Wave position division method, device, electronic device, storage medium and program product

Abstract

The present application provides a wave position division method, apparatus, electronic device, storage medium, and program product, which relate to the field of communication technologies. By predicting the terminal position and dividing the wave positions in advance, this method can more accurately determine the wave position range where the terminal is located at different service scheduling moments, so as to make preparations for beam switching in advance. In this way, the beam resources can be dynamically adjusted according to the movement of the terminal, making the beam coverage range more in line with the actual needs of the terminal, thereby improving the utilization rate of satellite communication resources.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a method, apparatus, electronic device, storage medium, and program product for wave position division. Background Art

[0002] Currently, low-earth orbit satellite systems mainly adopt a beam coverage scheme based on geographical location. According to the coverage range and the number of beams of low-earth orbit satellites, the coverage range is divided into different beam coverage areas. When scheduling beams, each beam polls and scans the beam coverage area. However, this division method only considers the coverage range, which may lead to inaccurate wave position division, resulting in unreasonable allocation of beam resources. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method, apparatus, electronic device, storage medium, and program product for wave position division to improve the problem of inaccurate wave position division caused by the existing wave position division method, resulting in unreasonable allocation of beam resources.

[0004] In a first aspect, the embodiments of this application provide a method for wave position division, and the method includes:

[0005] Obtain the initial position information of each terminal within the satellite coverage range;

[0006] Predict the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information;

[0007] Divide each terminal according to the predicted position information at the subsequent service scheduling moment to obtain a plurality of division ranges corresponding to the subsequent service scheduling moment;

[0008] Determine the wave positions corresponding to the service beams at the subsequent service scheduling moment according to the plurality of division ranges corresponding to the subsequent service scheduling moment.

[0009] In the above implementation process, by predicting the terminal positions and dividing the wave positions in advance, it is possible to more accurately determine the wave position range where the terminal is located at different service scheduling moments, so as to make preparations for beam switching in advance. In this way, the beam resources can be dynamically adjusted according to the movement of the terminal, making the beam coverage range more in line with the actual needs of the terminal, thereby improving the utilization rate of satellite communication resources.

[0010] Optionally, the predicting the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information includes:

[0011] Predict the predicted position information of each terminal at the subsequent service scheduling moment through a machine learning model according to the initial position information.

[0012] In the above implementation process, since the machine learning model can learn the movement rules of the terminals, accurate prediction of the positions can be achieved.

[0013] Optionally, the initial position information includes the position information reported by each terminal during random access and / or the position information periodically reported after accessing the satellite network. In this way, more accurate positions can be predicted based on the actual position information of the terminals obtained.

[0014] Optionally, the initial position information includes the position information of each terminal within a historical period. Predicting the predicted position information of each terminal at the subsequent service scheduling moment based on the initial position information includes:

[0015] Determine the movement conditions of each terminal according to the initial position information;

[0016] Determine the prediction time window of each terminal according to the movement conditions of each terminal;

[0017] Predict the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information within the prediction time window of each terminal.

[0018] In the above implementation process, the prediction time window is determined according to the movement conditions of each terminal. In this way, a suitable prediction time window can be selected considering the movement conditions to more accurately reflect the immediate movement state of the terminal and achieve more accurate position prediction.

[0019] Optionally, determining the prediction time window of each terminal according to the movement conditions of each terminal includes:

[0020] Determine the prediction time window of each terminal according to the movement speed of each terminal, where the size of the prediction time window is negatively correlated with the movement speed of the terminal.

[0021] In the above implementation process, for different movement conditions, the data of different prediction time windows are used for position prediction. In this way, it is convenient to match the movement conditions of different terminals and achieve accurate position prediction.

[0022] Optionally, dividing each terminal according to the predicted position information at the subsequent service scheduling moment to obtain multiple division ranges corresponding to the subsequent service scheduling moment includes:

[0023] Divide each terminal according to the predicted position information at the subsequent service scheduling moment to obtain multiple initial division ranges corresponding to the subsequent service scheduling moment;

[0024] Determine the target terminals at the boundary positions within each initial division range;

[0025] Predict the moving trajectory of the target terminal;

[0026] Determine whether the target terminal will move from the first initial division range where the target terminal originally is to the second initial division range within a set time period according to the moving trajectory;

[0027] If so, adjust the first initial division range and the second initial division range to obtain the finally adjusted division range.

[0028] In the above implementation process, adjusting the initial division range according to the moving trajectory of the terminal enables the service beam corresponding to the adjusted division wave position to serve the target terminal for a long time, which can reduce the situation of unstable service caused by beam switching due to the rapid movement of the target terminal.

[0029] Optionally, the determining the wave position corresponding to the service beam at the subsequent service scheduling moment according to the multiple division ranges corresponding to the subsequent service scheduling moment includes:

[0030] Determine whether each division range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam;

[0031] If so, use this division range as the wave position corresponding to the service beam;

[0032] If not, continue to divide this division range until the divided division range is within the scanning range of the service beam.

[0033] In the above implementation process, by dividing the division range into the scanning range of the service beam, the limited beam resources can be concentrated and allocated to the user-dense areas, which helps to improve the utilization rate of beam resources and enhance the overall capacity of the system.

[0034] Optionally, the determining the wave position corresponding to the service beam at the subsequent service scheduling moment according to the multiple division ranges corresponding to the subsequent service scheduling moment includes:

[0035] Determine whether each division range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam;

[0036] If so, use this division range as the wave position corresponding to the service beam;

[0037] If not, allocate multiple service beams to this division range so that the scanning range formed by the multiple service beams can cover this division range.

[0038] In the above implementation process, by dividing the division range into the scanning range of the service beam, the limited beam resources can be concentrated and allocated to the areas with dense users, which helps to improve the utilization rate of beam resources and enhance the overall capacity of the system.

[0039] Optionally, the dividing each terminal according to the predicted position information at the subsequent service scheduling moment to obtain multiple division ranges corresponding to the subsequent service scheduling moment includes:

[0040] Clustering each terminal according to the predicted position information at the subsequent service scheduling moment to obtain multiple division ranges corresponding to the subsequent service scheduling moment after clustering.

[0041] In the above implementation manner, through the clustering algorithm, terminals with similar geographical locations can be grouped together to form multiple division ranges. This means that each beam can cover more terminals, improving resource utilization.

[0042] In a second aspect, an embodiment of the present application provides a wave position division device, and the device includes:

[0043] A position acquisition module, configured to acquire the initial position information of each terminal within the satellite coverage range;

[0044] A position prediction module, configured to predict the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information;

[0045] A range division module, configured to divide each terminal according to the predicted position information at the subsequent service scheduling moment to obtain multiple division ranges corresponding to the subsequent service scheduling moment;

[0046] A wave position determination module, configured to determine the wave positions corresponding to the service beams at the subsequent service scheduling moment according to the multiple division ranges corresponding to the subsequent service scheduling moment.

[0047] In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect above are run.

[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method provided in the first aspect above are run.

[0049] In a fifth aspect, an embodiment of the present application provides a computer program product, including computer program instructions, and when the computer program instructions are read and run by a processor, the steps in the method provided in the first aspect above are executed.

[0050] Other features and advantages of the present application will be described in the subsequent specification, and will, in part, be obvious from the specification, or will be understood by implementing the embodiments of the present application. The objectives and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written specification, claims, and drawings. Description of the Drawings

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can also be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a flowchart of a method for wave position division provided for an embodiment of the present application;

[0053] Figure 2 It is a schematic diagram of the distribution of a wave position provided for an embodiment of the present application;

[0054] Figure 3 It is a structural block diagram of a device for wave position division provided for an embodiment of the present application;

[0055] Figure 4 It is a schematic diagram of the structure of an electronic device for executing the wave position division method provided for an embodiment of the present application. Detailed Embodiments

[0056] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

[0057] It should be noted that the terms "system" and "network" in the embodiments of the present invention can be used interchangeably. "Multiple" means two or more. In view of this, "multiple" can also be understood as "at least two" in the embodiments of the present invention. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " generally represents an "or" relationship between the associated objects before and after without special instructions.

[0058] It should also be noted that all actions of obtaining signals, information, or data in the present application are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where it is located and with the authorization given by the owner of the corresponding device.

[0059] An embodiment of the present application provides a wave position division method. This method obtains the initial position information of each terminal within the satellite coverage range, then predicts the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information, divides each terminal according to the predicted position information to obtain multiple division ranges corresponding to the subsequent service scheduling moment, and then can determine the wave positions corresponding to the service beams according to the multiple division ranges. By predicting the terminal positions and dividing the wave positions in advance, this solution can more accurately determine the wave position range where the terminal is located at different service scheduling moments, so as to make preparations for beam switching in advance. In this way, the beam resources can be dynamically adjusted according to the movement of the terminal, making the beam coverage range more in line with the actual needs of the terminal, thereby improving the utilization rate of satellite communication resources.

[0060] Please refer to Figure 1 , Figure 1 which is a flowchart of a wave position division method provided by an embodiment of the present application. The method includes the following steps:

[0061] Step S110: Obtain the initial position information of each terminal within the satellite coverage range.

[0062] The satellite coverage range refers to the range on the ground corresponding to the wave positions when the satellite is at a certain position. In a satellite communication system, the coverage range of each satellite can be determined according to the relevant parameters of the satellite. In some embodiments, during the flight of the satellite, the ground station can send the ground position range information corresponding to its coverage range to the satellite in real time. For example, when the satellite flies to a certain position at a certain moment, the satellite can request the ground station to obtain the coverage range information. After receiving the request, the ground station can determine the coverage range corresponding to the satellite according to the current position of the satellite, and then send the ground position range corresponding to the coverage range to the satellite. It can be understood that the satellite corresponds to different coverage ranges at different positions, and the corresponding relationship can be preset and stored in the ground station. Of course, the satellite can also store this corresponding relationship, and the satellite can determine the current coverage range of the satellite according to the current position.

[0063] After determining the current coverage range of the satellite, the position information of each terminal within this coverage range can be obtained.

[0064] In some embodiments, the satellite can combine with a satellite navigation system to obtain the positions of each terminal within its coverage range. These navigation systems send encoded radio signals to the ground terminals. After receiving the signals, the terminals can calculate their own positions using the signal propagation time and the satellite ephemeris information and report them to the navigation system. In this way, the satellite can obtain the position information of each terminal from the navigation system.

[0065] In some other embodiments, the satellite can also obtain the location of the terminal through the interaction between the ground station and the terminal. For example, the ground station sends inquiry information to the terminal. After the terminal responds, the ground station calculates the location of the terminal based on the propagation time of the signal and the feedback information of the terminal, and then feeds it back to the satellite, so that the satellite can obtain the location information of the terminal.

[0066] In some other embodiments, the satellite can obtain the location information of the terminal through the random access process of the terminal, that is, the initial location information includes the location information reported by each terminal during random access.

[0067] Specifically, the satellite can send broadcast system information to each terminal within the satellite coverage area through a signaling beam, and then receive the location information fed back by each terminal according to the broadcast system information.

[0068] Among them, the signaling beam is a dedicated beam used for broadcasting system information and control signaling in the satellite communication system, which carries the basic information required for communication between the satellite and the terminal, including time synchronization information, frequency calibration parameters, access control parameters, etc.

[0069] The satellite will broadcast the signaling beam periodically at a preset time interval. For the signaling beam, the satellite has pre-divided multiple wave positions corresponding to the signaling beam according to its coverage area and the scanning range of the signaling beam. When broadcasting the signaling beam, it will periodically poll and scan each wave position to send broadcast system information. After the terminal is powered on or enters the satellite coverage area, it will search for the signaling beam of the satellite and achieve time synchronization by receiving the synchronization signal.

[0070] The terminal will initiate a random access process in cases such as state changes (such as power-on, wake-up), location changes (such as beam handover, satellite handover), network state changes (such as load balancing, system message update), communication requirements (such as data transmission, emergency call), etc. The terminal initiates random access by detecting the broadcast system information of the signaling beam. Specifically, the terminal can construct a random access request according to the access parameters in the broadcast system information. The terminal carries its own geographical location information in the random access request, which can be obtained through the positioning module on the terminal, and then sends a random access request to the satellite. The satellite obtains the location information therein through the random access request interface captured from the terminal.

[0071] And / or, the initial location information may also include the location information periodically reported by each terminal after accessing the satellite network. That is, after each terminal accesses the satellite network, it can periodically report its own location information through signaling, so that the satellite can also obtain the location information of each terminal.

[0072] Step S120: Predict the predicted location information of each terminal at the subsequent service scheduling moment according to the initial location information.

[0073] Since the initial position information of the terminal obtained by the satellite depends on the active reporting of the terminal, if at the time of service scheduling, the position of the terminal may have been obtained a long time ago. If beam division is performed based on the previously obtained position and then beam allocation is carried out, it may lead to inaccuracy because the position of the terminal will change. As a result, there may not be many terminals or no terminals in some wave positions. If beams are still allocated for service at this time, it will cause the problem of resource waste. Therefore, to improve this problem, the terminal position information at the time of service scheduling can be predicted in this solution.

[0074] The wave division method in this solution can be executed regularly, or it can also be executed before each service scheduling moment. For example, before the next service scheduling moment arrives, based on the current obtained position information of each terminal, that is, the initial position information, the predicted position information at the subsequent service scheduling moment can be predicted and wave division can be carried out. The subsequent service scheduling moment can refer to the next service scheduling moment or several subsequent service scheduling moments, etc. When the next service scheduling moment arrives, service scheduling can be carried out according to the already divided wave positions and allocated beams, which can improve the efficiency of service scheduling.

[0075] In some embodiments, the initial position information of each terminal can be collected. For example, the initial position information includes a large amount of historical position information reported by the terminal. In this way, the movement rules and trends of the terminal can be analyzed based on the historical position information, so as to predict the predicted position information at the subsequent service scheduling moment.

[0076] In some embodiments, position prediction can also be achieved through the Kalman filter algorithm. For example, the initial position information can be used as the observed value in the Kalman filter algorithm, and then position prediction can be carried out to obtain the predicted position information.

[0077] In some other embodiments, the machine learning model can also be used to predict the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information.

[0078] Specifically, the machine learning model can be a long short-term memory neural network model, which can well capture the long-term dependencies in time series data, so as to better predict the future position of the terminal.

[0079] Alternatively, the machine learning model can be a model generated based on the graph neural network and the long short-term memory neural network. The graph neural network can effectively process the spatial relationship between positions, and then the long short-term memory neural network can be used to extract the dependencies between positions, which can improve the accuracy of position prediction.

[0080] In the specific implementation process, a large amount of location information can be collected in advance for training the model. In addition to location information, information such as the speed, acceleration, and direction of the terminal, as well as environmental data such as terrain and traffic conditions, can also be collected and used together for training the model.

[0081] The graph neural network part can be used to capture the spatial relationship between terminals. The input is location information and other features, and the output is the node features after graph convolution processing, representing the spatial state of the terminals. The long short-term memory network is used to process time series data and capture the temporal dependencies. The input is the output features of the graph neural network, and the output is the predicted location information of the terminal at future moments. Here, the future moments can be future service scheduling moments, and the predicted location information for multiple subsequent service scheduling moments can be output.

[0082] It can be understood that the machine learning model can be implemented using other modes. For example, a long short-term memory neural network model can be used for short-term prediction, and a support vector machine or a backpropagation neural network can be used for long-term prediction to improve the overall prediction accuracy. Or a hybrid model combining an attention mechanism with a convolutional neural network and a long short-term memory network can also be used for prediction. For the implementation methods of other models, they will not be exemplified one by one here.

[0083] In some embodiments, the actual location reported by the terminal can be used as feedback data later for updating and optimizing the machine learning model, that is, online learning of the model using the actual location information, so that it can adapt to the changes in the movement patterns of the terminals, and then achieve accurate location prediction.

[0084] In some embodiments, in order to compensate for the location error predicted by the model, the predicted location obtained through the Kalman filter algorithm can also be integrated with the predicted location obtained through the machine learning model. For example, the two predicted locations can be averaged, and the obtained average value is used as the final predicted location. Or, the two predicted locations can also be weighted and fused to generate a more accurate predicted location.

[0085] Step S130: Divide each terminal according to the predicted location information at the subsequent service scheduling moment to obtain multiple division ranges corresponding to the subsequent service scheduling moment.

[0086] After obtaining the predicted location information, each terminal can be divided according to the predicted location information, that is, each terminal is divided into multiple division ranges, and each division range can include multiple terminals. In this way, the locations where terminals exist within the satellite coverage can be divided to form wave positions.

[0087] Step S140: Determine the wave positions corresponding to the service beams at the subsequent service scheduling moment according to the multiple division ranges corresponding to the subsequent service scheduling moment.

[0088] Among them, the service beam refers to the beam used by the satellite to provide actual data transmission services to terminals. Different from the signaling beam, the service beam is mainly used to carry user data (such as voice, video, text information, etc.). The coverage range of the service beam is usually smaller and more precise than that of the signaling beam because the service beam needs to concentrate energy to improve data transmission efficiency and energy.

[0089] After obtaining multiple division ranges, the multiple division ranges can be determined as the wave positions corresponding to the service beam. For example, if N division ranges are obtained, these N division ranges can be determined as the N wave positions corresponding to the service beam, as Figure 2 shown.

[0090] After determining the wave positions corresponding to the service beam, the satellite can schedule the service beam according to the determined wave positions, that is, adjust the pointing and resource allocation of the service beam so that the service beam can perform polling scans on each wave position (if the number of service beams is less than the number of wave positions). Of course, if the number of service beams is greater than the number of wave positions, one wave position can be scanned by one service beam to achieve service interaction between the satellite and each terminal within the wave position.

[0091] In the above implementation process, by predicting the terminal positions and dividing the wave positions in advance, it is possible to more accurately judge the wave position range where the terminal is located at different service scheduling moments, so as to make preparations for beam switching in advance. In this way, the beam resources can be dynamically adjusted according to the movement of the terminal, making the beam coverage range more in line with the actual needs of the terminal, thereby improving the utilization rate of satellite communication resources.

[0092] On the basis of the above embodiments, in the above implementation manner of predicting the positions of the terminals, the initial position information may further include the position information of each terminal in the previous time period. Then, the movement conditions of each terminal can be determined according to the initial position information, the prediction time window of each terminal can be determined according to the movement conditions of each terminal, and the predicted position information of each terminal at the subsequent service scheduling moment can be predicted according to the initial position information within the prediction time window of each terminal.

[0093] The initial position information can represent the movement trajectory of the terminal in the previous time period. The previous time period can refer to all time periods before the current time. Therefore, the movement conditions of each terminal can be determined through the initial position information. For example, by counting the distance between the first position and the last position of each terminal in the previous time period, if the distance is less than or equal to the set distance, it can be considered that the movement condition of the terminal is high-speed movement. On the contrary, if the distance is greater than the set distance, it can be considered that the movement condition of the terminal is low-speed movement.

[0094] Therefore, the prediction time window of each terminal can be determined according to the movement conditions of each terminal, and the prediction time windows corresponding to different movement conditions may be different.

[0095] In some embodiments, the prediction time window can be dynamically determined according to the movement conditions. For a terminal with a high-speed movement condition, the prediction time window is determined as the first prediction time window, and for a terminal with a low-speed movement condition, the prediction time window is determined as the second prediction time window. The length of the second prediction time window is greater than the length of the first prediction time window.

[0096] Among them, the first prediction time window and the second prediction time window can be set in advance for the two movement conditions. In this way, the first prediction time window and the second prediction time window are static and can be flexibly set according to actual needs. For example, the first prediction time window is set as T1, and the second prediction time window is set as T2, and T2 is greater than T1. When it is determined that the movement condition of a certain terminal is high-speed movement, its prediction time window is determined as T1, and when it is determined that the movement condition of a certain terminal is low-speed movement, the prediction time window is determined as T2.

[0097] In some other embodiments, the first prediction time window and the second prediction time window can also be intelligently predicted through a model. For example, the relevant information of the terminal with the determined high-speed movement condition, such as speed, acceleration, driving distance, etc., can be input into a machine learning model (such as a long short-term memory neural network model, etc.) for prediction, so that the model can predict the first prediction time window corresponding to the terminal in the high-speed movement scenario. The relevant information of the terminal with the determined low-speed movement condition, such as speed, acceleration, driving distance, etc., can also be input into a machine learning model (such as a long short-term memory neural network model, etc.) for prediction, so that the model can predict the second prediction time window corresponding to the terminal in the low-speed movement scenario.

[0098] The models used for high-speed prediction and low-speed prediction can be the same model or different models. During the training process, the model can learn the relationship between the relevant information of the terminal in the high-speed movement and low-speed movement scenarios and the prediction time window, so that a more accurate time window can be predicted by integrating the information of each terminal.

[0099] It can be understood that the distinction of movement conditions can be more granular. For example, it can also be divided into medium-speed movement conditions. For a terminal with a medium-speed movement condition, a prediction time window can also be determined. Then, for these terminals, the initial position information within the corresponding prediction time window can be obtained for position prediction.

[0100] In the above implementation process, the prediction time window is determined according to the movement conditions of each terminal. In this way, a suitable prediction time window can be selected considering the movement conditions to more accurately reflect the immediate movement state of the terminal and achieve more accurate position prediction.

[0101] Based on the above embodiments, in the method for determining the prediction time window of each terminal, the prediction time window of each terminal can also be determined according to the movement speed of each terminal, where the size of the prediction time window is negatively correlated with the movement speed of the terminal.

[0102] This negative correlation can be understood to include cases of step changes, such as the above-mentioned solutions for determining the prediction time window for high-speed movement and low-speed movement.

[0103] Of course, the negative correlation can also mean that there is a linear relationship between the movement speed and the prediction time window, that is, when one variable increases, the other variable decreases proportionally, or it can be a non-linear relationship, but generally it shows a negative correlation.

[0104] For example, a formula similar to the following can be used to determine the prediction time window of each terminal:

[0105] t = C / v, where C can be a constant, v represents the movement speed of the terminal in the historical period, and C can be used to adjust the proportional relationship between the size of the prediction time window and the speed, and can be set according to actual experience. Therefore, when the movement speeds of terminals are different, the determined prediction time windows can be different. The greater the movement speed, the shorter the prediction time window; conversely, the smaller the movement speed, the longer the prediction time window.

[0106] The initial position information may include some position information when the terminal accesses and after access. Therefore, for a terminal moving at high speed, the position change of the terminal accelerates. Therefore, a shorter prediction time window can be used to capture these rapid changes. The shorter time window can more sensitively reflect the immediate movement state of the terminal, thereby improving the prediction accuracy. For a terminal moving at low speed, the position change of the terminal is slower. Therefore, a longer time window can be used to capture the trends within a longer time range, and the longer time window can reduce the influence of noise and improve the prediction stability.

[0107] It can be understood that if the prediction time window of a certain terminal is greater than the duration between the time when the position information of the terminal is first obtained and the current time, then the initial position information within the prediction time window of this terminal includes all the position information within the previous period before the current time.

[0108] In the above implementation process, for different movement conditions, data with different prediction time windows are used for position prediction. In this way, it is convenient to match the movement conditions of different terminals and achieve accurate position prediction.

[0109] Based on the above embodiments, since the divided range may not match the scanning range of the service beam, in the method of determining the wave position corresponding to the service beam, it is possible to first determine whether each divided range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam. If so, the divided range is used as the wave position corresponding to the service beam. If not, the divided range is further divided until the divided range is within the scanning range of the service beam.

[0110] Among them, the scanning range of the service beam is related to the relevant configuration of the satellite, such as related to the beam width of the configured service beam.

[0111] If the divided range is within the scanning range of the service beam, it indicates that the divided range can be completely covered by the service beam, so the divided range can be used as the wave position corresponding to the service beam. If the divided range is not within the scanning range of the service beam, it indicates that the divided range cannot be completely covered by the service beam. At this time, the divided range can be further divided, for example, further divided into multiple divided ranges until the divided range is within the scanning range of the service beam.

[0112] In some implementation manners, each divided range contains some terminals with close positions. The boundary of the divided range can be the minimum circumscribed circle, the minimum circumscribed ellipse, the minimum circumscribed rectangle, etc. The scanning range of the service beam can be circular, elliptical, etc. Therefore, it is possible to determine whether the divided range is within the scanning range of the service beam by determining whether the scanning range of the service beam can cover the boundary of the divided range.

[0113] In the method of further dividing the divided range, a recursive division method can be adopted. For example, the divided range is first divided into two sub-ranges, and then it is determined whether these two sub-ranges are respectively within the scanning range of the service beam. If so, these two sub-ranges are respectively used as the wave positions of the service beam. If not, further division is continued until the condition that the sub-range is within the scanning range of the service beam is met and the division stops.

[0114] In the above implementation process, by dividing the divided range into the scanning range of the service beam, the limited beam resources can be concentrated and allocated to the area with dense users, which helps to improve the utilization rate of beam resources and enhance the overall capacity of the system.

[0115] Based on the above embodiments, when determining whether each divided range is within the scanning range of the service beam, the first parameter of the minimum circumscribed circle formed by each divided range can be obtained. The first parameter can include radius, diameter, area, or circumference, etc. Then, the second parameter of the minimum circumscribed circle formed by the scanning range of the service beam is obtained. The second parameter can also include radius, diameter, area, or circumference, etc. Then, it is determined whether the first parameter is less than or equal to the second parameter.

[0116] Each divided range obtained by division may not be a regular shape. For example, if it is divided according to a rectangle, then at this time, the first parameter of the minimum circumscribed circle formed by this divided range can be obtained. Here, the minimum circumscribed circle algorithm (such as the Welzl algorithm, etc.) can be used to calculate the minimum circumscribed circle of each divided range. The minimum circumscribed circle is the smallest circular area that contains all terminals within this divided range. After obtaining the minimum circumscribed circle, parameters such as the radius, diameter, area, or circumference of the minimum circumscribed circle can be calculated as the first parameter.

[0117] When determining the minimum circumscribed circle corresponding to the scanning range of the service beam, the detailed parameters of this service beam can be obtained from the satellite system, including information such as the shape, directivity, beam width, scanning angle, etc. of the beam. Then, based on the parameters of the service beam, its scanning range can be determined. Its scanning range can be circular, elliptical, or an irregular polygon, etc. If the shape is circular, then the minimum circumscribed circle of its scanning range is its circle. If it is not circular, then the minimum circumscribed circle algorithm can also be used to obtain its minimum circumscribed circle and calculate the corresponding second parameter, that is, radius, diameter, area, or circumference, etc.

[0118] When comparing the first parameter and the second parameter, the same parameters are compared. For example, if the first parameter includes radius R1, diameter D1, area S1, or circumference Y1, and the second parameter includes radius R2, diameter D2, area S2, or circumference Y2, then R1 is compared with R2, D1 and D2 are compared, S1 and S2 are compared, and Y1 and Y2 are compared. If R1 is less than or equal to R2, or D1 is less than or equal to D2, or S1 is less than or equal to S2, or Y1 is less than or equal to Y2, then it is considered that the divided range is within the scanning range of the service beam. Otherwise, it is considered that the divided range is not within the scanning range of the service beam.

[0119] In some other embodiments, the shape formed by dividing the range can also be the minimum circumscribed ellipse, the minimum circumscribed rectangle, etc., and the shape formed by the scanning range of the service beam can also be the minimum circumscribed ellipse and the minimum circumscribed rectangle, etc. For the convenience of comparison, when determining the shapes formed by the dividing range and the scanning range, the shapes of the two can be unified, for example, both are the minimum circumscribed rectangles, etc. In this way, parameters such as the area, perimeter, or diagonal length of the minimum circumscribed rectangle can be compared to determine whether the dividing range is within the scanning range. The specific comparison method is similar to the above method and will not be elaborated here.

[0120] In the above implementation process, by calculating the parameters of the minimum circumscribed circles of the dividing range and the scanning range, it can be accurately determined whether the dividing range is within the scanning range through the comparison of the parameters.

[0121] Based on the above embodiments, in other ways of determining the wave positions corresponding to the service beams, it is also possible to first determine whether each dividing range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam. If so, the dividing range is used as the wave position corresponding to the service beam. If not, multiple service beams are allocated to the dividing range so that the scanning ranges formed by the multiple service beams can cover the dividing range.

[0122] Among them, the method of determining whether the dividing range is within the scanning range of the service beam can refer to the relevant descriptions in the above embodiments and will not be repeated here.

[0123] In this implementation method, if the dividing range is not within the scanning range of the service beam, it means that a single service beam cannot fully cover the dividing range. Then multiple service beams can be allocated to the dividing range. Here, the gap between the dividing range and the scanning range can be compared. For example, using the radius of the minimum circumscribed circle. If the difference between the radius R1 of the minimum circumscribed circle of the dividing range minus the radius R2 of the minimum circumscribed circle of the scanning range is less than R2 and greater than 0, at this time, two service beams can be allocated to the dividing range. Of course, when specifically determining the number of service beams to be allocated, if R1 divided by R2 can be divided evenly, the number of service beams is the quotient of R1 divided by R2. If R1 divided by R2 cannot be divided evenly, the number of service beams is the quotient of R1 divided by R2 plus one.

[0124] In this way, the total scanning range formed by the multiple service beams can completely cover the dividing range. When scanning, these multiple service beams of the satellite can be pointed to the dividing range, and by adjusting the pointing angles of each service beam, each service beam can cover different ranges within the dividing range, thereby achieving full coverage and realizing communication between the satellite and each terminal within the dividing range.

[0125] In the above implementation process, by dividing the division range into the scanning range of the service beam, the limited beam resources can be concentrated and allocated to the areas with dense users, which helps to improve the utilization rate of beam resources and enhance the overall capacity of the system.

[0126] Based on the above embodiments, in the method of dividing each terminal to obtain multiple division ranges, the terminals can be clustered according to the predicted position information of each terminal at the subsequent service scheduling moment, and multiple division ranges corresponding to the subsequent service scheduling moment after clustering can be obtained.

[0127] For example, the K-means clustering algorithm can be used to cluster multiple terminals, and the specific implementation process is as follows:

[0128] a. Initialize the clustering centers:

[0129] Randomly select the predicted position information of K terminals from all terminals as the initial clustering centers.

[0130] b. Calculate the distance from each terminal to the clustering centers:

[0131] For each terminal, calculate its distances to all clustering centers.

[0132] c. Assign each terminal to the nearest clustering center.

[0133] Assign each terminal to the cluster corresponding to the nearest clustering center.

[0134] d. Recalculate the clustering centers:

[0135] For each cluster, recalculate the position mean of all terminals within the cluster as the new clustering center, and the new clustering center is the average value of the predicted position information of all terminals in the cluster.

[0136] e. Determine whether to converge:

[0137] If the positions of all clustering centers no longer change, or the change is less than a preset threshold, the algorithm converges and stops iterating.

[0138] If the clustering centers change, return to step b, continue to calculate the new clustering centers and reassign the terminals.

[0139] Repeat steps b to e. If the clustering centers change, continue to execute the above steps until the clustering centers converge, that is, there is no significant change.

[0140] The clustering result is multiple division ranges. If a certain division range is not within the scanning range of the service beam, then this division range needs to be further clustered, that is, use the clustering algorithm to further divide this division range into multiple subclasses until the ranges of all subclasses are within the scanning range of the service beam.

[0141] In practical applications, the positions of the terminals may change dynamically. In this case, these terminals can be reclustered regularly to update the clustering result.

[0142] In some other embodiments, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) can also be used to cluster multiple terminals. This algorithm is suitable for processing clusters with noise and irregular shapes, can automatically discover clusters of any shape, and can effectively identify and process noise points. The specific implementation process of this clustering algorithm can refer to the implementation in related technologies and will not be described in detail here.

[0143] In the above implementation process, through the clustering algorithm, terminals with close geographical locations can be grouped together to form multiple division ranges. This means that each beam can cover more terminals, improving resource utilization.

[0144] Based on the above embodiments, in the above method of clustering each terminal, during the clustering process, the clustering center can be determined according to the distribution of the predicted position information of each terminal.

[0145] In this implementation, the mean and standard deviation of all terminals can be calculated to obtain the distribution range of these terminals. The distribution range is generally within the range of the mean plus or minus 1 to 2 standard deviations. In this way, K points can be evenly selected as the initial clustering centers according to the distribution range, for example, equally spaced points within the data range can be selected.

[0146] In some other embodiments, the terminals can also be divided into high-density areas and low-density areas according to the predicted position information of the terminals, and then the initial clustering centers are selected from the high-density areas and low-density areas. The number of initial clustering centers selected in the high-density area can be greater than the number of initial clustering centers selected in the low-density area.

[0147] In some other embodiments, the predicted position information of multiple terminals can also be subjected to principal component analysis, project the predicted position information of the terminals onto the principal component direction, and evenly select K points on the principal component direction as the initial clustering centers.

[0148] In some other embodiments, a machine learning model can also be used to extract the initial clustering centers corresponding to the predicted location information of multiple terminals. For example, the predicted location information of multiple terminals can be input into the machine learning model, and multiple initial clustering centers can be output through the machine learning model. During the training process, the machine learning model can learn the relationship between the distribution of the predicted location information of a large number of terminals and the clustering centers. In this way, the clustering centers can be accurately predicted by the machine learning model. Then, the clustering algorithm is run. Since the initial clustering centers predicted by the machine learning model are relatively accurate, the clustering algorithm can converge quickly, improving the efficiency of terminal division.

[0149] Among them, the machine learning model can specifically be a deep learning model, such as a random forest model, a convolutional neural network model, a recurrent neural network model, a Transformer model, etc.

[0150] In the above implementation process, the clustering centers are determined according to the distribution of the terminals, so as to truly reflect the actual distribution of the terminals, making the clustering result more accurate, thereby improving the utilization rate of beam resources and reducing unnecessary coverage areas.

[0151] Based on the above embodiments, in the way of dividing each terminal, in order to simplify the division process, it can also be divided according to the scanning range of the service beam. In the specific implementation process, the minimum circumscribed circle formed by these terminals can be determined first according to the predicted location information of each terminal at the subsequent service scheduling moment, that is, the area without terminals within the satellite coverage range is excluded. Then, the minimum circumscribed circle is divided according to the scanning range. For example, starting from the center of the minimum circumscribed circle, the minimum circumscribed circle is divided into multiple sub-regions along the set direction. The diameter of each sub-region can not exceed the diameter of the scanning range. The sub-regions divided in this way can be used as the division range and can be used as the wave positions corresponding to the service beams. If a certain terminal is located on the boundary of multiple sub-regions, the range of the sub-region can be appropriately expanded.

[0152] In some embodiments, if the number of terminals in the sub-region divided in this way is small, the sub-region can be merged with other sub-regions with a high terminal density, and multiple service beams can be allocated to the merged sub-region subsequently.

[0153] In some embodiments, the terminal density in each sub-region can be calculated. If the number of terminals in a certain sub-region is too small, the boundary of the sub-region can be adjusted, such as merging with other sub-regions with a high terminal density as in the above scheme.

[0154] In this solution, after determining the wave positions of the service beams, the service beams can be polled and scheduled for these wave positions so that the terminals in each wave position can obtain services.

[0155] Based on the above embodiments, after the wave positions are divided, the boundaries and ranges of the wave positions can also be dynamically adjusted according to the position change situation of the terminals.

[0156] For example, if the wave positions for the next service scheduling moment are divided at the current moment, and the position information reported by the terminal is received during the period from the current moment to the next service scheduling moment, then the predicted position of the terminal at the next service scheduling moment can be adjusted according to the position information of the terminal. The specific adjustment method can be to correct its predicted position according to the latest received position information of the terminal, such as by weighted averaging or other methods. Then, the divided wave positions are adjusted according to its corrected predicted position. For example, if the terminal was originally divided into wave position 1, and if the corrected predicted position is closer to the clustering center of wave position 2, then the terminal can be adjusted to wave position 2. At this time, the boundaries and ranges of wave position 1 and wave position 2 need to be adjusted.

[0157] In some embodiments, in order to reduce the amount of adjustment, it can also be determined whether the difference between the corrected predicted position of the terminal in the above example and the previous predicted position exceeds a threshold. If it exceeds the threshold, then the wave position is re-adjusted. If it does not exceed, then the wave position is not adjusted.

[0158] In some other embodiments, if the wave positions for the next service scheduling moment (referred to as moment 1) have been divided at the current moment, at the next service scheduling moment after the next service scheduling moment (referred to as moment 2), one way is to re-divide the wave positions according to the above method before moment 2. Another way is that if it is considered that the position changes of some terminals may be small, so terminals with large position changes can be re-clustered to avoid full-scale calculation.

[0159] For example, before moment 2, predict the predicted positions of each terminal at moment 2. The predicted positions of each terminal at moment 2 can be compared with the previously obtained positions of the terminals. For example, for terminal 1, the predicted position of terminal 1 at moment 2 can be compared with the previously obtained position of terminal 1 (which can be the position of terminal 1 closest to moment 2 reported during the period between moment 1 and moment 2. If no position is reported during this period, it is the predicted position at moment 1). If the position difference is greater than the set threshold, it is considered that the position change is large. At this time, terminal 1 can be re-clustered, that is, recalculate the distance between terminal 1 and the clustering centers of each divided wave position, and then re-divide terminal 1 into the corresponding wave position. It is equivalent to only adjusting terminal 1 for the wave positions at moment 2 at this time.

[0160] Understandably, in this case, the wave position can be adjusted only for several adjacent service scheduling moments. For example, the wave position can be divided with a period of 3 service scheduling moments. At the 4th service scheduling moment, the wave position needs to be re-divided according to the above method in a timely manner to cope with the position change of the terminal. Specifically, for example, the wave position is divided according to the above method at moment 1. At moments 2 and 3, the wave position can be adjusted only for the terminals with large position changes. At moment 4, the wave position is re-divided according to the above method again.

[0161] In some embodiments, in the above method of dividing multiple terminals according to the predicted position information of the terminals, after multiple division ranges have been obtained through clustering or other means, which can be referred to as multiple initial division ranges, considering the subsequent position changes of the terminals, the target terminals at the boundary positions within each initial division range can be determined first, and then the movement trajectories of these target terminals can be predicted. The initial division ranges can be adjusted according to the movement trajectories. For example, it can be determined whether a target terminal will move from the first initial division range where the target terminal originally is to the second initial division range within a set time period according to the movement trajectory. If so, the first initial division range and the second initial division range are adjusted to obtain the finally adjusted division range. Then, the wave positions corresponding to the service beams at subsequent service scheduling moments can be determined according to the finally obtained division range.

[0162] Among them, being at the boundary position can be understood as the distance between the terminal and the boundary of the minimum circumscribed circle formed by the initial division range being less than the set distance. Then, for the target terminals at the boundary positions, the movement trajectories of these target terminals can be predicted. Here, the position information of these target terminals and the relevant parameter information of the terminal (such as the speed and acceleration of the terminal, the environmental parameters where the terminal is located, the type of the terminal, etc.) can be input into a deep learning model for prediction to obtain the movement trajectories of these target terminals.

[0163] For example, it is possible to determine whether the target terminal will move out of the original division range within a short period of time (such as a set duration, e.g., 30 s) according to the movement trajectory of the target terminal. If so, it means that the position of the target terminal changes relatively fast. For example, the target terminal is on a fast-moving device such as a high-speed train. In this case, the target terminal can be divided into the division range it is about to move to. For example, initially, the target terminal is within division range 1 (i.e., the first initial division range). Through movement trajectory prediction, if it is determined that the target terminal will move into division range 2 (i.e., the second initial division range) within the set duration, the target terminal can be divided into division range 2, that is, division range 2 is expanded and division range 1 is reduced, so that the service beam corresponding to division range 2 can serve the target terminal for a longer time, and the situation of unstable service caused by beam switching due to the fast movement of the target terminal can be reduced. Of course, if the target terminal does not move out of the original division range within the set time period, division range 1 is not adjusted.

[0164] It can be understood that for each target terminal at the boundary within each initial division range, the above method can be used for processing, so as to optimize the initial division range and achieve a better division of wave positions.

[0165] Please refer to Figure 3 , Figure 3 FIG. [X] is a structural block diagram of a wave position division device provided by an embodiment of the present application. The device can be a module, a program segment, or code on an electronic device. It should be understood that the device corresponds to the above Figure 1 method embodiment and can execute Figure 1 each step involved in the method embodiment. The specific functions of the device can be seen in the above description. To avoid repetition, the detailed description is appropriately omitted here.

[0166] Optionally, the device 200 includes:

[0167] A position acquisition module 210, configured to acquire the initial position information of each terminal within the satellite coverage range;

[0168] A position prediction module 220, configured to predict the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information;

[0169] A range division module 230, configured to divide each terminal according to the predicted position information at the subsequent service scheduling moment to obtain a plurality of division ranges corresponding to the subsequent service scheduling moment;

[0170] A wave position determination module 240, configured to determine the wave positions corresponding to the service beams at the subsequent service scheduling moment according to the plurality of division ranges corresponding to the subsequent service scheduling moment.

[0171] Optionally, the location prediction module 220 is configured to predict the predicted location information of each terminal at the subsequent service scheduling moment according to the initial location information through a machine learning model.

[0172] Optionally, the initial location information includes the location information reported by each terminal during random access and / or the location information periodically reported after accessing the satellite network.

[0173] Optionally, the initial location information includes the location information of each terminal within a historical period. The location prediction module 220 is configured to determine the movement condition of each terminal according to the initial location information; determine the prediction time window of each terminal according to the movement condition of each terminal; and predict the predicted location information of each terminal at the subsequent service scheduling moment according to the initial location information within the prediction time window of each terminal.

[0174] Optionally, the location prediction module 220 is configured to determine the prediction time window of each terminal according to the movement speed of each terminal, where the size of the prediction time window is negatively correlated with the movement speed of the terminal.

[0175] Optionally, the range division module 230 is configured to divide each terminal according to the predicted location information at the subsequent service scheduling moment to obtain a plurality of initial division ranges corresponding to the subsequent service scheduling moment; determine the target terminals at the boundary positions within each initial division range; predict the movement trajectories of the target terminals; determine whether the target terminals will move from the first initial division range where the target terminals originally are to the second initial division range within a set time period according to the movement trajectories; and if so, adjust the first initial division range and the second initial division range to obtain the finally adjusted division ranges.

[0176] Optionally, the wave position determination module 240 is configured to determine whether each division range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam; if so, use this division range as the wave position corresponding to the service beam; if not, continue to divide this division range until the divided division range is within the scanning range of the service beam.

[0177] Optionally, the wave position determination module 240 is configured to determine whether each division range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam; if so, use this division range as the wave position corresponding to the service beam; if not, allocate a plurality of service beams to this division range so that the scanning range formed by the plurality of service beams can cover this division range.

[0178] Optionally, the range division module 230 is configured to cluster each terminal according to the predicted position information at the subsequent service scheduling moment, so as to obtain multiple division ranges corresponding to the subsequent service scheduling moment after clustering.

[0179] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described device can refer to the corresponding process in the foregoing method embodiment, and will not be repeated herein.

[0180] Please refer to Figure 4 , Figure 4 FIG. is a schematic structural diagram of an electronic device for implementing a wave position division method provided by an embodiment of the present application. The electronic device may include: at least one processor 310, such as a CPU, at least one communication interface 320, at least one memory 330, and at least one communication bus 340. Among them, the communication bus 340 is used to implement connection communication between these components. Among them, the communication interface 320 of the device in the embodiment of the present application is used to communicate with other node devices for signaling or data. The memory 330 may be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. Optionally, the memory 330 may also be at least one storage device located far from the foregoing processor. The memory 330 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 310, the electronic device executes the above Figure 1 shown method process.

[0181] It can be understood that Figure 4 the structure shown is only schematic, and the electronic device may further include more or fewer components than those shown in Figure 4 , or have a different configuration from that shown in Figure 4 . Figure 4 Each component shown in can be implemented by hardware, software, or a combination thereof.

[0182] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it executes the method process executed by the electronic device in the method embodiment shown in Figure 1 .

[0183] This embodiment discloses a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided in the foregoing method embodiments. For example, it includes:

[0184] Obtain the initial position information of each terminal within the satellite coverage range;

[0185] Predict the predicted position information of each terminal at the subsequent service scheduling moment according to the initial position information;

[0186] Divide each terminal according to the predicted position information at the subsequent service scheduling moment to obtain multiple division ranges corresponding to the subsequent service scheduling moment;

[0187] Determine the wave positions corresponding to the service beams at the subsequent service scheduling moment according to the multiple division ranges corresponding to the subsequent service scheduling moment.

[0188] In summary, the embodiments of the present application provide a wave position division method, device, electronic device, storage medium and program product. By predicting the terminal positions and dividing the wave positions in advance, it is possible to more accurately determine the wave position range where the terminal is located at different service scheduling moments, so as to make preparations for beam switching in advance. In this way, the beam resources can be dynamically adjusted according to the movement of the terminal, making the beam coverage range more in line with the actual needs of the terminal, thereby improving the utilization rate of satellite communication resources.

[0189] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces. The indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0190] In addition, the units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0191] Furthermore, in each embodiment of the present application, the functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0192] In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0193] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A wave position division method, characterized in that: The method comprises: Obtaining the initial location information of each terminal within the satellite coverage area; Predicting predicted location information of each terminal at a subsequent service scheduling time according to the initial location information; Dividing each terminal according to the predicted position information of the subsequent service scheduling time to obtain multiple division ranges corresponding to the subsequent service scheduling time; Determining the beam position corresponding to the service beam at the subsequent service scheduling moment according to the multiple division ranges corresponding to the subsequent service scheduling moment; The step of dividing each terminal according to the predicted location information of the subsequent service scheduling moment to obtain multiple division ranges corresponding to the subsequent service scheduling moment includes: Dividing each terminal according to the predicted position information at the subsequent service scheduling time to obtain a plurality of initial division ranges corresponding to the subsequent service scheduling time; Determine the target terminal at the boundary position within each initial division range; Predicting the movement trajectory of the target terminal; Determining, according to the movement trajectory, whether the target terminal will move from the first initial division range where the target terminal was originally located to the second initial division range within a set time period; If so, the first initial division range and the second initial division range are adjusted to obtain a final adjusted division range.

2. The method according to claim 1, characterized in that The predicting the predicted location information of each terminal at the subsequent service scheduling time according to the initial location information includes: The predicted location information of each terminal at the subsequent service scheduling moment is predicted based on the initial location information through a machine learning model.

3. The method according to claim 1, characterized in that: The initial location information includes location information reported by each terminal during random access and / or location information periodically reported after accessing the satellite network.

4. The method according to claim 1, characterized in that The initial location information includes location information of each terminal in a historical period, and the predicted location information of each terminal at a subsequent service scheduling moment is predicted based on the initial location information, including: Determine the movement status of each terminal according to the initial position information; Determine the prediction time window of each terminal according to the movement of each terminal; The predicted location information of each terminal at the subsequent service scheduling time is predicted based on the initial location information of each terminal within the prediction time window.

5. The method according to claim 4, characterized in that The step of determining the prediction time window of each terminal according to the movement situation of each terminal includes: The prediction time window of each terminal is determined according to the movement speed of each terminal, wherein the size of the prediction time window is negatively correlated with the movement speed of the terminal.

6. The method according to claim 1, characterized in that The determining, according to the multiple division ranges corresponding to the subsequent service scheduling moment, the beam position corresponding to the service beam at the subsequent service scheduling moment includes: Determine whether each division range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam; If yes, the divided range is used as the wave position corresponding to the service beam; If not, continue to divide the divided range until the divided range is within the scanning range of the service beam.

7. The method according to claim 1, characterized in that The determining, according to the multiple division ranges corresponding to the subsequent service scheduling moment, the beam position corresponding to the service beam at the subsequent service scheduling moment includes: Determine whether each division range corresponding to the subsequent service scheduling moment is within the scanning range of the service beam; If yes, the divided range is used as the wave position corresponding to the service beam; If not, multiple service beams are allocated to the divided range so that the scanning range formed by the multiple service beams can cover the divided range.

8. The method according to claim 1, characterized in that The dividing each terminal according to the predicted position information of the subsequent service scheduling time to obtain a plurality of division ranges corresponding to the subsequent service scheduling time includes: Each terminal is clustered according to the predicted position information of the subsequent service scheduling time, so as to obtain a plurality of division ranges corresponding to the clustered subsequent service scheduling time.

9. A wave position division device, characterized in that: The device comprises: A location acquisition module is used to obtain the initial location information of each terminal within the satellite coverage area; A location prediction module, used to predict the predicted location information of each terminal at a subsequent service scheduling time according to the initial location information; A range division module, used to divide each terminal according to the predicted location information of the subsequent service scheduling time, to obtain multiple division ranges corresponding to the subsequent service scheduling time; A beam position determination module, used to determine the beam position corresponding to the service beam at the subsequent service scheduling moment according to a plurality of division ranges corresponding to the subsequent service scheduling moment; Among them, the range division module is specifically used to divide each terminal according to the predicted position information of the subsequent business scheduling moment to obtain multiple initial division ranges corresponding to the subsequent business scheduling moment; determine the target terminal at the boundary position within each initial division range; predict the moving trajectory of the target terminal; determine whether the target terminal will move from the first initial division range where the target terminal was originally located to the second initial division range within a set time period based on the movement trajectory; if so, adjust the first initial division range and the second initial division range to obtain the final adjusted division range.

10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 8 is executed.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is executed.

12. A computer program product, characterized in that The method comprises computer program instructions, and when the computer program instructions are read and executed by a processor, the method according to any one of claims 1 to 8 is executed.

Images