A safety assessment method for transportation products based on flight attitude

Abstract

The present invention discloses a safety assessment method for transportation products based on flight attitude, which relates to the technical field of data processing. The method includes: synchronously and real-time sensing the attitude change and environmental state of a target unmanned aerial vehicle in a preset monitoring window by using a flight attitude sensing array and an environmental sensing array at a preset monitoring interval to obtain a flight attitude sensing data set sequence and an environmental sensing data set sequence; constructing a preset flight attitude framework sequence; obtaining a flight attitude sensing framework sequence; determining a flight attitude framework deviation degree sequence; determining a flight attitude deviation influence coefficient; determining an environmental deviation influence coefficient; and performing comprehensive analysis to obtain a safety assessment result of the transportation product. The present invention solves the technical problem in the prior art that the lack of attitude correlation analysis of the flight attitude of unmanned aerial vehicles leads to low accuracy of the safety assessment of transportation products, and achieves the technical effect of reliably assessing the safety of transportation products according to the flight attitude of unmanned aerial vehicles.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a safety assessment method for transportation products based on flight attitude. Background Art

[0002] Currently, the analysis of the flight attitude of drones often starts from a single dimension. For example, based on information such as the pitch angle, roll angle of the drone, or temperature and air pressure in the environment, individual factors are analyzed. The complex interaction relationships between these factors during flight are ignored. For example, in some cases, a sudden change in flight attitude may be caused by environmental factors (such as a change in wind speed or air temperature), and then return to a normal flight attitude at the next time point. If flight attitude or environmental factors are considered separately, it may lead to misjudgment or underestimation of the actual safety risk.

[0003] The prior art has the technical problem that the lack of attitude correlation analysis of the flight attitude of drones leads to low accuracy in the safety assessment of transportation products. Summary of the Invention

[0004] This application provides a safety assessment method for transportation products based on flight attitude, which is used to solve the technical problem in the prior art that the lack of attitude correlation analysis of the flight attitude of drones leads to low accuracy in the safety assessment of transportation products.

[0005] In view of the above problems, this application provides a safety assessment method for transportation products based on flight attitude. The method includes:

[0006] Using a flight attitude sensing array and an environment sensing array to synchronously and real-time sense the attitude change and environmental state of the target drone at a preset monitoring interval within a preset monitoring window, to obtain a flight attitude sensing data set sequence and an environment sensing data set sequence;

[0007] Obtaining the preset flight path and preset flight parameters of the target drone, and combining the preset monitoring interval and the preset monitoring window to construct a preset flight attitude frame sequence;

[0008] Traversing the flight attitude sensing data set sequence for attitude parsing to obtain a flight attitude sensing frame sequence;

[0009] Performing mapping deviation analysis on the preset flight attitude frame sequence and the flight attitude sensing frame sequence to determine a flight attitude frame deviation degree sequence;

[0010] Performing a comprehensive analysis of the double impacts of deviation superposition influence and centralized deviation degree on the flight attitude frame deviation degree sequence to determine a flight attitude deviation influence coefficient;

[0011] Perform a nearest neighbor interaction correlation trend analysis on the sequence of environmental sensing data sets in the order from front to back to determine the target environmental interaction correlation sensing data set, and perform an environmental deviation analysis in combination with the preset environmental data set corresponding to the preset flight parameters to determine the environmental deviation influence coefficient;

[0012] Use the product safety assessment network layer to comprehensively analyze the flight attitude deviation influence coefficient and the environmental deviation influence coefficient to obtain the transportation product safety assessment result.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0014] In this application, by using the flight attitude sensing array and the environmental sensing array to synchronously and real-time sense the attitude change and environmental state of the target UAV in the preset monitoring window at the preset monitoring interval, a sequence of flight attitude sensing data sets and a sequence of environmental sensing data sets are obtained. Then, the preset flight path and preset flight parameters of the target UAV are obtained, and in combination with the preset monitoring interval and the preset monitoring window, a preset flight attitude frame sequence is constructed. Furthermore, the flight attitude sensing data set sequence is traversed for attitude analysis to obtain the flight attitude sensing frame sequence. By performing a mapping deviation analysis on the preset flight attitude frame sequence and the flight attitude sensing frame sequence, the flight attitude frame deviation degree sequence is determined. Then, a two-way influence comprehensive analysis of the deviation superposition influence and the concentrated deviation degree is performed on the flight attitude frame deviation degree sequence to determine the flight attitude deviation influence coefficient. Furthermore, a nearest neighbor interaction correlation trend analysis is performed on the sequence of environmental sensing data sets in the order from front to back to determine the target environmental interaction correlation sensing data set, and an environmental deviation analysis is performed in combination with the preset environmental data set corresponding to the preset flight parameters to determine the environmental deviation influence coefficient. The product safety assessment network layer is used to comprehensively analyze the flight attitude deviation influence coefficient and the environmental deviation influence coefficient to obtain the transportation product safety assessment result. The technical effect of improving the reliability of transportation product safety assessment is achieved. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a schematic flowchart of a method for assessing the safety of a transportation product based on flight attitude provided by an embodiment of this application;

[0017] Figure 2Schematic diagram of the process for determining the centralized deviation from a straight line in a method for safety assessment of a transportation product based on flight attitude provided by an embodiment of the present application. Detailed implementation manners

[0018] The present application provides a method for safety assessment of a transportation product based on flight attitude, which is used to solve the technical problem in the prior art that the attitude correlation analysis of the flight attitude of an unmanned aerial vehicle is lacking, resulting in low accuracy of the safety assessment of the transportation product.

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0020] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, method, product or server including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0021] Embodiment, as Figure 1 shown, the present application provides a method for safety assessment of a transportation product based on flight attitude, wherein the method includes:

[0022] S100: Use a flight attitude sensing array and an environment sensing array to synchronously and real-time sense the attitude change and environment state of a target unmanned aerial vehicle at a preset monitoring interval within a preset monitoring window, and obtain a flight attitude sensing data set sequence and an environment sensing data set sequence;

[0023] In a possible embodiment, the target unmanned aerial vehicle (UAV) is any type of UAV for product transportation. The preset monitoring interval is the time interval between two adjacent monitorings when those skilled in the art preset the monitoring of the flight attitude and flight environment of the target UAV, which can be 3 seconds, 5 seconds, etc. Preferably, the preset monitoring interval should be set according to factors such as the flight speed of the UAV and the sensor accuracy. The preset monitoring time is the time period preset by those skilled in the art for monitoring the flight attitude and flight environment of the target UAV, which can be 3 minutes, 6 minutes, 10 minutes, etc. The flight attitude sensing array is an array composed of sensors for monitoring the flight attitude of the UAV, including gyroscopes, accelerometers, magnetometers, etc. The parameters of each sensor include but are not limited to measurement range, sensitivity, resolution, etc. The environment sensing array is an array composed of sensors for monitoring the flight environment where the UAV is located, including temperature sensors, pressure sensors, humidity sensors, light sensors, wind speed sensors, etc.

[0024] In an embodiment, the flight attitude sensor array and the environment sensor array are started to ensure their normal operation and synchronization. The data of each sensor is connected to the data acquisition component through a hardware interface, and each sensor is calibrated to ensure the accuracy of measurement. Within the preset monitoring interval, data is simultaneously collected from the flight attitude sensor and the environment sensor array. When collecting data, the time synchronization of the flight attitude data and the environment data should be ensured, that is, they have the same timestamp, and the flight attitude sensing data set sequence and the environment sensing data set sequence are obtained. Among them, the flight attitude sensing data set sequence reflects the change of the flight attitude of the target UAV over time within the preset monitoring window. The environment sensing data set sequence reflects the change of the flight environment of the target UAV over time within the preset monitoring window.

[0025] Preferably, each flight attitude sensing data set includes data such as the attitude angles (such as pitch angle, roll angle, yaw angle), acceleration, and angular velocity of the UAV. Each environment sensing data set includes environmental variables such as pressure, temperature, humidity, and wind speed. By obtaining the flight attitude sensing data set sequence and the environment sensing data set sequence, the technical effect of providing basic analysis data for subsequent flight attitude deviation analysis and environmental state development trend analysis is achieved.

[0026] Exemplarily, assume that the target UAV flies from point A to point B according to a preset flight path and preset flight parameters during a certain flight mission. During this process, the real-time flight attitude of the UAV is collected through a flight attitude sensing array (such as recording the pitch angle, roll angle, and yaw angle of the UAV once per second), and at the same time, data such as the temperature, humidity, and air pressure of the environment where the UAV is located during the flight is recorded through an environmental sensing array. The whole process is synchronized according to a preset monitoring interval (for example, collecting data once per second), and the finally obtained sequence of flight attitude sensing data sets and sequence of environmental sensing data sets can provide a data basis for subsequent flight attitude analysis and environmental deviation analysis.

[0027] S200: Obtain the preset flight path and preset flight parameters of the target UAV, and combine the preset monitoring interval and the preset monitoring window to construct a preset flight attitude frame sequence;

[0028] In a possible embodiment, the preset flight path is the flight trajectory pre-planned by the target UAV during the process of performing the product transportation task. This path can be obtained from the UAV flight plan or mission instructions and usually includes information such as the starting point, ending point, flight altitude, and heading. The preset flight parameters include the flight mode of the UAV (such as automatic flight, manual flight, etc.), flight speed, flight altitude, pitch angle, roll angle, yaw angle, etc. These parameters are usually defined in the flight plan and are associated with the flight path. The preset flight attitude frame sequence refers to the sequence of each possible attitude change (pitch angle, roll angle, yaw angle, etc.) that the UAV may experience during flight according to the flight path and flight parameters.

[0029] Optionally, according to the preset monitoring interval (such as collecting flight data once per second) and the preset monitoring window (such as the specific time period of the flight mission), calculate the flight attitude change and related flight parameters of the UAV at each collection moment. That is, at each time node of the preset flight path, the corresponding flight attitude is collected. Combining the flight path and flight parameters, and based on the monitoring interval and flight time, gradually calculate the flight attitude of the UAV at each moment in the preset flight path. Each flight path point has a corresponding flight attitude frame. By obtaining the preset flight attitude frame sequence, the technical effect of providing comparison data for subsequent analysis of the attitude deviation of the target UAV within the preset monitoring window is achieved.

[0030] S300: Traverse the sequence of flight attitude sensing data sets for attitude analysis to obtain a sequence of flight attitude sensing frames;

[0031] S400: Perform mapping deviation analysis on the preset flight attitude frame sequence and the flight attitude sensing frame sequence to determine a sequence of flight attitude frame deviation degrees;

[0032] In a possible embodiment, each piece of attitude data in the sequence of flight attitude sensing data sets is parsed to extract the required flight attitude parameters (such as pitch angle, roll angle, yaw angle, etc.). Optionally, the pitch angle (Pitch), roll angle (Roll), yaw angle (Yaw), etc. are extracted from the sensor data. And the instantaneous attitude change of the UAV is calculated according to each piece of attitude data. For example, the change in the pitch angle represents the up and down tilt of the UAV, the change in the roll angle represents the lateral flip of the UAV, and the change in the yaw angle represents the change in the heading of the UAV. The parsed attitude data is synchronized with the time stamp to ensure that each attitude data can be correctly corresponding in the time series. Furthermore, according to the parsed attitude data, the flight attitude sensing framework sequence is constructed. The flight attitude sensing framework sequence reflects the change of the attitude of the target UAV over time during the flight in the preset monitoring window.

[0033] In one embodiment, the preset flight attitude framework and the flight attitude sensing framework at the same time point are extracted from the preset flight attitude framework sequence and the flight attitude sensing framework sequence, and analyzed by using a mapping deviation analyzer to obtain the corresponding flight attitude framework deviation degree. Among them, the flight attitude framework deviation degree reflects the deviation degree of the flight attitude of the target UAV from the preset flight attitude at this time point. When the flight attitude framework deviation degree is larger, it indicates that the flight attitude of the target UAV deviates more, and the possibility of the transported product being overturned is greater.

[0034] Optionally, a plurality of sample preset flight attitude frameworks, a plurality of sample flight attitude sensing frameworks, and the corresponding plurality of sample flight attitude framework deviation degrees are obtained as a training data set. The training data set is used to perform supervised training on the framework constructed based on the feedforward neural network, and the mapping relationship between the preset flight attitude framework, the flight attitude sensing framework, and the flight attitude framework deviation degree is learned until the training converges, and the trained mapping deviation analyzer is obtained. It achieves the technical effect of intelligently analyzing the flight attitude framework deviation degree and improving the analysis efficiency.

[0035] S500: Perform a comprehensive analysis of the two-way influences of deviation superposition influence and centralized deviation degree on the flight attitude framework deviation degree sequence to determine the flight attitude deviation influence coefficient;

[0036] Furthermore, perform a comprehensive analysis of the two-way influences of deviation superposition influence and centralized deviation degree on the flight attitude framework deviation degree sequence to determine the flight attitude deviation influence coefficient. Step S500 of the embodiment of the present application further includes:

[0037] Based on the monitoring time sequence of the flight attitude framework deviation degrees in the flight attitude framework deviation degree sequence, weight distribution is performed to determine the sequence of allocated weight values;

[0038] Perform weighted calculation on the flight attitude frame deviation degrees in the flight attitude frame deviation degree sequence according to the assigned weight value sequence to determine the weighted flight attitude frame deviation degree;

[0039] Conduct an analysis of the centralized deviation degree of the flight attitude frame deviation degree sequence to determine the flight attitude frame centralized deviation degree;

[0040] Perform an average value calculation on the weighted flight attitude frame deviation degree and the flight attitude frame centralized deviation degree to obtain the flight attitude deviation influence coefficient.

[0041] In a possible embodiment, after obtaining the flight attitude frame deviation degree sequence, conduct a comprehensive influence analysis from two dimensions: the superimposed influence of each deviation and the general deviation situation within a preset monitoring window, to obtain the flight attitude deviation influence coefficient. Among them, the flight attitude deviation influence coefficient reflects the comprehensive deviation analysis situation of the deviation flight attitude of the target unmanned aerial vehicle within the preset monitoring window.

[0042] In an embodiment, perform weight assignment according to the monitoring time sequence of the flight attitude frame deviation degrees in the flight attitude frame deviation degree sequence, and assign different weights to the deviation degrees at different time points. Preferably, the flight attitude frame deviation degree closer to the end of the preset monitoring window should be assigned a higher weight. Take the ratio of the rank of each flight attitude frame deviation degree in the flight attitude frame deviation degree sequence to the total number of the flight attitude frame deviation degree sequence as the corresponding assigned weight value, and thus obtain the assigned weight value sequence.

[0043] Optionally, multiply each flight attitude frame deviation degree in the flight attitude frame deviation degree sequence by the corresponding assigned weight value according to the assigned weight value sequence, and then sum the products to obtain the weighted flight attitude frame deviation degree.

[0044] Optionally, analyze the general distribution situation of multiple flight attitude frame deviation degrees in the flight attitude frame deviation degree sequence, extract the data with concentrated distribution, and determine the flight attitude frame centralized deviation degree. Among them, the flight attitude frame centralized deviation degree reflects whether the attitude change is stable or too drastic during the flight of the unmanned aerial vehicle, and is the general attitude deviation situation of the target unmanned aerial vehicle.

[0045] Furthermore, comprehensively analyze the weighted flight attitude frame deviation degree and the flight attitude frame centralized deviation degree, and evaluate the influence coefficient of the flight attitude deviation by calculating the average value of the two. Take the average value calculation result as the flight attitude deviation influence coefficient. The flight attitude frame centralized deviation degree reflects the overall deviation situation of the attitude fluctuation of the target unmanned aerial vehicle within the preset monitoring window.

[0046] By analyzing the two dimensions of weighted calculation of the flight attitude frame deviation sequence and the centralized deviation, the stability and deviation of the UAV flight attitude can be evaluated in real time and accurately. It achieves the technical effect of providing more accurate flight attitude feedback and improving the reliability of subsequent analysis of the safety of transportation products.

[0047] Further, step S500 of the embodiment of the present application further includes:

[0048] Construct a centralized deviation analysis space based on the flight attitude frame deviation sequence, wherein the centralized deviation analysis space is a two-dimensional analysis space, the horizontal axis is time, the vertical axis is the flight attitude frame deviation, and the centralized deviation analysis space includes a plurality of analysis space points, and each analysis space point corresponds to the flight attitude frame deviation at a time point;

[0049] Calculate the mean value of the ordinates of the plurality of analysis space points, and take the straight line passing through the mean value of the ordinates and parallel to the horizontal axis of the centralized deviation analysis space as the starting straight line;

[0050] Iterate the starting straight line in the centralized deviation analysis space according to a preset moving step length to determine the centralized deviation straight line;

[0051] Construct a centralized deviation neighborhood based on the centralized deviation straight line and the preset moving step length, calculate the mean value of the ordinates of the plurality of analysis space points in the centralized deviation neighborhood, and obtain the centralized deviation degree of the flight attitude frame.

[0052] Further, as Figure 2 shown, iterating the starting straight line in the centralized deviation analysis space according to a preset moving step length to determine the centralized deviation straight line, step S500 of the embodiment of the present application further includes:

[0053] Construct a starting neighborhood of the starting straight line in the centralized deviation analysis space according to the preset moving step length, wherein the starting neighborhood includes a plurality of analysis space points whose distance to the starting straight line is the preset moving step length;

[0054] Count the number of analysis space points in the starting neighborhood to obtain the starting neighborhood statistic;

[0055] Move the starting straight line according to the preset moving step length in the first direction and the second direction to obtain a first iterative straight line and a second iterative straight line, the first direction is above the starting straight line, and the second direction is below the starting straight line;

[0056] Construct a first iterative neighborhood of the first iterative straight line and a second iterative neighborhood of the second iterative straight line to obtain a first iterative neighborhood statistic and a second iterative neighborhood statistic;

[0057] Determine whether the first iterative neighborhood statistic and / or the second iterative neighborhood statistic is greater than or equal to the starting neighborhood statistic. If so, iterate the first iterative line and / or the second iterative line in the first direction and / or the second direction respectively until the preset number of iterations is satisfied, and use the iterative line corresponding to the maximum value of the iterative neighborhood statistic during the iteration process as the concentrated deviation line.

[0058] Further, when both the first iterative neighborhood statistic and the second iterative neighborhood statistic are less than or equal to the starting neighborhood statistic, use the starting line as the concentrated deviation line.

[0059] In a possible embodiment, construct a two-dimensional analysis space, where the horizontal axis of the two-dimensional analysis space is time and the vertical axis is the flight attitude frame deviation. Input each flight attitude frame deviation and the corresponding time point in the flight attitude frame deviation sequence into the two-dimensional analysis space to obtain a plurality of analysis space points. Each analysis space point corresponds to the flight attitude frame deviation at a time point. Furthermore, construct the concentrated deviation analysis space based on the plurality of analysis space points and the two-dimensional analysis space.

[0060] Optionally, calculate the mean value of the ordinates of the plurality of analysis space points, and use the line passing through the mean value of the ordinates and parallel to the horizontal axis of the concentrated deviation analysis space as the starting line. Then iterate the starting line in the concentrated deviation analysis space according to a preset moving step size to determine the concentrated deviation line. Wherein, the preset moving step size is the deviation value moved during two adjacent iterations preset by those skilled in the art. The concentrated deviation line is the line with the most densely distributed analysis space points around it, and the concentrated deviation neighborhood obtained based on the concentrated deviation line can best reflect the concentrated distribution of the flight attitude frame deviation sequence.

[0061] Optionally, construct a concentrated deviation neighborhood based on the concentrated deviation line and the preset moving step size. Wherein, the concentrated deviation neighborhood includes a plurality of analysis space points whose distance to the concentrated deviation line is the preset moving step size. Furthermore, calculate the mean value of the ordinates of the plurality of analysis space points in the concentrated deviation neighborhood to obtain the flight attitude frame concentrated deviation.

[0062] In an embodiment, construct a starting neighborhood of the starting line in the concentrated deviation analysis space according to the preset moving step size, where the starting neighborhood includes a plurality of analysis space points whose distance to the starting line is the preset moving step size. Count the number of analysis space points in the starting neighborhood to obtain the starting neighborhood statistic. Wherein, the starting neighborhood statistic reflects the density of the analysis space points distributed around the starting line.

[0063] Furthermore, move the starting straight line according to the preset moving step length in the first direction and the second direction to obtain a first iterative straight line and a second iterative straight line. The first direction is above the starting straight line, and the second direction is below the starting straight line.

[0064] Based on the same construction principle as the starting neighborhood, obtain a first iterative neighborhood of the first iterative straight line and a second iterative neighborhood of the second iterative straight line. And respectively count the number of analysis space points in the first iterative neighborhood and the second iterative neighborhood to obtain a first iterative neighborhood statistic and a second iterative neighborhood statistic.

[0065] Optionally, determine whether the first iterative neighborhood statistic and / or the second iterative neighborhood statistic is greater than or equal to the starting neighborhood statistic. If so, it indicates that there is a straight line with a larger number of analysis space points distributed around it than the number of analysis space points distributed around the starting straight line. At this time, iterate the first iterative straight line and / or the second iterative straight line in the first direction and / or the second direction respectively until the preset number of iterations (the maximum number of iterations preset by those skilled in the art) is satisfied, and use the iterative straight line corresponding to the maximum value of the iterative neighborhood statistic during the iterative process as the concentrated deviation straight line.

[0066] When both the first iterative neighborhood statistic and the second iterative neighborhood statistic are less than or equal to the starting neighborhood statistic, it indicates that the number of analysis space points distributed around the starting straight line is the largest. At this time, stop the iteration and use the starting straight line as the concentrated deviation straight line.

[0067] S600: Perform a nearest neighbor interaction correlation trend analysis on the sequence of environmental sensing data sets in the order from front to back to determine a target environmental interaction correlation sensing data set, and combine it with the preset environmental data set corresponding to the preset flight parameters to perform an environmental deviation analysis to determine an environmental deviation influence coefficient;

[0068] S700: Use the product safety assessment network layer to comprehensively analyze the flight attitude deviation influence coefficient and the environmental deviation influence coefficient to obtain a transportation product safety assessment result.

[0069] Further, perform a nearest neighbor interaction correlation trend analysis on the sequence of environmental sensing data sets in the order from front to back to determine a target environmental interaction correlation sensing data set. Step S600 of the embodiment of the present application further includes:

[0070] Extract a first environmental sensing data set and a second environmental sensing data set from the sequence of environmental sensing data sets;

[0071] Perform inner product calculation and normalization matrix processing on the first environmental sensing data set and the second environmental sensing data set to obtain a first nearest neighbor interaction correlation matrix;

[0072] Perform convolution calculation on the first nearest neighbor interaction correlation matrix and the second environmental sensing data set to determine a first environmental interaction correlation sensing data set;

[0073] Extract the third environmental sensing data set again, and perform nearest neighbor interaction correlation trend analysis on it and the first environmental interaction correlation sensing data set to determine a second environmental interaction correlation sensing data set;

[0074] Extract the Nth environmental sensing data set again, perform nearest neighbor interaction correlation trend analysis on it and the (N - 2)th environmental interaction correlation sensing data set to determine the (N - 1)th environmental interaction correlation sensing data set, and use the (N - 1)th environmental interaction correlation sensing data set as the target environmental interaction correlation sensing data set, where N is the number of environmental sensing data sets in the environmental sensing data set sequence, and N is an integer greater than or equal to 1.

[0075] Further, step S600 of the embodiment of the present application further includes:

[0076] Perform similarity inner product calculation on the first environmental sensing data set and the second environmental sensing data set using the cosine similarity formula to obtain a first data similarity coefficient set;

[0077] Traverse the first data similarity coefficient set using a similarity coefficient processor for normalization processing, and perform matrix construction on the processing results to obtain the first nearest neighbor interaction correlation matrix.

[0078] Further, step S600 of the embodiment of the present application further includes:

[0079] The obtained similarity coefficient processor includes a similarity coefficient processing formula, and the similarity coefficient processing formula is:

[0080] ;

[0081] Wherein, is the normalized value of the i-th data similarity coefficient set in the first data similarity coefficient set, e is the base of the natural logarithm, q is the total number of data similarity coefficients in the first data similarity coefficient set, is the data similarity coefficient of the i-th type of first environmental sensing data and second environmental sensing data in the first environmental sensing data set and the second environmental sensing data set.

[0082] In a possible embodiment, by performing a nearest neighbor interaction correlation trend analysis on the sequence of environmental sensing data sets, a layer-by-layer analysis of the environmental sensing data sets is achieved, thereby determining the environmental change trend within a preset monitoring window. The target environmental interaction correlation sensing data set obtained after considering the correlation trend is subjected to a deviation analysis with the preset environmental data set corresponding to the preset flight parameters, and finally an environmental deviation influence coefficient is obtained. The environmental deviation influence coefficient reflects the degree of environmental deviation when the target unmanned aerial vehicle transports products within the preset monitoring window. Optionally, the cosine similarity formula is used to calculate the environmental data similarity between the target environmental interaction correlation sensing data set and the preset environmental data set. Furthermore, the difference between the environmental data similarity and 1 is used as the environmental deviation influence coefficient.

[0083] Furthermore, a sample flight attitude deviation influence coefficient, a sample environmental deviation influence coefficient, and a sample transportation product safety assessment result are obtained as training data. The training data is used to perform supervised training on a framework constructed based on a convolutional neural network, and the network parameters are updated according to the training situation during the training until the training converges, obtaining the trained product safety assessment network layer. The flight attitude deviation influence coefficient and the environmental deviation influence coefficient are transmitted to the product safety assessment network layer for analysis, obtaining the transportation product safety assessment result. The technical effect of reliably assessing the safety of the transported product based on the flight attitude of the unmanned aerial vehicle is achieved.

[0084] In a possible embodiment, from the sequence of environmental sensing data sets, the first environmental sensing data set located at the first position and the second environmental sensing data set located at the second position are extracted in chronological order. These sets respectively represent the flight environmental data of the target unmanned aerial vehicle at the first time point and the second time point, and may include multiple environmental parameters such as temperature, humidity, air pressure, and wind speed.

[0085] Optionally, the cosine similarity formula is used to perform an inner product calculation on the extracted first environmental sensing data set and the second environmental sensing data set. The inner product calculation is used to quantify the correlation and similarity between these two data sets, which can help reveal the potential association between them. And the similarity coefficient processing formula is used to perform a normalization matrix processing on the inner product calculation result, obtaining the first nearest neighbor interaction correlation matrix. That is, the inner product result is normalized to eliminate the differences in different dimensions and data scales, ensuring the comparability between different data sets. Among them, the first nearest neighbor interaction correlation matrix reflects the implicit association relationship between the first environmental sensing data set and the second environmental sensing data set.

[0086] Then, perform a convolution calculation on the calculated first nearest neighbor interaction correlation matrix and the second environmental sensing data set. The convolution operation can further explore the deep correlation relationship between the first environmental sensing data set and the second environmental data set, thereby obtaining the first environmental interaction correlation sensing data set. The main purpose of this stage is to extract important correlation patterns through convolution, making the analysis results more accurate and capturing more subtle trends in environmental changes.

[0087] Preferably, obtain a plurality of sample nearest neighbor interaction correlation matrices, a plurality of sample environmental sensing data sets, and a plurality of sample environmental interaction correlation sensing data sets as convolution network training data, and use the convolution network training data to perform supervised training on the convolution network layer until the training converges to obtain a trained convolution network layer. Use the convolution network layer to perform a convolution calculation on the first nearest neighbor interaction correlation matrix and the second environmental sensing data set to obtain the first environmental interaction correlation sensing data set.

[0088] Furthermore, extract the third environmental sensing data set, and perform a nearest neighbor interaction correlation trend analysis on it and the first environmental interaction correlation sensing data set according to the same principle as obtaining the first environmental interaction correlation sensing data set, thereby determining the second environmental interaction correlation sensing data set.

[0089] Based on the same principle as obtaining the first environmental interaction correlation sensing data set, continue to extract the Nth environmental sensing data set, and perform a nearest neighbor interaction correlation trend analysis on it and the previous environmental interaction correlation data set (the N - 2th) to obtain the (N - 1)th environmental interaction correlation sensing data set. Finally, take the (N - 1)th environmental interaction correlation sensing data set as the target environmental interaction correlation sensing data set. This set contains key environmental features that have been analyzed and refined through multiple layers and can effectively reflect the impact of environmental changes on the flight mission.

[0090] Optionally, perform a similarity inner product calculation on the first environmental sensing data set and the second environmental sensing data set using the cosine similarity formula. The cosine similarity can measure the similarity between two data sets and help screen out data points with a relatively high degree of similarity. Furthermore, use a similarity coefficient processor to traverse the first data similarity coefficient set for normalization processing. The normalized similarity coefficient can remove the bias of the data and make the measurement of similarity more fair. Construct a matrix from the normalized results to generate the first nearest neighbor interaction correlation matrix, providing a quantitative basis for subsequent analysis.

[0091] Optionally, the obtained similarity coefficient processor includes a similarity coefficient processing formula, and the similarity coefficient processing formula is:

[0092] ;

[0093] in, is the normalized value of the ith data similarity coefficient set in the first data similarity coefficient set, e is the base of the natural logarithm, q is the total number of data similarity coefficients in the first data similarity coefficient set, is the data similarity coefficient of the i-th type of first environmental sensor data and second environmental sensor data in the first environmental sensor data set and the second environmental sensor data set.

[0094] Optionally, the similarity coefficient processing formula uses an exponential function to perform weighted processing on the similarity, ensuring that a greater weight is given to data points with higher similarity, thereby further improving the accuracy of the analysis.

[0095] Through inner product calculation and cosine similarity, the similarities between different environmental data sets can be quickly identified, and multi-level neighbor interaction correlation trend analysis can be performed on this basis. Through convolution calculation and multi-level analysis, the system can deeply explore the subtle correlations between environmental data sets, ensuring that the target environmental interaction correlation sensor data set obtained in the end can accurately reflect environmental changes. The technical effect of accurately assessing the impact of environmental deviation and providing solid data support for analyzing the safety assessment of transportation products has been achieved.

[0096] In summary, the embodiments of the present application have at least the following technical effects:

[0097] The present application realizes the full data collection of the flight process by synchronously monitoring the flight attitude changes and environmental conditions of the target UAV within a preset monitoring window in real time through the flight attitude sensor array and the environmental sensor array. Furthermore, by gradually analyzing the flight attitude data set sequence and the environmental data set sequence, the potential risks in the flight process can be deeply explored. Through the analysis of the flight attitude parsing and mapping deviation, the degree of deviation of the flight attitude can be accurately evaluated, and the impact of the environmental deviation can be analyzed. A comprehensive analysis is performed based on the flight attitude deviation influence coefficient and the environmental deviation influence coefficient obtained by the analysis, taking into account the mutual influence of the flight attitude and environmental changes, effectively improving the evaluation capability of complex risk factors in the flight process, and achieving the technical effect of improving the reliability of the safety evaluation of transportation products.

[0098] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0099] The above are only the preferred embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0100] This specification and the drawings are merely exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for safety assessment of transportation products based on flight attitude, characterized in that: The method comprises: Using the flight attitude sensor array and the environment sensor array to synchronously sense the attitude changes and environmental conditions of the target UAV in a preset monitoring window in real time according to the preset monitoring interval, and obtain a flight attitude sensor data set sequence and an environment sensor data set sequence; Acquire the preset flight path and preset flight parameters of the target UAV, and construct a preset flight attitude frame sequence in combination with the preset monitoring interval and the preset monitoring window; Traversing the flight attitude sensing data set sequence to perform attitude analysis and obtain a flight attitude sensing frame sequence; Performing mapping deviation analysis on the preset flight attitude frame sequence and the flight attitude sensing frame sequence to determine a flight attitude frame deviation degree sequence; Performing a comprehensive analysis of the dual effects of deviation superposition effect and concentrated deviation degree on the flight attitude frame deviation degree sequence to determine the flight attitude deviation influence coefficient; Performing a neighbor interaction correlation trend analysis on the environmental sensor data set sequence from front to back to determine a target environmental interaction correlation sensor data set, performing an environmental deviation analysis on a preset environmental data set corresponding to the preset flight parameters to determine an environmental deviation impact coefficient; The product safety assessment network layer is used to conduct a comprehensive analysis on the flight attitude deviation influence coefficient and the environment deviation influence coefficient to obtain a transportation product safety assessment result.

2. A method for transport product safety assessment based on flight attitude as claimed in claim 1, characterized in that: The flight attitude frame deviation degree sequence is subjected to a comprehensive analysis of the dual effects of deviation superposition effect and concentrated deviation degree to determine the flight attitude deviation influence coefficient, including: Based on the monitoring time of the flight attitude frame deviation in the flight attitude frame deviation sequence, weight allocation is performed in sequence to determine the allocation weight value sequence; Performing weighted calculation on the flight attitude frame deviations in the flight attitude frame deviation sequence according to the distribution weight value sequence to determine a weighted flight attitude frame deviation; Performing a concentrated deviation degree analysis on the flight attitude frame deviation degree sequence to determine the flight attitude frame concentrated deviation degree; The weighted flight attitude framework deviation and the flight attitude framework concentrated deviation are averaged to obtain the flight attitude deviation influence coefficient.

3. A method for safety assessment of transportation products based on flight attitude as claimed in claim 2, characterized in that: include: Based on the flight attitude framework deviation sequence, a concentrated deviation analysis space is constructed, wherein the concentrated deviation analysis space is a two-dimensional analysis space, the horizontal axis is time, the vertical axis is the flight attitude framework deviation, and the concentrated deviation analysis space includes a plurality of analysis space points, each analysis space point corresponds to the flight attitude framework deviation at a time point; Calculating the mean ordinate values ​​of the plurality of analysis space points, and taking a straight line passing through the mean ordinate value and parallel to the abscissa axis of the concentrated deviation analysis space as a starting straight line; Iterate the starting straight line in the concentrated deviation analysis space according to a preset moving step length to determine a concentrated deviation straight line; A concentrated deviation neighborhood is constructed based on the concentrated deviation straight line and the preset moving step length, and the mean values ​​of the longitudinal coordinates of multiple analysis space points in the concentrated deviation neighborhood are calculated to obtain the concentrated deviation degree of the flight attitude framework.

4. A method for safety assessment of transportation products based on flight attitude as claimed in claim 3, characterized in that: Iterating the starting straight line in the concentrated deviation analysis space according to a preset moving step length to determine the concentrated deviation straight line includes: Constructing a starting neighborhood of the starting straight line in the concentrated deviation analysis space according to the preset moving step, wherein the starting neighborhood includes a plurality of analysis space points whose distance to the starting straight line is equal to the preset moving step; Counting the number of analysis space points in the starting neighborhood to obtain starting neighborhood statistics; According to a first direction and a second direction, the starting straight line is moved according to the preset moving step length to obtain a first iterative straight line and a second iterative straight line, wherein the first direction is above the starting straight line and the second direction is below the starting straight line; Constructing a first iteration neighborhood of the first iteration straight line and a second iteration neighborhood of the second iteration straight line, and obtaining first iteration neighborhood statistics and second iteration neighborhood statistics; Determine whether the first iterative neighborhood statistic and / or the second iterative neighborhood statistic is greater than or equal to the initial neighborhood statistic. If so, iterate the first iterative straight line and / or the second iterative straight line along the first direction and / or the second direction respectively until a preset number of iterations is met, and take the iterative straight line corresponding to the maximum value of the iterative neighborhood statistic during the iteration process as the concentrated deviation straight line.

5. A method for transport product safety assessment based on flight attitude as claimed in claim 4, characterized in that: When both the first iterative neighborhood statistic and the second iterative neighborhood statistic are less than or equal to the initial neighborhood statistic, the initial straight line is used as the concentrated deviation straight line.

6. A method for safety assessment of transportation products based on flight attitude as claimed in claim 1, characterized in that: The environmental sensor data set sequence is subjected to neighbor interaction correlation trend analysis in order from front to back to determine the target environmental interaction correlation sensor data set, including: Extracting a first environmental sensor data set and a second environmental sensor data set of the environmental sensor data set sequence; Performing inner product calculation and normalized matrix processing on the first environmental sensor data set and the second environmental sensor data set to obtain a first nearest neighbor interaction correlation matrix; Performing convolution calculation on the first neighbor interaction correlation matrix and the second environment sensor data set to determine a first environment interaction correlation sensor data set; Extracting a third environment sensor data set again, performing a neighbor interaction correlation trend analysis on the third environment sensor data set and the first environment interaction correlation sensor data set, and determining a second environment interaction correlation sensor data set; Extract the Nth environmental sensor data set again, perform neighbor interaction correlation trend analysis on it and the N-2th environmental interaction correlation sensor data set, determine the N-1th environmental interaction correlation sensor data set, and take the N-1th environmental interaction correlation sensor data set as the target environmental interaction correlation sensor data set, wherein N is the number of environmental sensor data sets in the environmental sensor data set sequence, and N is an integer greater than or equal to 1.

7. A method for safety assessment of transportation products based on flight attitude as claimed in claim 6, characterized in that: include: Using a cosine similarity formula, similar inner product calculation is performed on the first environmental sensor data set and the second environmental sensor data set to obtain a first data similarity coefficient set; The first data similarity coefficient set is traversed by a similarity coefficient processor for normalization processing, and a matrix is ​​constructed for the processing result to obtain the first neighbor interaction correlation matrix.

8. A method for transport product safety assessment based on flight attitude as claimed in claim 7, characterized in that: include: The similarity coefficient processor is obtained to include a similarity coefficient processing formula, and the similarity coefficient processing formula is: ； in, is the normalized value of the ith data similarity coefficient set in the first data similarity coefficient set, e is the base of the natural logarithm, q is the total number of data similarity coefficients in the first data similarity coefficient set, is the data similarity coefficient of the i-th type of first environmental sensor data and second environmental sensor data in the first environmental sensor data set and the second environmental sensor data set.

Images