed with the preset planning coefficient threshold to obtain the first high-risk sub-planning area. Obtain the first high-risk area factor corresponding to the first high-risk sub-planning area; obtain the influence area factor of the first high-risk area factor based on the regional correlation model; and obtain the risk impact coefficient of the first high-risk area factor on the influence area factor based on the regional correlation model. The comprehensive planning coefficient of the influencing factors is obtained by subtracting the risk impact coefficient and the sub-regional planning coefficient. The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first and second high-risk regional factors. The optimal sky route planning path for UAVs is generated based on the sky route planning evaluation coefficient.

2. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 1, characterized in that, It also includes the following steps: Generate regional factors based on the sub-planning areas of the UAV flight area; Obtain the regional association paths of the sub-planning area; Generate factor correlation channels and channel influence coefficients between regional factors based on regional correlation paths; A regional correlation model is constructed based on regional factors, factor correlation channels, and channel influence coefficients.

3. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 2, characterized in that, The environmental condition data of the flight area is obtained based on environmental data, specifically including the following steps: Establish environmental classification standards; Based on environmental classification standards and environmental data, the environmental types included in the drone flight area and the area proportion of each environmental type are obtained. The environmental type and the area percentage corresponding to the environmental type constitute the environmental status data.

4. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 3, characterized in that, Based on environmental data, sub-planning areas for the drone are set, and corresponding planning parameters and weights are set for each sub-planning area. This includes the following steps: Sub-planning areas for drones are set up based on environmental type and the area proportion corresponding to the environmental type; Set the planning parameters and planning weights for the sub-planning areas according to the environmental type.

5. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 4, characterized in that, The sub-region planning coefficients for sub-planning areas are obtained based on real-time monitoring parameters, planning parameters, and planning weights, specifically including the following steps: The parameter deviation values ​​corresponding to the sub-planning areas are obtained based on real-time monitoring parameters and planning parameters; The sub-region planning coefficient is obtained by weighting and summing the parameter deviation values ​​corresponding to the sub-planning areas based on the planning weights.

6. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 5, characterized in that, The first high-risk sub-planning area is determined by comparing and analyzing the planning coefficients of the sub-area with preset planning coefficient thresholds. This process includes the following steps: If the planning coefficient of a sub-region is greater than or equal to the preset planning coefficient threshold, the planning risk of the sub-region is judged to be normal. If the planning coefficient of a sub-region is less than the preset planning coefficient threshold, the planning risk of the sub-region is judged to be abnormal, and the sub-region is marked as the first high-risk sub-region.

7. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 6, characterized in that, The generation of factor correlation channels and channel influence coefficients between regional factors based on regional correlation paths includes the following steps: Based on the regional association path, the adjacent sub-planning regions of the sub-planning region are obtained, and the path connectivity, path length and path environment complexity between the sub-planning region and the adjacent sub-planning regions are obtained; Based on the path connectivity, the factor pointing identifiers of the regional factors and the adjacent regional factors are obtained. Each regional factor has a factor pointing identifier. Based on the factor pointing identifiers, factor association channels between the regional factors and the adjacent regional factors are generated. The coefficients of the first channel corresponding to the factor-related channel are obtained based on the preset length influence weight and path length. Set an environment complexity set, which includes a preset complexity level and a level influence coefficient; Obtain the actual complexity level corresponding to the path environment complexity of the sub-planning area and the adjacent sub-planning area, compare the actual complexity level with the preset complexity level of the environment complexity set to obtain the preset complexity level corresponding to the actual complexity level, and record the level influence coefficient corresponding to the preset complexity level as the second channel coefficient. Set the weights for the first channel and the second channel; based on the weights and coefficients of the first channel, the weights and coefficients of the second channel, and the coefficients of the second channel, obtain the channel influence coefficients corresponding to the factor-related channels.

8. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 7, characterized in that, Based on the regional correlation model, the influencing regional factor of the first high-risk regional factor is obtained, and the risk impact coefficient of the first high-risk regional factor on the influencing regional factor is obtained based on the regional correlation model. The specific steps include: Obtain the factor pointing identifier of the first high-risk area factor; Based on the factor pointing identifier, the target factor correlation channel of the first high-risk area factor is obtained; Based on the target factor correlation channel, the influence area factor corresponding to the first high-risk area factor is obtained; Obtain the factor correlation channel between the first high-risk area factor and the affected area factor, and mark the channel influence coefficient corresponding to the factor correlation channel as the target channel influence coefficient; The risk impact coefficient of the first high-risk area factor on the influencing area factor is obtained based on the target channel impact coefficient and the sub-region planning coefficient corresponding to the first high-risk area factor.

9. The method for planning and designing skyways based on artificial intelligence algorithms according to claim 8, characterized in that, The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; based on the first and second high-risk regional factors, the air route planning evaluation coefficient of the UAV flight area is obtained, specifically including the following steps: If the comprehensive planning coefficient of the influencing regional factor is less than the preset planning coefficient threshold, the planning risk of the influencing regional factor is judged to be high, and the influencing regional factor is marked as the second highest risk regional factor. Obtain the first risk percentage corresponding to the first highest risk region factor in the regional correlation model; obtain the second risk percentage corresponding to the second highest risk region factor in the regional correlation model; A first risk weight and a second risk weight are set, and the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first risk weight and the first risk ratio, the second risk weight and the second risk ratio.

10. A system for planning and designing skyways based on artificial intelligence algorithms, applied to the method for planning and designing skyways based on artificial intelligence algorithms as described in any one of claims 1 to 9, characterized in that, include: First acquisition module: Acquires environmental data of the UAV's flight area, and obtains environmental condition data of the flight area based on the environmental data; Based on environmental data, set sub-planning areas for the drone, and set the corresponding planning parameters and planning weights for each sub-planning area; Data Acquisition and Comparison Module: Collects real-time monitoring parameters of the sub-planning area, and obtains the sub-region planning coefficient of the sub-planning area based on the real-time monitoring parameters, planning parameters, and planning weights; compares and analyzes the sub-region planning coefficient with the preset planning coefficient threshold to obtain the first high-risk sub-planning area; Second acquisition module: Acquire the first high-risk area factor corresponding to the first high-risk sub-planning area; Based on the regional correlation model, the regional factors affecting the first high-risk regional factor are obtained, and the risk impact coefficient of the first high-risk regional factor on the regional factors is obtained based on the regional correlation model. Calculation module: The difference between the risk impact coefficient and the sub-region planning coefficient is processed to obtain the comprehensive planning coefficient of the factors affecting the region; Comparison and analysis module: The comprehensive planning coefficient of the influencing regional factors is compared and analyzed with the preset planning coefficient threshold to obtain the second high-risk regional factor; the skyway planning evaluation coefficient of the UAV flight area is obtained based on the first and second high-risk regional factors. Generation module: Generates the optimal skyway planning path for the UAV based on the skyway planning evaluation coefficient.

Images