Access method, apparatus, device, medium and product of non-terrestrial network

Abstract

This application provides a method, apparatus, device, medium, and product for accessing non-terrestrial networks, relating to the field of wireless communication technology. The method acquires target environment data, target location data, and preset satellite orbit parameters. Based on the target environment data, it determines the target environment label, predicts the target received power at each sampling time point within a preset prediction window, and uses a preset access prediction model to output the target predicted access probability at each sampling time point within the preset prediction window based on the predicted target received power and target environment label. The method then adjusts the radio frequency transceiver unit accordingly based on the predicted access probability at each time point. This allows for real-time prediction of the feasibility probability of non-terrestrial network access by considering the actual environmental obstruction status of the user terminal, its geographical location, and the dynamic changes in satellite orbit, thereby improving the success rate of non-terrestrial network access.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a method, apparatus, device, medium and product for accessing a non-terrestrial network. Background Technology

[0002] Non-terrestrial networks rely on satellite communication to achieve full-area signal coverage, effectively making up for the coverage blind spots of terrestrial cellular networks in remote areas, oceans, and high-altitude scenarios. They have the advantages of wide coverage, strong anti-interference ability, and high communication reliability, and are widely used in emergency communication, field operations, aviation and maritime, and network coverage in remote areas. They are an important component of the next generation of mobile communication networks.

[0003] Currently, the conventional access methods for non-terrestrial network terminals mostly adopt fixed passive access mechanisms. The terminals perform satellite signal scanning and network access attempts according to preset fixed radio frequency wake-up cycles, fixed satellite signal scanning frequencies, and fixed random access parameters, which results in high power consumption and shortens the terminal's battery life. Summary of the Invention

[0004] This application provides a method, apparatus, device, medium, and product for accessing non-terrestrial networks to solve the problems in the prior art.

[0005] In a first aspect, this application provides a method for accessing a non-terrestrial network, comprising:

[0006] Acquire target environmental data, target location data, and preset satellite orbit parameters;

[0007] The target environment label is determined based on the target environment data;

[0008] Based on the target environment label, the target location data, and the preset satellite orbit parameters, the predicted target received power corresponding to each sampling time point within the preset prediction window is determined;

[0009] A preset access prediction model is adopted, and the target predicted access probability corresponding to each sampling time point in the preset prediction window is determined based on the predicted target received power and the target environment label.

[0010] The radio frequency transceiver unit is adjusted accordingly based on the target predicted access probability corresponding to each sampling time point within the preset prediction window.

[0011] In one possible design, determining the target environment label based on the target environment data includes:

[0012] Obtain the current light intensity, current motion acceleration, and current positioning accuracy parameters;

[0013] In response to the current light intensity being greater than or equal to a first preset light threshold and the current positioning accuracy characterization parameter being less than or equal to a first preset accuracy threshold, the target environment label is determined to be a first environment label;

[0014] In response to the current light intensity being less than a first preset light threshold and greater than or equal to a second preset light threshold, and the current motion acceleration being greater than a preset acceleration threshold and the current positioning accuracy characterization parameter being greater than a first preset accuracy threshold and less than or equal to a second preset accuracy threshold, the target environment label is determined to be a second environment label; the first preset light threshold is greater than the second preset light threshold; the first preset accuracy threshold is less than the second preset accuracy threshold;

[0015] In response to the current light intensity being less than a second preset light threshold, the target environment label is determined to be a third environment label.

[0016] In one possible design, determining the predicted target received power corresponding to each sampling time point within a preset prediction window based on the target environment label, the target location data, and the preset satellite orbit parameters includes:

[0017] Obtain the preset satellite transmission power and preset satellite transmission frequency;

[0018] Based on the preset satellite orbit parameters, the satellite position data corresponding to each sampling time point within the preset prediction window is determined;

[0019] The free space path loss corresponding to each sampling time point within the preset prediction window is determined based on the satellite position data, the target position data, and the preset satellite transmission frequency.

[0020] The target environment penetration loss is determined based on the target environment label;

[0021] The predicted target receiving power is determined based on the preset satellite transmission power, target environment penetration loss, and free space path loss corresponding to each sampling time point within the preset prediction window.

[0022] In one possible design, the step of employing a preset access prediction model and determining the target predicted access probability corresponding to each sampling time point within the preset prediction window based on the predicted target received power and the target environment label within each sampling time point within the preset prediction window includes:

[0023] A preset satellite orbit calculation model is used, and the rate of change of satellite elevation angle corresponding to each sampling time point within the preset prediction window is determined based on the target position data;

[0024] Obtain the environmental label sequence within a preset historical time period;

[0025] Retrieve access results within a preset historical time period;

[0026] The satellite elevation angle change rate corresponding to each sampling time point within the preset prediction window, the environmental label sequence within the historical preset time period, the access results within the historical preset time period, and the predicted target received power corresponding to each sampling time point within the preset prediction window are input into the preset access prediction model, and the predicted access probability of the target corresponding to each sampling time point within the preset prediction window is output; the preset access prediction model is pre-trained to convergence.

[0027] In one possible design, the corresponding adjustment of the radio frequency transceiver unit based on the target predicted access probability corresponding to each sampling time point within a preset prediction window includes:

[0028] The target predicted access probability corresponding to each sampling time point within the preset prediction window is compared sequentially with the preset access threshold.

[0029] If the target predicted access probability corresponding to each sampling time point within the preset prediction window is less than or equal to the preset access threshold, then the radio frequency transceiver unit is adjusted to a sleep state.

[0030] If there is at least one future predicted time corresponding to a target predicted access probability greater than the preset access threshold, then a target predicted time that meets the preset conditions is selected, and the radio frequency transceiver unit is adjusted to the running state at the target predicted time.

[0031] The target access parameters are determined based on the predicted target received power corresponding to the predicted target time; the target access parameters include the physical random access channel transmit power and the physical random access channel preamble repetition count;

[0032] The radio frequency transceiver unit is used to access non-terrestrial networks based on the target access parameters.

[0033] In one possible design, the method further includes:

[0034] Obtain updated access data for non-terrestrial network access;

[0035] The preset access prediction model is fine-tuned based on the updated non-terrestrial network access data to update the preset access prediction model.

[0036] Secondly, this application provides an access device for a non-terrestrial network, comprising:

[0037] The acquisition module is used to acquire target environment data, target location data, and preset satellite orbit parameters;

[0038] The determination module is used to determine the target environment label based on the target environment data;

[0039] The determination module is also used to determine the predicted target received power corresponding to each sampling time point within the preset prediction window based on the target environment label, the target location data and the preset satellite orbit parameters;

[0040] The determination module is also used to determine the target predicted access probability corresponding to each sampling time point in the preset prediction window by adopting a preset access prediction model and based on the predicted target received power corresponding to each sampling time point in the preset prediction window and the target environment label.

[0041] The control module is used to control the radio frequency transceiver unit according to the target predicted access probability corresponding to each sampling time point within a preset prediction window.

[0042] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0043] The memory stores computer-executed instructions;

[0044] The processor executes computer execution instructions stored in the memory to implement the method as described in any of the first aspects.

[0045] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any of the first aspects.

[0046] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the first aspects.

[0047] This application provides a method, apparatus, device, medium, and product for accessing non-terrestrial networks. The method acquires target environment data, target location data, and preset satellite orbit parameters. First, it determines the target environment label based on the target environment data. Then, based on the target environment label, target location data, and preset satellite orbit parameters, it predicts the target received power at each sampling time point within a preset prediction window. Finally, using a preset access prediction model, it outputs the target predicted access probability at each sampling time point within the preset prediction window based on the predicted target received power and target environment label. The method then adjusts the radio frequency transceiver unit accordingly based on the predicted access probability at each time point. This allows for real-time prediction of the feasibility of non-terrestrial network access at different time points, taking into account the terminal's actual environmental obstruction status, geographical location, and dynamic changes in satellite orbit. This effectively solves the technical drawbacks of traditional non-terrestrial network access methods that rely on fixed wake-up cycles, fixed scanning frequencies, and fixed access parameters, making them unable to adapt to environmental and satellite dynamic changes. This method improves the success rate of non-terrestrial network access while ensuring low-power standby operation of the terminal. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] Figure 1 An application scenario diagram corresponding to a non-terrestrial network access method provided in an embodiment of this application;

[0050] Figure 2 A flowchart illustrating a non-terrestrial network access method provided in an embodiment of this application;

[0051] Figure 3 A flowchart illustrating a non-terrestrial network access method provided in another embodiment of this application;

[0052] Figure 4 A schematic diagram of the structure of a non-terrestrial network access device provided in an embodiment of this application;

[0053] Figure 5 This is a structural example diagram of an electronic device provided in an embodiment of this application.

[0054] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application.

[0056] To clearly understand the technical solution of this application, the solutions of the prior art will be described in detail first.

[0057] Non-terrestrial networks (NTNs) refer to communication networks built using non-terrestrial infrastructure such as satellites. They serve as an extension and supplement to terrestrial cellular networks, achieving integrated air-space-ground coverage. The deep integration of NTNs with 5G / 6G aims to solve communication problems in areas where terrestrial networks are difficult to cover or are economically infeasible. Currently, conventional access methods for NTN terminals mostly employ fixed passive access mechanisms. Terminals perform satellite signal scanning and network access attempts according to preset fixed radio frequency wake-up cycles, fixed satellite signal scanning frequencies, and fixed random access parameters, resulting in high power consumption and shortened battery life.

[0058] To address the aforementioned issues, this disclosure provides a method for accessing non-terrestrial networks. By acquiring target environment data, target location data, and preset satellite orbit parameters, a target environment label is first determined based on the target environment data. Then, based on the target environment label, target location data, and preset satellite orbit parameters, the predicted target received power at each sampling time point within a preset prediction window is predicted. A preset access prediction model is then used to output the predicted target received power and target environment label at each sampling time point within the preset prediction window. The radio frequency transceiver unit is adjusted accordingly based on the predicted access probability at each time point. This allows for real-time prediction of the feasibility of non-terrestrial network access at different time points, taking into account the terminal's actual environmental obstruction status, geographical location, and dynamic changes in satellite orbit. This effectively solves the technical drawbacks of traditional non-terrestrial network access methods that rely on fixed wake-up cycles, fixed scanning frequencies, and fixed access parameters, making them unable to adapt to dynamic environmental and satellite changes. This method improves the success rate of non-terrestrial network access while maintaining low-power standby operation of the terminal.

[0059] Figure 1 An application scenario diagram corresponding to a non-terrestrial network access method provided in an embodiment of this application is shown, such as... Figure 1As shown, the application scenario provided in this embodiment includes: a user terminal 10, a target sensor 11, a processor 12, and a radio frequency transceiver unit 13. The user terminal includes the target sensor 11, the processor 12, and the radio frequency transceiver unit 13. The non-terrestrial network access method is applied to the user terminal 10. The target sensor 11 is used to collect target environmental data and target location data. Target environmental data refers to the external environment data of the user terminal 10. Target location data is the location information of the user terminal 10. The target sensor 11 can be an ambient light sensor, a navigation satellite system, etc. The processor 12 obtains the target environmental data and target location data from the target sensor 11, and obtains preset satellite orbit parameters. The processor 12 determines the target environmental label based on the target environmental data, and determines the predicted target received power corresponding to each sampling time point within the preset prediction window based on the target environmental label, target location data, and preset satellite orbit parameters. A preset access prediction model is adopted, and the target predicted access probability corresponding to each sampling time point in the preset prediction window is determined based on the predicted target received power and target environment label corresponding to each sampling time point in the preset prediction window. The radio frequency transceiver unit 13 is adjusted accordingly based on the target predicted access probability corresponding to each sampling time point in the preset prediction window.

[0060] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0061] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0062] Figure 2 This application provides a flowchart illustrating a method for accessing a non-terrestrial network according to an embodiment of the present application. Figure 2As shown, the execution subject of this embodiment is a non-terrestrial network access device. This device can be implemented through a computer program, or through a medium storing the relevant computer program, such as a USB flash drive and / or optical disc; alternatively, it can be implemented through a physical device integrating or installing the relevant computer program, such as a chip or electronic device. The electronic device may be a computer or a server, etc. The non-terrestrial network access method provided in this embodiment includes the following steps:

[0063] S201. Acquire target environment data, target location data, and preset satellite orbit parameters.

[0064] Among them, the target environment data refers to the data of the environment in which the user terminal is located.

[0065] Optionally, the target environment data may include light intensity and acceleration data, etc.

[0066] The target location data refers to the current location data of the user terminal.

[0067] Optionally, the target location data may include the three-dimensional coordinates of the user terminal's current location, including longitude, latitude, and altitude.

[0068] Among them, the preset satellite orbit parameters refer to the satellite broadcast ephemeris parameters, which are a set of standardized data describing the satellite's trajectory and time synchronization relationship in space.

[0069] Optionally, the preset satellite orbit parameters are satellite orbit parameters stored locally on the user terminal, including but not limited to the basic satellite orbit parameters pre-stored at the terminal's factory, the full constellation satellite orbit parameters downloaded via the terrestrial cellular network, and the real-time updated satellite orbit parameters received via satellite broadcast channels. The user terminal performs satellite selection based on the preset satellite orbit parameters, and only performs subsequent orbit calculations, signal predictions, and access probability assessments on satellites that meet the following conditions: satellites with preset satellite orbit parameters can be satellites with an elevation angle greater than or equal to a preset degree and belonging to the satellite constellation of the operator to which the user terminal belongs.

[0070] Optionally, the preset degree can be 10 degrees.

[0071] Understandably, user terminals can automatically update the preset satellite orbit parameters stored locally at preset intervals to ensure the accuracy of orbit calculations.

[0072] Optionally, the preset cycle can be 2 hours, or it can be set manually.

[0073] It is understandable that a user terminal, also known as a terminal device, refers to an electronic device that can directly interact with a communication network, support non-terrestrial network connections, and provide communication services to users. It has the capabilities of data acquisition, computing and processing, signal transmission and reception, and human-computer interaction.

[0074] It is understandable that user terminals can have built-in optical sensors, inertial measurement units, and navigation satellite systems.

[0075] Among them, the navigation satellite system can be a Global Navigation Satellite System (GNSS) receiver.

[0076] Among them, the target sensor refers to the sensor used to acquire target environmental data.

[0077] Optionally, the target sensor may include, but is not limited to, an optical sensor, an inertial measurement unit, etc.

[0078] Specifically, in this embodiment, the processor acquires target environmental data from the target sensor, target location data from the GNSS receiver, and preset satellite orbit parameters from the preset database.

[0079] S202. Determine the target environment label based on the target environment data.

[0080] The target environment data includes parameters representing light intensity, current motion acceleration, and current positioning accuracy.

[0081] Furthermore, in another possible implementation, the specific implementation steps of S202 include:

[0082] Obtain the current light intensity, current motion acceleration, and current positioning accuracy parameters;

[0083] In response to the current light intensity being greater than or equal to a first preset light threshold and the current positioning accuracy characterization parameter being less than or equal to a first preset accuracy threshold, the target environment label is determined as the first environment label;

[0084] In response to the current light intensity being less than a first preset light threshold and greater than or equal to a second preset light threshold, and the current motion acceleration being greater than a preset acceleration threshold, and the current positioning accuracy characterization parameter being greater than a first preset accuracy threshold and less than or equal to a second preset accuracy threshold, the target environment label is determined to be the second environment label;

[0085] In response to the current light intensity being less than the second preset light threshold, the target environment label is determined to be the third environment label.

[0086] The light intensity is the average light value output by the light sensor over a preset time period, measured in lux.

[0087] The current acceleration refers to the linear acceleration output by the inertial measurement unit after removing the gravitational component, and the unit is multiples of gravitational acceleration. The current positioning accuracy is characterized by the current horizontal dilution of precision (HDOP) value output by the global navigation satellite system receiver.

[0088] Understandably, the smaller the HDOP value, the higher the horizontal positioning accuracy.

[0089] Optionally, the first preset illumination threshold is greater than the second preset illumination threshold. The first preset illumination threshold and the second preset illumination threshold are preset.

[0090] Optionally, the first preset accuracy threshold is less than the second preset accuracy threshold, and the first preset accuracy threshold and the second preset accuracy threshold are preset.

[0091] For example, the first preset illumination threshold can be 10,000 lux, and the second preset illumination threshold can be 500 lux. The first preset accuracy threshold can be 2.5. The second preset accuracy threshold can be 5. The preset acceleration threshold can be 0.2g.

[0092] For example, in this embodiment, in response to the current light intensity being greater than or equal to 10,000 lux and the current positioning accuracy characterization parameter being less than or equal to 2.5, the target environment label is determined to be the first environment label. The first environment label can be understood as the current environment being an open outdoor scene with sufficient light, good satellite geometric distribution, and high positioning accuracy.

[0093] For example, in this embodiment, in response to the current light intensity being less than 10,000 lux and greater than or equal to 500 lux, the current motion acceleration being greater than 0.2g, and the current positioning accuracy characterization parameter being greater than 2.5 and less than 5, the target environment label is determined to be the second environment label. The second environment label can be understood as the current environment being a vehicle near the window scene, with moderate lighting inside the vehicle due to glass obstruction, continuous vibration during driving, and partial obstruction of satellite signals leading to decreased positioning accuracy.

[0094] For example, in this embodiment, in response to the current light intensity being less than 500 lux, the target environment label is determined to be a third environment label. The third environment label can be understood as the current environment being an indoor scene, either windowless or with extremely low light.

[0095] If any of the above conditions are not met, the target environment label will be determined as the fourth environment label. The fourth environment label can be understood as the current scene being unknown.

[0096] Specifically, by combining three types of data—current light intensity, motion acceleration, and positioning accuracy—and employing a hierarchical threshold judgment logic, the corresponding target environment label can be determined based on different target environment data, accurately identifying the different occlusion environment states of the terminal.

[0097] S203. Based on the target environment label, target location data and preset satellite orbit parameters, determine the predicted target received power corresponding to each sampling time point within the preset prediction window.

[0098] Furthermore, in another possible implementation, the specific implementation steps of S203 include:

[0099] Obtain the preset satellite transmission power and preset satellite transmission frequency;

[0100] Based on preset satellite orbit parameters, determine the satellite position data corresponding to each sampling time point within the preset prediction window;

[0101] The free space path loss corresponding to each sampling time point within the preset prediction window is determined based on the satellite position data, target position data, and preset satellite transmission frequency.

[0102] The penetration loss of the target environment is determined based on the target environment label;

[0103] The predicted target received power is determined based on the preset satellite transmit power, target environment penetration loss, and free space path loss at each sampling time point within the preset prediction window.

[0104] Among them, the preset satellite transmit power refers to the satellite downlink reference signal transmit power, which is the rated transmit power when the satellite transmits downlink reference signals to the ground terminal, and is a fixed parameter of the satellite system.

[0105] Among them, the preset satellite transmission frequency refers to the satellite downlink carrier center frequency, which is the carrier center frequency of the satellite downlink communication signal and is a fixed parameter of the satellite system.

[0106] Among them, satellite position data refers to the satellite's three-dimensional geocentric coordinates, which are the satellite's three-dimensional position coordinates in the Earth's central inertial coordinate system.

[0107] Free space path loss refers to the inherent energy loss caused by energy diffusion when radio waves propagate in unobstructed free space.

[0108] Among them, the target environment penetration loss refers to the preset loss corresponding to the current target environment label.

[0109] The predicted target received power is the average power of the downlink reference signal from a certain satellite that the terminal is expected to receive at a certain future time.

[0110] Specifically, in this embodiment, the processor uses the Simplified General Perturbations 4 Model (SGP4) and determines the three-dimensional coordinates of the target satellite at each sampling time point within a preset prediction window based on preset satellite orbit parameters. It acquires the target location data from the user terminal and converts the latitude, longitude, and altitude in the target location data into three-dimensional coordinates in the geocentric coordinate system corresponding to the user terminal. Using a preset calculation formula, it calculates the elevation angle and slant range between the target satellite and the user terminal at each sampling time point within the preset prediction window based on the three-dimensional coordinates in the geocentric coordinate system corresponding to the user terminal. Using the formula corresponding to free space path loss and based on the preset satellite transmission frequency and the slant range data between the target satellite and the user terminal, it calculates the free space path loss corresponding to the target satellite. Finally, it acquires the target environment label and determines the corresponding target environment penetration loss based on the target environment label. Furthermore, the difference between the preset satellite transmit power and the target environment penetration loss, and the difference between the preset satellite transmit power and the free space path loss corresponding to each sampling time point within the preset prediction window of the target satellite, are calculated to determine the predicted target receive power corresponding to each sampling time point within the preset prediction window.

[0111] The preset formulas include the Euclidean distance formula and the spherical trigonometric formula.

[0112] The Euclidean distance formula is used to calculate the slope distance. The spherical trigonometry formula is used to calculate the angle of elevation.

[0113] The formula for free space path loss is shown below:

[0114]

[0115] Where L refers to free space path loss, f refers to the preset satellite transmission frequency, and d refers to the slant range data between the target satellite and the user terminal.

[0116] The target satellite refers to the satellite whose target access probability is to be calculated, and the preset satellite orbit parameters include the orbit parameters corresponding to the target satellite.

[0117] The number of target satellites is at least one.

[0118] For example, the target environment penetration loss corresponding to the first environment label is 0dB, the target environment penetration loss corresponding to the second environment label is 8dB, the target environment penetration loss corresponding to the third environment label is 30dB, and the target environment penetration loss corresponding to the fourth environment label is 15dB.

[0119] The preset prediction window is a pre-defined future time interval, such as 60 seconds, from which access probability prediction needs to be performed. The sampling time point refers to a discrete time node within the preset prediction window, divided according to fixed time intervals.

[0120] For example, the preset prediction window can be 60 seconds, and each sampling time point within the preset prediction window can be divided into 12 sampling points with a step size of 5 seconds. The predicted target received power of the target satellite at each sampling time point within the preset prediction window can be understood as the predicted target received power corresponding to each sampling point within the next 60 seconds, with a step size of 5 seconds.

[0121] S204. Using a preset access prediction model, and based on the predicted target received power and target environment label corresponding to each sampling time point within the preset prediction window, determine the target predicted access probability corresponding to each sampling time point within the preset prediction window.

[0122] Furthermore, in another possible implementation, the specific implementation steps of S204 include:

[0123] A preset satellite orbit calculation model is used, and the rate of change of satellite elevation angle corresponding to each sampling time point within the preset prediction window is determined based on the target position data;

[0124] Obtain the environmental label sequence within a preset historical time period;

[0125] Retrieve access results within a preset historical time period;

[0126] The satellite elevation angle change rate at each sampling time point within the preset prediction window, the environmental label sequence within the historical preset time period, the access results within the historical preset time period, and the predicted target received power at each sampling time point within the preset prediction window are input into the preset access prediction model, and the target predicted access probability at each sampling time point within the preset prediction window is output; the preset access prediction model is pre-trained to convergence.

[0127] The preset satellite orbit calculation model is the simplified general perturbation 4 model.

[0128] The target location data includes the longitude, latitude, and altitude of the user terminal's current location.

[0129] Among them, the satellite elevation angle change rate refers to the amount of change in the satellite elevation angle per unit time, and the unit is degrees / second.

[0130] Among them, the historical preset time period refers to the past time interval that is pre-set and used to extract historical features, such as the past 60 seconds.

[0131] Optionally, the preset historical time period can be 60 seconds.

[0132] Among them, the environmental label sequence refers to an ordered sequence of multiple environmental labels obtained at fixed sampling intervals within a preset historical time period. For example, a sequence of 12 environmental labels, one every 5 seconds for the past 60 seconds, is used to characterize the dynamic change process of the environment.

[0133] The access result within the historical preset time period refers to the final result of each non-terrestrial network access attempt initiated by the terminal within the historical preset time period, with the value being either "access successful" or "access failed".

[0134] The target predicted access probability refers to the probability, output by the preset access prediction model, that a user terminal will successfully initiate non-terrestrial network access at a future sampling time point.

[0135] The target predicted access probability ranges from 0 to 1, with a higher value indicating a higher probability of successful access.

[0136] Specifically, in this embodiment, the processor uses the Simplified General Perturbations 4 Model (SGP4) and determines the three-dimensional coordinates of the target satellite at each sampling time point within a preset prediction window based on preset satellite orbit parameters. It acquires the target location data from the user terminal and converts the latitude, longitude, and altitude in the target location data into three-dimensional coordinates in the geocentric coordinate system corresponding to the user terminal. A preset calculation formula is used to calculate the elevation angle corresponding to each sampling time point within the preset prediction window, based on the three-dimensional coordinates in the geocentric coordinate system corresponding to the user terminal and the satellite's three-dimensional coordinates at each sampling time point. The elevation angles of two adjacent sampling time points are then differentially calculated to obtain the rate of change of the satellite elevation angle at each sampling time point.

[0137] Furthermore, the environmental tag sequence within a historical preset time period is obtained, and the access results within the historical preset time period are obtained. The satellite elevation angle change rate corresponding to each sampling time point within the preset prediction window, the environmental tag sequence within the historical preset time period, the access results within the historical preset time period, and the predicted target received power corresponding to each sampling time point within the preset prediction window are input into the preset access prediction model, and the target predicted access probability corresponding to each sampling time point within the preset prediction window is output.

[0138] Specifically, the training steps for the preset access prediction model are as follows:

[0139] Training samples are obtained, each containing four sets of feature data and one set of label data. These include: satellite elevation angle change rate samples for each training sampling moment within the training prediction time interval; historical environmental state sequence samples for the historical reference time interval; historical access attempt result samples for the historical reference time interval; link received power prediction values ​​for each training sampling moment within the training prediction time interval; and actual access success probability labels for each training sampling moment within the training prediction time interval. The length of each sequence is consistent with the number of training sampling moments in the corresponding time interval. For each training sampling moment, labeling is performed according to the following rules: If the terminal actually initiates a non-terrestrial network access attempt at that training sampling moment, it is directly labeled based on the access result, with successful access labeled as 1 and failed access labeled as 0. If the user terminal does not initiate an access attempt at that training sampling moment, it is labeled based on the reference signal received power actually measured at that moment and the standard access power threshold, with actual reference signal received power greater than or equal to the standard access power threshold labeled as 1 and less than the standard access power threshold labeled as 0.

[0140] Optionally, the standard access power threshold can be set to -125 dBm (dBm), which can be customized.

[0141] Further, training hyperparameters are set, with the Adam optimizer used and the binary cross-entropy loss function employed. After parameter settings, training data is input into the model in batches for forward inference to obtain the predicted probabilities of the model output. The loss value between the model output and the true label is calculated based on the loss function, and the gradient of the loss value with respect to each model parameter is calculated using the backpropagation algorithm. The Adam optimizer is then used to update the model parameters based on the gradient. After each batch of training, validation is performed on the validation set, calculating the validation set loss and validation set accuracy. This batch training and validation process is repeated until the preset convergence condition is met. Model training is stopped and the current model parameters are saved when any of the following conditions are met: the validation set loss no longer decreases for 5 consecutive rounds, or the training set accuracy reaches 95% or higher and the validation set accuracy reaches 90% or higher, or the number of training rounds reaches the preset maximum of 100 rounds. After training, the model performance is finally evaluated using the test set. If the test set accuracy reaches 85% or higher, the model is considered to have converged; otherwise, the training dataset is expanded and retraining is performed.

[0142] For example, the training hyperparameters can be a batch size of 32, an initial learning rate of 0.001, and a learning rate decay strategy where the learning rate is decayed to 0.9 times the original value every 10 batches trained.

[0143] S205. The radio frequency transceiver unit is adjusted accordingly based on the target predicted access probability corresponding to each sampling time point within the preset prediction window.

[0144] Furthermore, in another possible implementation, the specific implementation steps of S205 include:

[0145] The target predicted access probability corresponding to each sampling time point within the preset prediction window is compared with the preset access threshold in turn.

[0146] If the target predicted access probability corresponding to each sampling time point within the preset prediction window is less than or equal to the preset access threshold, then the radio frequency transceiver unit will be adjusted to a sleep state.

[0147] If there is at least one future predicted time corresponding to a target predicted access probability greater than a preset access threshold, then select a target predicted time that meets the preset conditions, and adjust the radio frequency transceiver unit to the running state at the target predicted time.

[0148] The target access parameters are determined based on the predicted target received power at the target prediction time.

[0149] It employs radio frequency transceiver units and performs non-terrestrial network access based on target access parameters.

[0150] Optionally, the preset access threshold is pre-set, and this embodiment does not limit it.

[0151] For example, the preset access threshold can be 80%.

[0152] The target access parameters include the physical random access channel transmit power and the physical random access channel preamble repetition count. The physical random access channel transmit power is the output power set by the terminal when transmitting the physical random access channel preamble sequence. The physical random access channel preamble repetition count is the number of times the terminal continuously transmits the same preamble sequence.

[0153] The target access parameters may also include a preamble format.

[0154] The preamble format is an access preamble signal system with different durations, subcarrier spacings, and sequence lengths, as specified in the 3rd Generation Partnership Project (3GPP) protocol.

[0155] Specifically, in this embodiment, each sampling time point within the preset prediction window corresponds to a target predicted access probability. Therefore, the target predicted access probability corresponding to each sampling time point within the preset prediction window is compared with a preset access threshold. If the target predicted access probability corresponding to each sampling time point within the preset prediction window is less than or equal to the preset access threshold, the RF transceiver unit is adjusted to a sleep state. If there is at least one future prediction time corresponding to a target predicted access probability greater than the preset access threshold, a target prediction time that meets the preset conditions is selected, and the RF transceiver unit is adjusted to an operating state at the target prediction time. Then, the predicted target received power corresponding to the target prediction time is obtained, and the corresponding physical random access channel transmit power and physical random access channel preamble repetition count are determined according to a preset mapping table. Then, the RF transceiver unit is used to access the non-terrestrial network according to the target access parameters.

[0156] The preset condition can be the maximum value of the predicted target received power in the future prediction time within the preset prediction window when the target predicted access probability is greater than the preset access threshold, or it can be the first future prediction time within the preset prediction window when the target predicted access probability is greater than the preset access threshold.

[0157] The preset mapping table includes the mapping relationship between the range of the predicted target received power and the transmit power of the physical random access channel and the number of preamble repetitions of the physical random access channel.

[0158] For example, if the predicted target received power is greater than -110dBm, the physical random access channel transmit power is 23dBm, and the physical random access channel preamble repetition count is 1. If the predicted target received power is less than or equal to -110dBm and greater than -130dBm, the physical random access channel transmit power is 26dBm, and the physical random access channel preamble repetition count is 2.

[0159] Understandably, when the predicted target received power is high, a lower transmit power and fewer preamble repetitions are used to reduce user terminal power consumption. Conversely, when the predicted target received power is low, a higher transmit power and more preamble repetitions are used to ensure the satellite can correctly detect the preamble signal and improve access success rate.

[0160] Optionally, when the predicted access probabilities of two or more satellites at the same or different sampling time points are both greater than a preset access threshold, the user terminal selects a unique target access satellite and target access time according to the following settings to avoid resource conflicts and power consumption waste caused by multiple satellites accessing simultaneously. The user terminal sorts all satellite-time combinations that meet the access conditions from highest to lowest predicted access probability, prioritizing the combination with the highest predicted access probability. A higher predicted access probability indicates a greater likelihood of successful access, effectively reducing the additional power consumption and latency caused by retries after access failure.

[0161] Specifically, by comparing the target predicted access probability at each sampling time point within the preset prediction window with the preset access threshold, the system wakes up only at the target prediction time that meets the conditions and performs access using dynamically adapted target access parameters. This avoids the problem of a large amount of invalid radio frequency power consumption caused by traditional fixed-cycle wake-up and access. At the same time, by dynamically matching the access parameters with the predicted target received power, the system significantly reduces the standby power consumption of user terminals and extends battery life, while improving the success rate and timeliness of non-terrestrial network access.

[0162] This application provides a non-terrestrial network access method. By acquiring target environment data, target location data, and preset satellite orbit parameters, the method first determines the target environment label based on the target environment data. Based on the target environment label, target location data, and preset satellite orbit parameters, it predicts the target received power corresponding to each sampling time point within a preset prediction window. Then, using a preset access prediction model, it outputs the target predicted access probability corresponding to each sampling time point within the preset prediction window based on the predicted target received power and target environment label. Based on the predicted access probability at each time point, it adjusts the radio frequency transceiver unit accordingly. This allows for real-time prediction of the feasibility probability of non-terrestrial network access at different time points by combining the actual environmental obstruction status, geographical location, and dynamic changes in satellite orbit of the terminal. This effectively solves the technical drawbacks of traditional non-terrestrial network access methods that rely on fixed wake-up cycles, fixed scanning frequencies, and fixed access parameters, which cannot adapt to environmental and satellite dynamic changes. This method improves the success rate of non-terrestrial network access while ensuring low-power standby operation of the terminal.

[0163] As an optional implementation, based on any of the above embodiments, the following steps are also included:

[0164] Obtain updated access data for non-terrestrial network access;

[0165] The preset access prediction model is fine-tuned based on updated access data from non-terrestrial network access in order to update the preset access prediction model.

[0166] Among them, the updated access data for non-terrestrial network access refers to the access data recorded by the processor after each access.

[0167] The updated access data for non-terrestrial network access includes the predicted target received power at each sampling time point within the preset prediction window, the satellite elevation angle change rate at each sampling time point within the preset prediction window, the environmental label sequence within the historical preset time period corresponding to the current access time, and the access results within the historical preset time period and the actual access results for the current access.

[0168] Specifically, the processor automatically saves the access data for each non-terrestrial network access after each access. If the number of stored and updated non-terrestrial network access data exceeds a preset number, fine-tuning is triggered, and the model is fine-tuned using mini-batch gradient descent, updating only the weight parameters of the last hidden layer and the output layer.

[0169] Optionally, the preset quantity is pre-set.

[0170] For example, the preset quantity can be 100.

[0171] The preset access prediction model can be a multilayer perceptron model.

[0172] Among them, the multilayer perceptron model is a feedforward artificial neural network composed of multiple fully connected neuron layers, including at least one input layer, one hidden layer and one output layer.

[0173] Specifically, through an online fine-tuning mechanism, based on the actual access data collected locally by the user terminal, continuous optimization is performed to gradually improve the access prediction accuracy in different scenarios, reduce invalid radio frequency wake-ups and access attempts, and significantly reduce the power consumption of user terminal satellite communication.

[0174] Figure 3 A flowchart illustrating a non-terrestrial network access method provided in another embodiment of this application is shown below. Figure 3 As shown. The non-terrestrial network access method provided in this embodiment is applied to the processor of a user terminal. The non-terrestrial network access method provided in this embodiment specifically includes the following steps:

[0175] S301. Acquire target environment data, target location data, and preset satellite orbit parameters.

[0176] S302. Determine the target environment label based on the target environment data.

[0177] S303. Based on the target environment label, target location data and preset satellite orbit parameters, determine the predicted target received power corresponding to each sampling time point within the preset prediction window.

[0178] S304. Using a preset access prediction model, and based on the predicted target received power and target environment label corresponding to each sampling time point within the preset prediction window, determine the target predicted access probability corresponding to each sampling time point within the preset prediction window.

[0179] S305. Determine whether the target predicted access probability corresponding to each sampling time point within the preset prediction window is less than or equal to the preset access threshold.

[0180] S306. In response to the fact that the target predicted access probability corresponding to each sampling time point within the preset prediction window is less than or equal to the preset access threshold, the radio frequency transceiver unit is adjusted to a sleep state.

[0181] S307. In response to the existence of at least one future prediction time corresponding to a target predicted access probability greater than a preset access threshold, select the first future prediction time within the preset prediction window whose target predicted access probability is greater than the preset access threshold as the target prediction time, and adjust the radio frequency transceiver unit to the running state at the target prediction time.

[0182] S308, determine the target access parameters based on the predicted target received power corresponding to the target prediction time.

[0183] S309 uses a radio frequency transceiver unit and performs non-terrestrial network access based on target access parameters.

[0184] Figure 4 This is a schematic diagram of the structure of a non-terrestrial network access device provided in an embodiment of this application, as shown below. Figure 4 As shown, the non-terrestrial network access device provided in this embodiment is located in an electronic device. The non-terrestrial network access device 40 provided in this embodiment includes: an acquisition module 41, a determination module 42, and a control module 43.

[0185] Specifically, the acquisition module 41 is used to acquire target environment data, target location data, and preset satellite orbit parameters. The determination module 42 is used to determine the target environment label based on the target environment data; the determination module 42 is also used to determine the predicted target received power corresponding to each sampling time point within the preset prediction window based on the target environment label, target location data, and preset satellite orbit parameters; the determination module 42 is also used to determine the target predicted access probability corresponding to each sampling time point within the preset prediction window by using a preset access prediction model and based on the predicted target received power and target environment label corresponding to each sampling time point within the preset prediction window; the control module 43 is used to control the radio frequency transceiver unit accordingly based on the target predicted access probability corresponding to each sampling time point within the preset prediction window.

[0186] Optionally, when determining the target environment label based on the target environment data, the determining module 42 is specifically used to: acquire the current light intensity, current motion acceleration, and current positioning accuracy characterization parameters; in response to the current light intensity being greater than or equal to a first preset light threshold and the current positioning accuracy characterization parameters being less than or equal to a first preset accuracy threshold, determine the target environment label as a first environment label; in response to the current light intensity being less than the first preset light threshold but greater than or equal to a second preset light threshold, and the current motion acceleration being greater than a preset acceleration threshold and the current positioning accuracy characterization parameters being greater than the first preset accuracy threshold but less than or equal to the second preset accuracy threshold, determine the target environment label as a second environment label; the first preset light threshold is greater than the second preset light threshold; the first preset accuracy threshold is less than the second preset accuracy threshold; and in response to the current light intensity being less than the second preset light threshold, determine the target environment label as a third environment label.

[0187] Optionally, when determining the predicted target received power corresponding to each sampling time point within the preset prediction window based on the target environment label, target location data, and preset satellite orbit parameters, the determining module 42 is specifically used for: acquiring the preset satellite transmit power and preset satellite transmit frequency; determining the satellite location data corresponding to each sampling time point within the preset prediction window based on the preset satellite orbit parameters; determining the free space path loss corresponding to each sampling time point within the preset prediction window based on the satellite location data, target location data, and preset satellite transmit frequency; determining the target environment penetration loss based on the target environment label; and determining the predicted target received power corresponding to each sampling time point within the preset prediction window based on the preset satellite transmit power, target environment penetration loss, and free space path loss corresponding to each sampling time point within the preset prediction window.

[0188] Optionally, the determining module 42, when using a preset access prediction model and determining the target predicted access probability for each sampling time point within the preset prediction window based on the predicted target received power and target environmental labels corresponding to each sampling time point within the preset prediction window, specifically performs the following: using a preset satellite orbit calculation model and based on target position data to determine the satellite elevation angle change rate corresponding to each sampling time point within the preset prediction window; obtaining the environmental label sequence within a historical preset time period; obtaining the access results within a historical preset time period; inputting the satellite elevation angle change rate, the environmental label sequence, the access results, and the predicted target received power for each sampling time point within the preset prediction window into the preset access prediction model, and outputting the target predicted access probability for each sampling time point within the preset prediction window; the preset access prediction model is pre-trained to convergence.

[0189] Optionally, when the control module 43 controls the radio frequency transceiver unit based on the target predicted access probability corresponding to each sampling time point within the preset prediction window, it specifically performs the following: comparing the target predicted access probability corresponding to each sampling time point within the preset prediction window with a preset access threshold in sequence; if the target predicted access probability corresponding to each sampling time point within the preset prediction window is less than or equal to the preset access threshold, then adjusting the radio frequency transceiver unit to a sleep state; if there is at least one target predicted access probability corresponding to a future prediction time that is greater than the preset access threshold, then selecting a target prediction time that meets the preset conditions, and adjusting the radio frequency transceiver unit to an operating state at the target prediction time; determining the target access parameters based on the predicted target received power corresponding to the target prediction time; the target access parameters include the physical random access channel transmit power and the physical random access channel preamble repetition count; and using the radio frequency transceiver unit and based on the target access parameters to access the non-terrestrial network.

[0190] Optionally, the access device for non-terrestrial networks may also include a fine-tuning module.

[0191] Accordingly, the acquisition module 41 is used to acquire updated access data for non-terrestrial network access. The fine-tuning module is used to fine-tune the preset access prediction model based on the updated access data for non-terrestrial network access, so as to update the preset access prediction model.

[0192] It should be noted that the non-terrestrial network access method provided in the above embodiments can be applied to terminal devices / base stations, or chips or chip modules in terminal devices / base stations.

[0193] This application also provides a chip, which includes at least one processor for executing program instructions to perform a non-terrestrial network access method as described in the above embodiments.

[0194] This application also provides a chip module including at least one processor for executing program instructions to perform a non-terrestrial network access method as described in the above embodiments.

[0195] Figure 5 Example diagram of the structure of an electronic device provided in an embodiment of this application, such as Figure 5 As shown, the electronic device 50 provided in this embodiment includes: a processor 51 and a memory 52 communicatively connected to the processor 51.

[0196] The memory 52 stores computer-executed instructions; the processor 51 executes the computer-executed instructions stored in the memory 52 to implement a non-terrestrial network access method provided in any of the above embodiments.

[0197] The program may include program code, which includes computer-executable instructions. Memory 52 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device.

[0198] In this embodiment, the memory 52 and the processor 51 are connected via a bus. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single straight line, but this does not mean that there is only one bus or one type of bus.

[0199] This application also provides a computer-readable storage medium, which stores computer-executable instructions. When executed by a processor, the computer-executable instructions are used to implement a non-terrestrial network access method provided in any of the above embodiments.

[0200] This application also provides a computer program product, including a computer program that, when executed by a processor, implements a non-terrestrial network access method provided in any of the above embodiments.

[0201] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to implement the solution of this embodiment according to actual needs.

[0202] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The unit composed of the above modules can be implemented in hardware or in the form of hardware plus software functional units.

[0203] The integrated modules described above, implemented as software functional modules, can be stored in a computer-readable storage medium. These software functional modules, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods of the various embodiments of this application.

[0204] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0205] The memory may include high-speed RAM, and may also include non-volatile storage (NVM), such as at least one disk storage device, and may also be a USB flash drive, external hard drive, read-only memory, disk or optical disc, etc.

[0206] The aforementioned storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0207] An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Alternatively, the storage medium can be an integral part of the processor. The processor and storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and storage medium can exist as discrete components in an electronic control unit or main control device.

[0208] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0209] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for accessing a non-terrestrial network, characterized in that, include: Acquire target environment data, target location data, and preset satellite orbit parameters; The target environment label is determined based on the target environment data; Based on the target environment label, the target location data, and the preset satellite orbit parameters, the predicted target received power corresponding to each sampling time point within the preset prediction window is determined; A preset access prediction model is adopted, and the target predicted access probability corresponding to each sampling time point in the preset prediction window is determined based on the predicted target received power and the target environment label. The radio frequency transceiver unit is adjusted accordingly based on the target predicted access probability corresponding to each sampling time point within the preset prediction window.

2. The method according to claim 1, characterized in that, The process of determining the target environment label based on the target environment data includes: Obtain the current light intensity, current motion acceleration, and current positioning accuracy parameters; In response to the current light intensity being greater than or equal to a first preset light threshold and the current positioning accuracy characterization parameter being less than or equal to a first preset accuracy threshold, the target environment label is determined to be a first environment label; In response to the current light intensity being less than a first preset light threshold and greater than or equal to a second preset light threshold, and the current motion acceleration being greater than a preset acceleration threshold and the current positioning accuracy characterization parameter being greater than a first preset accuracy threshold and less than or equal to a second preset accuracy threshold, the target environment label is determined to be a second environment label; the first preset light threshold is greater than the second preset light threshold; the first preset accuracy threshold is less than the second preset accuracy threshold; In response to the current light intensity being less than a second preset light threshold, the target environment label is determined to be a third environment label.

3. The method according to claim 1, characterized in that, The step of determining the predicted target received power corresponding to each sampling time point within the preset prediction window based on the target environment label, the target location data, and the preset satellite orbit parameters includes: Obtain the preset satellite transmission power and preset satellite transmission frequency; Based on the preset satellite orbit parameters, the satellite position data corresponding to each sampling time point within the preset prediction window is determined; The free space path loss corresponding to each sampling time point within the preset prediction window is determined based on the satellite position data, the target position data, and the preset satellite transmission frequency. The target environment penetration loss is determined based on the target environment label; The predicted target receiving power is determined based on the preset satellite transmission power, target environment penetration loss, and free space path loss corresponding to each sampling time point within the preset prediction window.

4. The method according to claim 3, characterized in that, The step of employing a preset access prediction model and determining the target predicted access probability corresponding to each sampling time point within the preset prediction window based on the predicted target received power and the target environment label within each sampling time point within the preset prediction window includes: A preset satellite orbit calculation model is used, and the rate of change of satellite elevation angle corresponding to each sampling time point within the preset prediction window is determined based on the target position data; Obtain the environmental label sequence within a preset historical time period; Retrieve access results within a preset historical time period; The satellite elevation angle change rate corresponding to each sampling time point within the preset prediction window, the environmental label sequence within the historical preset time period, the access results within the historical preset time period, and the predicted target received power corresponding to each sampling time point within the preset prediction window are input into the preset access prediction model, and the predicted access probability of the target corresponding to each sampling time point within the preset prediction window is output; the preset access prediction model is pre-trained to convergence.

5. The method according to claim 4, characterized in that, The step of adjusting the radio frequency transceiver unit based on the target predicted access probability corresponding to each sampling time point within a preset prediction window includes: The target predicted access probability corresponding to each sampling time point within the preset prediction window is compared sequentially with the preset access threshold. If the target predicted access probability corresponding to each sampling time point within the preset prediction window is less than or equal to the preset access threshold, then the radio frequency transceiver unit is adjusted to a sleep state. If there is at least one future predicted time corresponding to a target predicted access probability greater than the preset access threshold, then a target predicted time that meets the preset conditions is selected, and the radio frequency transceiver unit is adjusted to the running state at the target predicted time. The target access parameters are determined based on the predicted target received power corresponding to the predicted target time; the target access parameters include the physical random access channel transmit power and the physical random access channel preamble repetition count; The radio frequency transceiver unit is used to access non-terrestrial networks based on the target access parameters.

6. The method according to claim 1, characterized in that, The method further includes: Obtain updated access data for non-terrestrial network access; The preset access prediction model is fine-tuned based on the updated non-terrestrial network access data to update the preset access prediction model.

7. An access device for a non-terrestrial network, characterized in that, include: The acquisition module is used to acquire target environment data, target location data, and preset satellite orbit parameters; The determination module is used to determine the target environment label based on the target environment data; The determination module is also used to determine the predicted target received power corresponding to each sampling time point within the preset prediction window based on the target environment label, the target location data and the preset satellite orbit parameters; The determination module is also used to determine the target predicted access probability corresponding to each sampling time point in the preset prediction window by adopting a preset access prediction model and based on the predicted target received power corresponding to each sampling time point in the preset prediction window and the target environment label. The control module is used to control the radio frequency transceiver unit according to the target predicted access probability corresponding to each sampling time point within a preset prediction window.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images