A method, device and electronic equipment for aviation trajectory navigation based on geomagnetic signals

Abstract

This specification discloses an aviation trajectory navigation method, device and electronic equipment based on geomagnetic signals, specifically including: determining the geomagnetic trajectory heat map and two-dimensional geomagnetic tensor corresponding to the target object according to the historical trajectory geomagnetic sequence of the target object. Determine the motion time characteristics of the target object according to the two-dimensional geomagnetic tensor, input the geomagnetic trajectory heat map into the spatial feature extraction model, and determine the motion space characteristics of the target object. Fuse the motion time characteristics and motion space characteristics to determine the predicted position information for trajectory navigation of the target object. Through this method, the time and space characteristics can be effectively combined, the accuracy of the predicted position can be effectively improved, and the trajectory deviation caused by the cumulative error problem of the inertial navigation system can be corrected to a great extent. The application limitations of geomagnetic navigation technology based on pattern recognition means and the problem of data transmission errors caused by long-distance transmission are solved, and the task execution efficiency is effectively improved while taking into account low-cost consumption.

Description

Technical Field

[0001] The present invention relates to the field of geomagnetic navigation, and in particular to an aviation trajectory navigation method, device and electronic equipment based on geomagnetic signals. Background Art

[0002] With the continuous development and progress of science and technology at this stage, various technologies related to flight in the field of aerospace are becoming more and more mature. The widespread popularization and application of aviation technology has brought great convenience and many benefits to people's daily life, economic trade, and cultural exchanges.

[0003] At a time when the advantages of aviation flight technology are extremely significant, it is very important to successfully ensure the accuracy of the flight trajectory of flight equipment. At present, the common related technologies in the field of geomagnetic navigation include the more traditional rigid transformation method, which converts geomagnetic signals into position information through linear technology, but this type of technology has the problem of poor nonlinear mapping positioning effect. The neural network-related technology based on pattern recognition can effectively solve this problem, but at present, similar recognition and positioning technologies such as ground feature scene matching positioning technology and regional geomagnetic field feature classification and recognition positioning technology often require high resources and costs for regional modeling and labeling. At the same time, most of these technologies are indoor technologies applied to significant changes in the local distribution characteristics of the magnetic field. When processing geomagnetic signals, they often require more obvious numerical changes to detect changes, which leads to low position prediction accuracy, and may also affect the accuracy of flight navigation due to transmission error interference, so that the overall flight efficiency is affected.

[0004] Therefore, how to ensure that flight equipment can complete flight missions efficiently and according to the expected flight trajectory with high precision and low cost is a crucial issue. Summary of the invention

[0005] The present specification provides an aviation trajectory navigation method, device and electronic equipment based on geomagnetic signals to partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions:

[0007] This specification provides an aviation trajectory navigation method based on geomagnetic signals, including:

[0008] Acquire a historical trajectory geomagnetic sequence of the target object, where the historical trajectory geomagnetic sequence is used to represent a sequence of geomagnetic vectors collected on the historical motion trajectory of the target object at time points divided according to preset time intervals within a preset historical duration;

[0009] According to the determined geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence, a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object is generated, and a two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence is determined;

[0010] Determine the motion time characteristics corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor, and input the geomagnetic trajectory heat map into a preset spatial feature extraction model, so that the spatial feature extraction model determines the motion spatial characteristics corresponding to the target object according to the geomagnetic trajectory heat map;

[0011] According to the motion time feature and the motion space feature, the predicted position information corresponding to the target object at the next time point is determined, and trajectory navigation is performed on the target object based on the predicted position information.

[0012] Optionally, determining the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence specifically includes:

[0013] Performing noise filtering on the historical trajectory geomagnetic sequence to obtain a noise-filtered historical trajectory geomagnetic sequence;

[0014] According to the noise-filtered historical trajectory geomagnetic sequence, determining the magnetic field intensity change gradient corresponding to the noise-filtered historical trajectory geomagnetic sequence, and according to the magnetic field intensity change gradient and the noise-filtered historical trajectory geomagnetic sequence, determining the historical trajectory geomagnetic gradient sequence corresponding to the noise-filtered historical trajectory geomagnetic sequence;

[0015] The geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic gradient sequence is used as the determined geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence.

[0016] Optionally, generating a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object according to the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence specifically includes:

[0017] Obtaining a motion trajectory of the target object on a historical motion trajectory;

[0018] Based on a preset regional geomagnetic heat map, a geomagnetic trajectory heat map corresponding to the historical trajectory geomagnetic sequence is determined according to the geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence and the motion trajectory line.

[0019] Optionally, according to the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence, the two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence specifically includes:

[0020] Based on the time dimension of the historical trajectory geomagnetic sequence, the historical trajectory geomagnetic sequence is subjected to fast Fourier transform processing to determine the corresponding frequency components in the historical trajectory geomagnetic sequence and the frequency intensity corresponding to the frequency components;

[0021] According to a preset frequency intensity threshold, a target frequency component is determined from the frequency components, and according to the frequency corresponding to the target frequency component, a period corresponding to the target frequency component is determined as the geomagnetic change period corresponding to the historical trajectory geomagnetic sequence;

[0022] Based on the geomagnetic variation cycle and the frequency corresponding to the geomagnetic variation cycle, the historical trajectory geomagnetic sequence is subjected to sequence folding processing to determine the two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence.

[0023] Optionally, determining the motion time feature corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor specifically includes:

[0024] Inputting the two-dimensional geomagnetic tensor into a preset time feature extraction model, so that the time feature extraction model determines the two-dimensional time feature corresponding to the historical trajectory geomagnetic sequence according to the two-dimensional geomagnetic tensor;

[0025] The two-dimensional time feature is subjected to dimensionality reduction processing to obtain a one-dimensional time feature corresponding to the two-dimensional time feature, and the one-dimensional time feature is weighted and summed according to the frequency intensity corresponding to the target frequency component to obtain a weighted one-dimensional time feature as the motion time feature corresponding to the target object.

[0026] Optionally, determining predicted position information corresponding to the target object at a next time point according to the motion time feature and the motion space feature, and performing trajectory navigation on the target object based on the predicted position information specifically includes:

[0027] The motion time feature and the motion space feature are combined and fused to obtain a spatiotemporal feature vector corresponding to the target object;

[0028] The spatiotemporal feature vector is input into a pre-trained position prediction model so that the position prediction model predicts the position of the target object according to the spatiotemporal feature vector, obtains the coordinate position information corresponding to the target object at the next time point as the predicted position information, and performs trajectory navigation on the target object based on the predicted position information.

[0029] Optionally, training the location prediction model specifically includes:

[0030] Obtaining expected trajectory information and sample spatiotemporal feature vectors corresponding to the target object;

[0031] Inputting the expected trajectory information and the sample spatiotemporal feature vector into a position prediction model to be trained, so that the position prediction model to be trained predicts the position of the target object according to the sample spatiotemporal feature vector to obtain sample predicted position information;

[0032] According to the sample predicted position information and the expected trajectory position information corresponding to the sample spatiotemporal feature vector, a loss value for the position prediction model to be trained is determined, and according to the loss value, the position prediction model to be trained is trained, wherein the size of the loss value is negatively correlated with the degree of similarity between the sample predicted position information and the expected trajectory position information.

[0033] This specification provides an aviation trajectory navigation device based on geomagnetic signals, including:

[0034] An acquisition module, used to acquire a historical trajectory geomagnetic sequence of a target object, wherein the historical trajectory geomagnetic sequence is used to represent a sequence of geomagnetic vectors collected on a historical motion trajectory of the target object at time points divided according to preset time intervals within a preset historical duration;

[0035] A generation module, for generating a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object and determining a two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence according to the determined geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence;

[0036] A feature determination module, for determining the motion time feature corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor, and inputting the geomagnetic trajectory heat map into a pre-trained spatial feature extraction model, so that the spatial feature extraction model determines the motion spatial feature corresponding to the target object according to the geomagnetic trajectory heat map;

[0037] A prediction module is used to determine the predicted position information corresponding to the target object at the next time point according to the motion time characteristics and the motion space characteristics, and perform trajectory navigation on the target object based on the predicted position information.

[0038] The present specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned aviation trajectory navigation method based on geomagnetic signals is implemented.

[0039] The present specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned aviation trajectory navigation method based on geomagnetic signals when executing the program.

[0040] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0041] It can be seen from the above method that in the aviation trajectory navigation method based on geomagnetic signals provided in this specification, the geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object and the two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence can be determined according to the acquired historical trajectory geomagnetic sequence of the target object. Then, the motion time characteristics corresponding to the target object can be determined according to the two-dimensional geomagnetic tensor, and the geomagnetic trajectory heat map can be input into the pre-trained spatial feature extraction model, so that the spatial feature extraction model determines the motion space characteristics corresponding to the target object according to the received geomagnetic trajectory heat map. Finally, according to the motion time characteristics and motion space characteristics, the predicted position information corresponding to the target object at the next time point is determined, and the trajectory navigation of the target object is performed based on the predicted position information.

[0042] As can be seen from the above, the aviation trajectory navigation method based on geomagnetic signals provided in this specification can determine the motion time characteristics and motion space characteristics of the target object on the historical motion trajectory according to the acquired historical trajectory geomagnetic sequence of the target object, and then predict the position information of the target object at the next moment according to the motion time characteristics and motion space characteristics, so as to guide the target object to perform the motion task according to the expected trajectory. The method in this specification can effectively and accurately predict the future position information of the target object, and the accuracy of the predicted position information can be effectively improved by combining the time characteristics and the space characteristics, and effectively avoid the trajectory deviation problem caused by the cumulative error problem of the inertial navigation system in the current technology and the data transmission error caused by the long-distance transmission of indoor technology. The predicted position information determined by this specification can accurately navigate the target object to efficiently complete the task according to the expected trajectory, and the resources and costs consumed in the process are also extremely economical compared to the modeling and construction of geomagnetic features in the region, which effectively improves the efficiency of task execution while taking into account low-cost consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0044] Figure 1 A schematic diagram of a flow chart of an aviation trajectory navigation method based on geomagnetic signals provided in this specification;

[0045] Figure 2a , Figure 2b , Figure 2c An example schematic diagram of a geomagnetic trajectory heat map determination process provided in this specification;

[0046] Figure 3 This is a schematic diagram of the overall process structure of an aviation trajectory navigation method based on geomagnetic signals provided in this specification;

[0047] Figure 4 A schematic diagram of an aviation trajectory navigation device based on geomagnetic signals provided in this specification;

[0048] Figure 5 A method provided in this specification corresponding to Figure 1 Schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0050] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0051] Figure 1 A schematic diagram of a flow chart of an aviation trajectory navigation method based on geomagnetic signals provided in this specification includes the following steps:

[0052] S101: Acquire the historical trajectory geomagnetic sequence of the target object.

[0053] At present, the increasingly mature and widely popular space flight technology has brought great practicality and convenience to various fields. It is extremely important for flight equipment to fly accurately according to the expected trajectory in the aerospace field. At present, the more traditional technology mainly corrects the inertial navigation trajectory that deviates from the expected track through rigid transformation. The expected trajectory information needs to be predicted during the positioning process, and the application effect is not good when facing nonlinear mapping scenarios such as complex terrain.

[0054] Related technologies such as the classification, identification and positioning technology of geomagnetic field characteristics in similar regions based on neural networks can overcome the above shortcomings. However, such technologies require modeling of magnetic field characteristics in the positioning area in advance, which is extremely resource-consuming and time-consuming. In addition, such technologies are mostly used for indoor monitoring and positioning where the local distribution characteristics of the magnetic field change significantly. When facing outdoor and large-scale navigation and positioning scenarios, the navigation effect accuracy is poor. Therefore, how to ensure high accuracy and achieve low-cost consumption so that the flight equipment can complete the flight mission according to the preset trajectory, thereby achieving accurate navigation of the flight equipment, is a very important issue.

[0055] To this end, this specification provides an aviation trajectory navigation method based on geomagnetic signals, wherein the execution subject adopted by the method provided in this specification can be a terminal device with a geomagnetic signal collection function such as a desktop computer, a laptop computer, or a server. In addition, the execution subject of this specification can also be a subject in the form of software, such as a client installed in a terminal device with a geomagnetic signal collection function. For the sake of convenience, this specification below only takes the terminal device as the execution subject to explain the provided aviation trajectory navigation method based on geomagnetic signals.

[0056] Based on this, the terminal device using the aviation trajectory navigation method based on geomagnetic signals provided in this specification can obtain the historical trajectory geomagnetic sequence collected for the target object on the historical motion trajectory. According to the historical trajectory geomagnetic sequence, the terminal device can determine the motion space characteristics and motion time characteristics of the target object on the historical motion trajectory, and predict the next position information of the target object based on the motion space characteristics and motion time characteristics to guide the target object to fly.

[0057] Among them, the application scenario of the trajectory navigation task performed by the terminal device for the target object can be determined according to the actual application needs. For example, for artificially controlled flight equipment such as civil airliners and helicopters, the terminal device can determine the spatial characteristics and time characteristics corresponding to the flight equipment on the historical motion trajectory based on the historical trajectory geomagnetic sequence collected by the flight equipment, and predict the next motion position of the flight equipment based on the spatiotemporal characteristics, and display the predicted position results to the relevant maintenance personnel. The maintenance personnel can operate the flight equipment to fly according to the predicted position results, or adjust the operating status and parameters of the current flight equipment according to the predicted position results to ensure that the deviation between the inertial navigation trajectory of the flight equipment and the expected trajectory is minimized.

[0058] For another example, for unmanned aerial devices that can automatically perform tasks without human control in the field of drones, the terminal device can determine the spatial and temporal characteristics corresponding to the unmanned aerial device based on the historical trajectory geomagnetic sequence collected by the unmanned aerial device, and predict the position information of the unmanned aerial device at the next moment based on the fusion vector of the spatial and temporal characteristics. The unmanned aerial device can perform flight missions based on the prediction results, and correct the inertial navigation system errors at the same time, thereby effectively avoiding deviations between the actual flight trajectory and the expected trajectory, ensuring that the target task is accurately performed according to the flight trajectory, and also effectively improving the task execution efficiency corresponding to the target task.

[0059] In this specification, a terminal device can obtain the historical trajectory geomagnetic sequence of a target object, wherein a terminal device applying the method in this specification can be set up on a target object, thereby facilitating real-time collection of the historical trajectory geomagnetic sequence of the target object during the movement of the target object.

[0060] In addition, the terminal device can also obtain the pre-set expected trajectory information corresponding to the target object, such as by requesting GPS data. The expected trajectory information is actively planned for the flight mission performed by the target object, and can be used to indicate the flight trajectory corresponding to the target object under the most ideal conditions when performing the flight mission. In the aviation trajectory navigation process of this manual, the expected trajectory information may not be directly involved in the subsequent position prediction based on spatiotemporal fusion features, and can only be used for reference, comparison and evaluation of the final predicted position information.

[0061] Regarding the historical trajectory geomagnetic sequence of the target object, it can be specifically used to indicate that multiple collection time points are divided according to preset time intervals within a preset historical duration, and data is collected for the geomagnetic vector corresponding to each time point on the historical motion trajectory of the target object. The geomagnetic vectors corresponding to each time point together constitute the historical trajectory geomagnetic sequence corresponding to the target object. Among them, the geomagnetic vector collected for each time point or position can specifically have three components, which correspond to the components of the geomagnetic field at the location of the target object in the north, east and vertical directions, that is, the geomagnetic components in the x-axis, y-axis and z-axis directions.

[0062] Specifically, assuming that the preset time interval for the historical trajectory geomagnetic sequence of the target object is 1s, the total data collection time is the last 10s of the historical movement process, that is, the preset number of time points is 10. The terminal device can obtain the geomagnetic vector of the target object at the corresponding time point according to the preset time interval and the corresponding number of time points. The specific data format can be { }, where each The geomagnetic vector used to represent the geographical location of the target object at the current time point may specifically include the three-directional geomagnetic components of the geomagnetic field at the location of the target object mentioned above in the north, east and vertical directions.

[0063] S102: generating a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object and determining a two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence according to the determined geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence.

[0064] In this specification, the terminal device can determine the geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object and the two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence based on the acquired historical trajectory geomagnetic sequence corresponding to the target object.

[0065] It should be noted in advance that this specification takes into account that the geomagnetic vector data directly obtained may have noise problems or device heterogeneity problems, which may affect the accuracy of subsequent position prediction results. Therefore, after collecting the historical trajectory geomagnetic sequence corresponding to the target object, the terminal device using the method in this specification can perform noise filtering on the historical trajectory geomagnetic sequence to obtain the historical trajectory geomagnetic sequence after noise filtering.

[0066] Then, the terminal device can determine the corresponding magnetic field intensity change gradient according to the historical trajectory geomagnetic sequence after noise filtering, and thus determine the historical trajectory geomagnetic gradient sequence corresponding to the historical trajectory geomagnetic sequence after noise filtering according to the historical trajectory geomagnetic sequence after noise filtering and the determined magnetic field intensity change gradient. The terminal device can use the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic gradient sequence as the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence.

[0067] Regarding the determination process of the above-mentioned geomagnetic trajectory heat map, specifically, the terminal device can pre-determine and obtain the regional geomagnetic heat map corresponding to the large-scale area corresponding to the location of the target object, and based on the historical motion trajectory of the target object, obtain the motion trajectory line of the target object on the historical motion trajectory.

[0068] Then, based on the regional geomagnetic heat map, the terminal device can determine the geomagnetic measurement sequence values ​​corresponding to the sampling points of the historical motion trajectory of the target object according to the corresponding positions of each time point in the historical trajectory sequence on the motion trajectory line. Next, the terminal device can fold the geomagnetic measurement sequence values ​​corresponding to the historical motion trajectory with a fixed length to determine the geomagnetic trajectory heat map of the historical trajectory geomagnetic sequence.

[0069] Among them, the regional geomagnetic heat map can be specifically an RGB color geomagnetic heat map pre-constructed according to the different geomagnetic signal intensities in the region. The three color components corresponding to each pixel in the map: red (R), green (G) and blue (B), respectively correspond to the geomagnetic components of the x-axis, y-axis and z-axis of the geomagnetic component of the pixel point in the region. The terminal device can determine the geomagnetic trajectory heat map corresponding to the historical trajectory geomagnetic sequence according to the motion trajectory of the target object and the corresponding regional geomagnetic heat map. The geomagnetic trajectory heat map can be specifically used to represent the geomagnetic signal change process of the geomagnetic vector corresponding to each time point in the historical trajectory geomagnetic sequence in the form of an RGB color image.

[0070] In order to facilitate the understanding of the specific manifestation of the geomagnetic trajectory heat map, the following is an explanation of the process of determining the geomagnetic trajectory heat map corresponding to a historical trajectory geomagnetic sequence. For details, please refer to Figure 2a , Figure 2b , Figure 2c .

[0071] Figure 2a , Figure 2b , Figure 2c An example schematic diagram of a geomagnetic trajectory heat map determination process provided in this specification.

[0072] Figure 2a The grayscale image of the regional geomagnetic heat map corresponding to the location of the target object is shown in FIG. For ease of understanding, it is assumed that the target object moves twice along different trajectories in the area corresponding to the regional geomagnetic heat map. The corresponding movement trajectory lines are Figure 2a The terminal device can determine the geomagnetic trajectory heat map of the historical trajectory geomagnetic sequence according to the trajectory direction of the motion trajectory line in the regional geomagnetic heat map, such as Figure 2b and Figure 2c as shown in .

[0073] Figure 2b The grayscale image shown in FIG. 1 is used to represent the geomagnetic trajectory heat map corresponding to the target object when it moves along the motion trajectory line traj1. Figure 2c The grayscale image shown in the figure is used to represent the geomagnetic trajectory heat map corresponding to the target object when it moves along the motion trajectory line traj2. It is not difficult to see from the example in the figure that no matter how the motion trajectory actually changes, the motion trajectory line can express the change process of the geomagnetic signal between the various positions passed by the target object in the corresponding motion trajectory in the form of image color changes. In practical applications, the change of the image color RGB value of the geomagnetic heat map can well reflect the change of the corresponding intensity of the geomagnetic vector between each time point, and to a certain extent reflect the spatial characteristics of the target object on the historical motion trajectory.

[0074] In addition, while determining the geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object according to the historical trajectory geomagnetic sequence, the terminal device can also determine the two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence according to the historical trajectory geomagnetic sequence.

[0075] Specifically, the terminal device may perform a fast Fourier transform on the historical trajectory geomagnetic sequence according to the time dimension in the historical trajectory geomagnetic sequence, thereby determining the corresponding frequency components in the historical trajectory geomagnetic sequence and the frequency intensity corresponding to each frequency component.

[0076] Then, the terminal device can determine a single or multiple target frequency components from each frequency component according to a preset frequency intensity threshold, and determine the period corresponding to the target frequency component according to the frequency corresponding to the target frequency component. The terminal device can use the period corresponding to the target frequency component as the geomagnetic change period corresponding to the above historical trajectory geomagnetic sequence.

[0077] The determination process of the above geomagnetic change period can be specifically referred to the following formula:

[0078]

[0079]

[0080]

[0081] in, It is specifically used to represent the historical trajectory geomagnetic sequence (the specific data format can be, for example, the { }), For Perform a fast Fourier transform ( ) and other formulas to determine the frequency intensity corresponding to each frequency component in the historical trajectory geomagnetic sequence. The second line of formulas above is used to calculate the frequency intensity corresponding to each frequency component in the historical trajectory geomagnetic sequence. Select the frequency components corresponding to the historical trajectory geomagnetic sequence whose intensity is ranked in the front The frequency components of It is used to indicate the previous The frequency magnitudes corresponding to the frequency components. The historical trajectory geomagnetic sequence The corresponding length of time, Corresponding to the previous The period of the frequency component. The above formula can be simplified to the following formula:

[0082]

[0083] After the calculation of the above formula, the terminal device can obtain the historical trajectory geomagnetic sequence , determine the historical trajectory geomagnetic sequence The intensity ranks first in each corresponding frequency component The period corresponding to the frequency component , and use it as a historical trajectory geomagnetic sequence The corresponding geomagnetic change cycle. Through the above cycle calculation process, the magnetic field characteristics of the historical trajectory geomagnetic sequence changing with time can be effectively displayed in the subsequent time feature extraction process, which makes the motion time characteristics more significant and easier to extract to a certain extent, effectively improving the accuracy of the final predicted position information.

[0084] Next, the terminal device can determine the corresponding motion time characteristics of the target object when it runs on the historical motion trajectory according to the geomagnetic sequence of the historical trajectory of the target object and the geomagnetic change cycle determined by the above process.

[0085] Specifically, the terminal device can perform sequence folding processing on the historical trajectory geomagnetic sequence based on the geomagnetic change cycle and the corresponding frequency corresponding to the historical trajectory geomagnetic sequence, so as to determine the two-dimensional geomagnetic tensor data corresponding to the historical trajectory geomagnetic sequence. For the specific operation flow of the folding process, please refer to the following formula:

[0086]

[0087] ,

[0088] In which, similar to the above formula, Specifically used to represent the historical trajectory geomagnetic sequence, Used to indicate the The frequency corresponding to the target frequency component, It is used to indicate the The period corresponding to the target frequency component. Specifically used in historical trajectory geomagnetic sequences The last bit of the operation, can be determined by the period of the frequency component Divisible. It is specifically used to represent the two-dimensional geomagnetic tensor data obtained after the target frequency component is processed by sequence folding. The two-dimensional geomagnetic tensor set shown in the second row can be obtained through the first row formula in the above formula. , .

[0089] By folding the historical trajectory geomagnetic sequence using the above formula, we can obtain the two-dimensional geomagnetic tensor data corresponding to the historical trajectory geomagnetic sequence. In the two-dimensional geomagnetic tensor, each column tensor and each row tensor correspond to adjacent moments and adjacent periods in the historical trajectory geomagnetic sequence. Among them, similar moments and periods can often reflect similar time series changes in data characteristics, thus forming more obvious two-dimensional local features, and the time characteristics in the historical trajectory geomagnetic sequence can be more significantly reflected by the two-dimensional geomagnetic tensor, which provides a favorable guarantee for the accuracy of subsequent prediction of motion positions.

[0090] S103: Determine the motion time characteristics corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor, and input the geomagnetic trajectory heat map into a preset spatial feature extraction model, so that the spatial feature extraction model determines the motion spatial characteristics corresponding to the target object according to the geomagnetic trajectory heat map.

[0091] In this specification, the terminal device can determine the corresponding motion time characteristics of the target object when it moves on the historical motion trajectory based on the historical trajectory geomagnetic sequence of the target object and the two-dimensional geomagnetic tensor determined by the above steps.

[0092] Specifically, the terminal device can input the two-dimensional geomagnetic tensor determined by the above steps into a preset time feature extraction model, so that the preset time feature extraction model can extract the two-dimensional time features corresponding to the historical trajectory geomagnetic sequence according to the received two-dimensional geomagnetic tensor. It should be noted that the above-mentioned time feature extraction model in this specification can adopt a Swin Transformer model, which has the advantages of high precision, high timeliness and attention to global and local information at the same time. This design allows the time series analysis task to directly benefit from the advanced visual backbone network.

[0093] The two-dimensional time features corresponding to the historical trajectory geomagnetic sequence can be extracted through the Swin Transformer model. The specific formula can be referred to as follows:

[0094]

[0095] in, It is specifically used to represent the two-dimensional geomagnetic tensor data corresponding to the historical trajectory geomagnetic sequence. It corresponds to the two-dimensional time characteristics of the historical trajectory geomagnetic sequence extracted by the Swin Transformer model.

[0096] Then, in order to ensure the uniformity of data dimensions in subsequent position prediction, the terminal device can perform dimensionality reduction processing on the two-dimensional time features obtained through the above process, thereby obtaining a one-dimensional time feature corresponding to the two-dimensional time feature. Next, the terminal device can perform weighted summation on the above one-dimensional time features according to the frequency intensity corresponding to the target frequency component determined in the above steps, thereby obtaining a one-dimensional time feature corresponding to the historical trajectory geomagnetic sequence after weighted summation, as the motion time feature corresponding to the target object.

[0097] Regarding the dimensionality reduction process performed on the two-dimensional time features, the following formula can be referred to:

[0098]

[0099] in, It is specifically used to represent the two-dimensional time characteristics corresponding to the historical trajectory geomagnetic sequence, which has the same meaning as the formula in the above content. Used to indicate the The frequency corresponding to the target frequency component, It is used to indicate the The period corresponding to the target frequency component, and the formula It is used to convert the above two-dimensional geomagnetic tensor data into Through the calculation process corresponding to this formula, the terminal device can reduce the two-dimensional time characteristics. The corresponding tensor dimension is obtained to obtain the one-dimensional time characteristics corresponding to the historical trajectory geomagnetic sequence .

[0100] The specific processing process of one-dimensional time features according to frequency intensity can refer to the following formula:

[0101]

[0102]

[0103] in, It is used to represent the frequency intensity corresponding to each target frequency component. The first row of formulas is used to Based on the frequency intensity corresponding to each target frequency component , determine the weight corresponding to each target frequency component, that is, Then, through the weighted summation of the next row formula, the terminal device can determine the one-dimensional time feature corresponding to the weighted summation of the historical trajectory geomagnetic sequence, and then use it as the motion time feature corresponding to the target object, that is, .

[0104] It should be noted that the overall process of determining the motion time characteristics corresponding to the target object based on the geomagnetic change cycle can be actually implemented through the mathematical model of TimesNet, which can overcome the problem of insufficient long-term dependency modeling capabilities of LSTM networks. Among them, the TimesNet model contains a stacked TimesBlock structure. After feature extraction of multiple layers of TimesBlock structures, deeper time characteristics in the historical trajectory geomagnetic sequence can be better extracted. The specific model category can also be flexibly adjusted according to the actual application scenario.

[0105] In addition, in the present specification, while determining the motion time characteristics corresponding to the target object through the above steps, the terminal device can also input the geomagnetic trajectory heat map corresponding to the historical trajectory geomagnetic sequence determined by the above steps into the pre-trained spatial feature extraction model, so that the spatial feature extraction model can determine the motion spatial characteristics corresponding to the target object in the historical trajectory geomagnetic sequence based on the received geomagnetic trajectory heat map.

[0106] Among them, the spatial feature extraction model can adopt the M-Darknet-PAFPN structure model. Darknet is a deep convolutional neural network that supports the YOLO (You Only Look Once) target detection algorithm, and PAFPN is a path aggregation feature pyramid network. The full English name is Path Aggregation Feature Pyramid Network. When the model itself is applied, it can better integrate multi-scale features in the data, thereby improving the overall model's detection ability for objects or objects of different sizes. The spatial feature extraction model mentioned in this manual can be composed of the above two neural networks, which is similar to the YOLOX (You Only Look Once with eXcitement) model commonly used in current technology, but there are some obvious differences.

[0107] In this specification, considering that most of the computing models supporting the YOLO target detection algorithm in the current technology perform target detection on natural images, and the geomagnetic trajectory heat map of the historical trajectory geomagnetic sequence is relatively special compared to the natural images in the ordinary technical field, in order to ensure the accuracy of the features extracted by the model and maintain a unified data dimension with the motion time features obtained by the above process, in this specification, the prediction head part of the YOLOX (YouOnly Look Once with eXcitement) model can be removed in the final feature output stage and replaced with a preset number of n CBL (Convolution-Batch Normalization-Leaky ReLU) modules, so that the final output features of the overall model can be mapped to a low-dimensional feature vector, which is convenient for executing subsequent spatiotemporal fusion and position prediction processes.

[0108] For example, the spatial feature extraction model of the M-Darknet-PAFPN structure proposed in this specification is different from the YOLOX model in that n CBL modules are provided before the final feature generation to reduce the feature tensor dimension. In addition, the target feature data of the normal YOLOX model when output to the final prediction head part often has different feature data corresponding to multiple dimensions. Assuming that the terminal device inputs the geomagnetic trajectory heat map corresponding to the historical trajectory geomagnetic sequence in the format of 640*640 into the YOLOX model, the feature data before inputting into the prediction head part will contain 1*256*80*80 dimensional level, 1*512*80*80 dimensional level, 1*1024*40*40 dimensional level and other multi-dimensional feature data. The normal calculation process will combine feature data of multiple dimensions, and the amount of calculation is relatively large, which may affect the overall processing efficiency of the model.

[0109] The spatial feature extraction model of the M-Darknet-PAFPN structure in this specification can only select feature data at the 1*256*80*80 dimensional level when processing the final feature generation, and input it into multiple preset CBL modules. The feature data is low-dimensionally mapped and normalized through the CBL module, and finally the linear activation process is completed through the linear activation function, so as to obtain the motion space characteristics corresponding to the target object in the historical trajectory geomagnetic sequence.

[0110] Regarding the specific process of the CBL module performing data processing on the feature data, please refer to the following formula:

[0111]

[0112]

[0113]

[0114] in, is a high-dimensional feature tensor of the selected dimension (e.g., feature data at the 1*256*80*80 dimension level in the above example), After the high-dimensional feature tensor The first line of the formula above calculates the low-dimensional feature tensor after dimension mapping. The second line of the formula is used as a whole for the low-dimensional feature tensor The normalization calculation process is is the normalized vector data calculated by the formula. The third line of formula is the linear activation function, which is activated by the variant linear correction unit (Leaky ReLU) in the CBL module. Execute the linear activation process. Finally, the terminal device can obtain the motion spatial features corresponding to the target object in the historical trajectory geomagnetic sequence through the spatial feature extraction model. , in the above formula , , , , , are all optimizable learning parameters in the training process of the spatial feature extraction model, and and Represents mean calculation and standard deviation calculation respectively.

[0115] S104: Determine predicted position information corresponding to the target object at a next time point according to the motion time feature and the motion space feature, and perform trajectory navigation on the target object based on the predicted position information.

[0116] In this specification, the terminal device can predict the location information corresponding to the target object at the next time point based on the motion time characteristics and motion space characteristics determined by the above steps. Then, the terminal device can perform trajectory navigation on the target object based on the generated predicted location information, so that the target object completes the task according to the normal expected trajectory.

[0117] Specifically, since the vector dimensions corresponding to the motion time features and motion space features determined through the above steps are the same and are both one-dimensional feature data, the terminal device can perform vector splicing and fusion processing on the motion time features and motion space features corresponding to the target object on the historical motion trajectory to obtain the spatiotemporal feature vector corresponding to the target object. Then, the terminal device can predict the position of the target object based on the spatiotemporal feature vector corresponding to the target object, determine the coordinate position information corresponding to the target object at the next time point, and use it as the predicted position information.

[0118] In this specification, the specific method of position prediction may be a position regression processing operation, which may be implemented by using a preset fully connected layer (FC) module as a position prediction model. The terminal device may input the above-mentioned spatiotemporal feature vector into a pre-trained position prediction model, so that the position prediction model may perform position prediction on the target object according to the spatiotemporal feature vector, and obtain the coordinate position information corresponding to the target object at the next time point as the predicted position information.

[0119] It should be noted that the terminal device can pre-train the position prediction model based on the set expected trajectory information, that is, perform model training on the above-mentioned fully connected layer module, so that the fully connected layer module can effectively memorize the mapping relationship between the expected trajectory information and the time and space fusion features. This ensures that when performing the above-mentioned position prediction, the predicted position information of the target object can be accurately determined based on the time and space feature vector of the target object to adjust the motion trajectory of the target object so that the deviation error between the inertial navigation trajectory during its actual movement and the expected trajectory is close to zero. In addition, the specific application method of the position prediction operation can be flexibly adjusted according to the actual application scenario and needs, and is not strictly limited in this manual.

[0120] Regarding the training process of the position prediction model, the terminal device can input the expected trajectory information and sample spatiotemporal feature vector corresponding to the acquired target object into the position prediction model to be trained, so that the position prediction model to be trained can predict the position of the target object according to the received sample spatiotemporal feature vector, thereby obtaining the sample predicted position information. Then, the terminal device can determine the loss value of the position prediction model to be trained during the training process according to the obtained sample predicted position information and the expected trajectory position information corresponding to the sample spatiotemporal feature vector, and train the position prediction model to be trained according to the loss value, and adjust the network parameter size of the position prediction model to be trained so that the prediction result of the position prediction model can be closer to the expected trajectory information. Among them, the size of the loss value is negatively correlated with the closeness between the sample predicted position information and the expected trajectory position information.

[0121] In addition, the time interval between the predicted position information and the current position obtained through the above process can also be adjusted according to demand. In this specification, the time interval between the predicted position information and the current position will not be strictly limited to the time interval between each time point in the historical trajectory geomagnetic sequence. For example, assuming that the historical trajectory geomagnetic sequence is a geomagnetic sequence collected at a time interval of 2s and a total duration of 10s, the predicted position information when predicting the position information of the target object through the above steps can be the predicted position information of the target position 2s after the corresponding time of the last sampling point. The length of time can also be flexibly set according to actual needs, for example, it can also be the predicted information 5s or 1s after the last sampling point.

[0122] Among them, it is necessary to additionally explain that the position corresponding to the last sampling point may not normally coincide with the current position of the target object when the predicted position information is generated. When the target object moves slowly or the position prediction time is extremely short, the position corresponding to the last sampling point may be close to the current position of the target object when the predicted position information is generated.

[0123] In addition, generally speaking, the position of the last sampling time point in the historical trajectory geomagnetic sequence is often a certain distance away from the actual position of the target object when the predicted position information is determined, and in actual applications, the calculation time of the position prediction process is often less than 1s. Therefore, a reasonable setting of the historical trajectory sampling interval can make the predicted position closer to the actual position. In short, the time interval between the two can be flexibly set according to needs, and there is no strict numerical limit.

[0124] Furthermore, after the terminal device determines the predicted position information for the target object, it can feed back the predicted position information to the target object to guide or prompt the target object to move according to the predicted position information, and play a role in accurate motion navigation for the target object, thereby effectively reducing the impact of the cumulative error problem that is common in the inertial navigation trajectory on the deviation of the actual motion trajectory. For example, in a flight scenario where there is active control by personnel, the terminal device can determine the predicted position information of the target object at the next moment according to the historical trajectory geomagnetic sequence corresponding to the target object through the above steps, and feed it back to the operator of the target object to prompt the relevant personnel of the future flight trajectory of the current target object, so as to ensure that the flight mission of the target object can proceed normally according to the predicted trajectory, and will not deviate from the expected trajectory due to the cumulative error problem of the inertial navigation system (INS).

[0125] In order to facilitate the understanding of the overall process from the historical trajectory geomagnetic sequence to the generation of the predicted position information of the target object, the following is an overall flow structure diagram of the aviation trajectory navigation method based on geomagnetic signals for explanation, as shown below: Figure 3 as shown in .

[0126] Figure 3 The present invention provides a schematic diagram of the overall process structure of an aviation trajectory navigation method based on geomagnetic signals provided in this specification.

[0127] like Figure 3 As shown, the terminal device can perform data preprocessing on the acquired historical trajectory geomagnetic sequence, that is, the noise filtering and gradient processing process in the above steps. Then, the terminal device can determine the motion time characteristics and motion space characteristics of the target object on the historical motion trajectory based on the geomagnetic vector value corresponding to each sampling time point in the processed historical trajectory geomagnetic sequence. Next, the terminal device can perform data splicing and fusion of the motion time characteristics and motion space characteristics in the form of one-dimensional tensor data, and input the fused spatiotemporal feature vector into the position prediction model pre-trained based on the expected trajectory information of the target object, and perform position regression processing according to the spatiotemporal feature vector through the position prediction model, so as to obtain the predicted position information of the target object.

[0128] In addition to the above, in this specification, the trajectory prediction network model based on the above-mentioned feature extraction process and position prediction process can be trained as a whole, and the model accuracy of the overall trajectory prediction network model can be adjusted by optimizing the error loss value of the predicted position obtained in the end. The specific training process of the trajectory prediction network model of the trajectory navigation method based on geomagnetic signals provided in this specification can be realized by referring to the following formula:

[0129]

[0130] in, Used to represent the positioning error of the trajectory prediction network model during the training process. It is used to represent the predicted position information predicted by the trajectory prediction network model to be trained based on the sample data, and It is used to represent the standard prediction position information corresponding to the sample data. Used to indicate the number of predicted points. Through the above formula, the positioning error is minimized Adjust the model parameters of each part of the trajectory prediction network model (for example, the CBL module in the above motion space feature extraction process , , , , as well as ), optimize the overall trajectory prediction network model, thereby improving the accuracy of the final predicted position information in practical applications.

[0131] In addition, the EMA (Exponential Moving Average) weight update method in the current technology can effectively smooth the weight distribution in the model during the training process, so that the generalization ability and stability of the model can be improved. Cosine learning rate scheduling (CosineLRScheduler) is a strategy for dynamically adjusting the learning rate. This method can adjust the model learning rate according to the periodic changes of the cosine function, help the model escape the local optimal solution, and promote better convergence. Therefore, in order to improve the training effect of the overall trajectory prediction network model, the above-mentioned EMA weight update, cosine learning rate scheduling and other training methods can be integrated into the training process of the trajectory prediction network model, so that the trajectory prediction network model can obtain more accurate and efficient location prediction capabilities through the training process.

[0132] From the above content, it can be seen that the aviation trajectory navigation method based on geomagnetic signals provided in this specification can determine the movement time characteristics and movement space characteristics of the target object on the historical movement trajectory according to the acquired historical trajectory geomagnetic sequence of the target object, and then predict the position information of the target object at the next moment based on the movement time characteristics and movement space characteristics, so as to guide the target object to perform the movement task according to the expected trajectory.

[0133] The method in this manual can effectively and accurately predict the future location information of the target object, and by combining time features and spatial features, the accuracy of the predicted position can be effectively improved, which greatly avoids the trajectory deviation problem caused by the cumulative error problem of the inertial navigation system in the current technology, and can accurately navigate the target object to complete the task efficiently according to the expected trajectory. At the same time, the resources and costs consumed by this method are greatly reduced compared to modeling and building geomagnetic features in the region, and the beneficial effects of low cost and high efficiency are very obvious.

[0134] The above are one or more implementation methods of this specification. Based on the same idea, this specification also provides a corresponding aviation trajectory navigation device based on geomagnetic signals, such as Figure 4 shown.

[0135] Figure 4 This is a schematic diagram of an aviation trajectory navigation device based on geomagnetic signals provided in this specification, including:

[0136] An acquisition module 401 is used to acquire a historical track geomagnetic sequence of a target object, where the historical track geomagnetic sequence is used to represent a sequence of geomagnetic vectors collected on a historical motion track of the target object at time points divided according to preset time intervals within a preset historical duration;

[0137] A generating module 402 is used to generate a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object and determine a two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence according to the determined geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence;

[0138] A feature determination module 403 is used to determine the motion time feature corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor, and input the geomagnetic trajectory heat map into a pre-trained spatial feature extraction model, so that the spatial feature extraction model determines the motion spatial feature corresponding to the target object according to the geomagnetic trajectory heat map;

[0139] The prediction module 404 is used to determine the predicted position information corresponding to the target object at the next time point according to the motion time feature and the motion space feature, and perform trajectory navigation on the target object based on the predicted position information.

[0140] Optionally, the generating module 402 is specifically used to perform noise filtering on the historical trajectory geomagnetic sequence to obtain the noise-filtered historical trajectory geomagnetic sequence; determine the magnetic field intensity change gradient corresponding to the noise-filtered historical trajectory geomagnetic sequence according to the noise-filtered historical trajectory geomagnetic sequence, and determine the historical trajectory geomagnetic gradient sequence corresponding to the noise-filtered historical trajectory geomagnetic sequence according to the magnetic field intensity change gradient and the noise-filtered historical trajectory geomagnetic sequence; and use the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic gradient sequence as the determined geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence.

[0141] Optionally, the generation module 402 is specifically used to obtain the motion trajectory line of the target object on the historical motion trajectory; based on a preset regional geomagnetic heat map, according to the geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence and the motion trajectory line, determine the geomagnetic trajectory heat map corresponding to the historical trajectory geomagnetic sequence.

[0142] Optionally, the generation module 402 is specifically used to perform fast Fourier transform processing on the historical trajectory geomagnetic sequence based on the time dimension of the historical trajectory geomagnetic sequence, and determine the corresponding frequency components in the historical trajectory geomagnetic sequence and the frequency intensity corresponding to the frequency components; determine the target frequency component from the frequency components according to a preset frequency intensity threshold, and determine the period corresponding to the target frequency component according to the frequency corresponding to the target frequency component as the geomagnetic change period corresponding to the historical trajectory geomagnetic sequence; based on the geomagnetic change period and the frequency corresponding to the geomagnetic change period, perform sequence folding processing on the historical trajectory geomagnetic sequence to determine the two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence.

[0143] Optionally, the feature determination module 403 is specifically used to input the two-dimensional geomagnetic tensor into a preset time feature extraction model, so that the time feature extraction model determines the two-dimensional time feature corresponding to the historical trajectory geomagnetic sequence based on the two-dimensional geomagnetic tensor; performs dimensionality reduction processing on the two-dimensional time feature to obtain a one-dimensional time feature corresponding to the two-dimensional time feature, and performs weighted summation on the one-dimensional time feature according to the frequency intensity corresponding to the target frequency component to obtain the weighted one-dimensional time feature as the motion time feature corresponding to the target object.

[0144] Optionally, the prediction module 404 is specifically used to perform feature splicing and fusion on the motion time features and the motion space features to obtain a spatiotemporal feature vector corresponding to the target object; input the spatiotemporal feature vector into a pre-trained position prediction model, so that the position prediction model predicts the position of the target object based on the spatiotemporal feature vector, obtains the coordinate position information corresponding to the target object at the next time point as the predicted position information, and performs trajectory navigation on the target object based on the predicted position information.

[0145] Optionally, the prediction module 404 is specifically used to obtain expected trajectory information and a sample spatiotemporal feature vector corresponding to the target object; input the expected trajectory information and the sample spatiotemporal feature vector into a position prediction model to be trained, so that the position prediction model to be trained predicts the position of the target object according to the sample spatiotemporal feature vector to obtain sample predicted position information; determine a loss value for the position prediction model to be trained according to the sample predicted position information and the expected trajectory position information corresponding to the sample spatiotemporal feature vector, and train the position prediction model to be trained according to the loss value, wherein the size of the loss value is negatively correlated with the similarity between the sample predicted position information and the expected trajectory position information.

[0146] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 An aviation trajectory navigation method based on geomagnetic signals is provided.

[0147] This manual also provides Figure 5 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 5 As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The aviation trajectory navigation method based on geomagnetic signals.

[0148] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0149] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0150] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0151] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0152] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0154] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0155] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0156] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0157] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0158] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0159] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0160] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0161] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0162] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0163] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. An aviation trajectory navigation method based on geomagnetic signals, characterized in that: include: Acquire a historical trajectory geomagnetic sequence of the target object, where the historical trajectory geomagnetic sequence is used to represent a sequence of geomagnetic vectors collected on the historical motion trajectory of the target object at time points divided according to preset time intervals within a preset historical duration; According to the determined geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence, a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object is generated, and a two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence is determined, wherein the geomagnetic trajectory heat map is used to characterize the geomagnetic signal change process displayed in the form of an RGB color image of the geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence; Determine the motion time characteristics corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor, and input the geomagnetic trajectory heat map into a preset spatial feature extraction model, so that the spatial feature extraction model determines the motion spatial characteristics corresponding to the target object according to the geomagnetic trajectory heat map; According to the motion time feature and the motion space feature, the predicted position information corresponding to the target object at the next time point is determined, and trajectory navigation is performed on the target object based on the predicted position information.

2. The method according to claim 1, characterized in that Determining the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence specifically includes: Performing noise filtering on the historical trajectory geomagnetic sequence to obtain a noise-filtered historical trajectory geomagnetic sequence; According to the noise-filtered historical trajectory geomagnetic sequence, determining the magnetic field intensity change gradient corresponding to the noise-filtered historical trajectory geomagnetic sequence, and according to the magnetic field intensity change gradient and the noise-filtered historical trajectory geomagnetic sequence, determining the historical trajectory geomagnetic gradient sequence corresponding to the noise-filtered historical trajectory geomagnetic sequence; The geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic gradient sequence is used as the determined geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence.

3. The method according to claim 1, characterized in that Generating a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object according to the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence, specifically comprising: Obtaining a motion trajectory of the target object on a historical motion trajectory; Based on a preset regional geomagnetic heat map, a geomagnetic trajectory heat map corresponding to the historical trajectory geomagnetic sequence is determined according to the geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence and the motion trajectory line.

4. The method according to claim 1, characterized in that Determining a two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence according to the geomagnetic vector value corresponding to each time point in the historical trajectory geomagnetic sequence specifically includes: Based on the time dimension of the historical trajectory geomagnetic sequence, the historical trajectory geomagnetic sequence is subjected to fast Fourier transform processing to determine the corresponding frequency components in the historical trajectory geomagnetic sequence and the frequency intensity corresponding to the frequency components; According to a preset frequency intensity threshold, a target frequency component is determined from the frequency components, and according to the frequency corresponding to the target frequency component, a period corresponding to the target frequency component is determined as the geomagnetic change period corresponding to the historical trajectory geomagnetic sequence; Based on the geomagnetic variation cycle and the frequency corresponding to the geomagnetic variation cycle, the historical trajectory geomagnetic sequence is subjected to sequence folding processing to determine the two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence.

5. The method according to claim 4, characterized in that Determining the motion time characteristics corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor, specifically includes: Inputting the two-dimensional geomagnetic tensor into a preset time feature extraction model, so that the time feature extraction model determines the two-dimensional time feature corresponding to the historical trajectory geomagnetic sequence according to the two-dimensional geomagnetic tensor; The two-dimensional time feature is subjected to dimensionality reduction processing to obtain a one-dimensional time feature corresponding to the two-dimensional time feature, and the one-dimensional time feature is weighted and summed according to the frequency intensity corresponding to the target frequency component to obtain a weighted one-dimensional time feature as the motion time feature corresponding to the target object.

6. The method according to claim 1, characterized in that Determining predicted position information corresponding to the target object at a next time point according to the motion time feature and the motion space feature, and performing trajectory navigation on the target object based on the predicted position information, specifically includes: The motion time feature and the motion space feature are combined and fused to obtain a spatiotemporal feature vector corresponding to the target object; The spatiotemporal feature vector is input into a pre-trained position prediction model so that the position prediction model predicts the position of the target object according to the spatiotemporal feature vector, obtains the coordinate position information corresponding to the target object at the next time point as the predicted position information, and performs trajectory navigation on the target object based on the predicted position information.

7. The method according to claim 6, characterized in that Training the location prediction model specifically includes: Obtaining expected trajectory information and sample spatiotemporal feature vectors corresponding to the target object; Inputting the expected trajectory information and the sample spatiotemporal feature vector into a position prediction model to be trained, so that the position prediction model to be trained predicts the position of the target object according to the sample spatiotemporal feature vector to obtain sample predicted position information; According to the sample predicted position information and the expected trajectory position information corresponding to the sample spatiotemporal feature vector, a loss value for the position prediction model to be trained is determined, and according to the loss value, the position prediction model to be trained is trained, wherein the size of the loss value is negatively correlated with the degree of similarity between the sample predicted position information and the expected trajectory position information.

8. An aviation trajectory navigation device based on geomagnetic signals, characterized in that: include: An acquisition module, used to acquire a historical trajectory geomagnetic sequence of a target object, wherein the historical trajectory geomagnetic sequence is used to represent a sequence of geomagnetic vectors collected on a historical motion trajectory of the target object at time points divided according to preset time intervals within a preset historical duration; A generation module, for generating a geomagnetic trajectory heat map corresponding to the historical motion trajectory of the target object and determining a two-dimensional geomagnetic tensor corresponding to the historical trajectory geomagnetic sequence according to the determined geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence, wherein the geomagnetic trajectory heat map is used to characterize the geomagnetic signal change process displayed in the form of an RGB color image of the geomagnetic vector values ​​corresponding to each time point in the historical trajectory geomagnetic sequence; A feature determination module, for determining the motion time feature corresponding to the target object according to the historical trajectory geomagnetic sequence and the two-dimensional geomagnetic tensor, and inputting the geomagnetic trajectory heat map into a pre-trained spatial feature extraction model, so that the spatial feature extraction model determines the motion spatial feature corresponding to the target object according to the geomagnetic trajectory heat map; A prediction module is used to determine the predicted position information corresponding to the target object at the next time point according to the motion time characteristics and the motion space characteristics, and perform trajectory navigation on the target object based on the predicted position information.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images