Beam scanning timing matching method, device and computer-readable storage medium

Abstract

The present application discloses a beam scanning timing matching method, apparatus, and computer-readable storage medium. The method includes: obtaining the number of current users communicating with a satellite in multiple beam positions corresponding to a beam at a first moment; obtaining the number of mobile users communicating with the satellite between the multiple beam positions within a predetermined time period starting from the first moment; using the multiple beam positions as multiple graph nodes and constructing a first graph structure based on the corresponding number of current users and number of mobile users; determining the scanning time corresponding to each beam position based on the first graph structure using a timing prediction model, wherein the scanning time indicates the duration of the beam scanning each beam position in the next time period predicted by the timing prediction model; and matching a preset timing plan with the scanning time to determine a final timing plan that matches the scanning time.

Description

Technical Field

[0001] The present application relates to the field of satellite technology, and in particular to a beam scanning timing matching method, device, and computer-readable storage medium. Background Art

[0002] In sparsely populated areas, such as vast expanses like the Gobi Desert or grasslands, satellite communication systems provide services to users through beam scanning. Typically, satellites count the number of users requiring communication services at each beam position within a specific area and allocate resources for beam scanning accordingly. However, due to the high mobility of users, they may move rapidly from one beam position to another. In this dynamic environment, if beams are still allocated and scanned based on the last count of users, some beam positions currently without users may be overserved, while other beam positions with user needs may not receive sufficient attention, resulting in uneven distribution of beam scanning resources for each beam position.

[0003] With respect to the technical problem of uneven allocation of beam resources caused by user mobility in satellite communications in the above-mentioned prior art, no effective solution has been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a beam scanning timing matching method, apparatus, and computer-readable storage medium to at least solve the technical problem of uneven beam resource allocation caused by user mobility in satellite communications in the prior art.

[0005] According to one aspect of an embodiment of the present application, a beam scanning timing matching method is provided, including: obtaining the current number of users communicating with the satellite in multiple wave positions corresponding to the beam at a first moment; obtaining the number of mobile users between the multiple wave positions communicating with the satellite within a predetermined time period starting from the first moment; using the multiple wave positions as multiple graph nodes, and constructing a first graph structure according to the corresponding number of current users and the number of mobile users; determining the scanning time corresponding to each wave position according to the first graph structure through a timing prediction model, wherein the scanning time is used to indicate the time length of the beam scanning each wave position in the next time period predicted by the timing prediction model; and matching the preset timing plan with the scanning time to determine a final timing plan that matches the scanning time.

[0006] According to another aspect of an embodiment of the present application, a beam scanning timing matching device is also provided, including: a first quantity acquisition module, used to obtain the number of current users communicating with the satellite in multiple wave positions corresponding to the beam at a first moment; a second quantity acquisition module, used to obtain the number of mobile users between multiple wave positions communicating with the satellite within a predetermined time period starting from the first moment; a graph structure construction module, used to use multiple wave positions as multiple graph nodes, and construct a first graph structure according to the corresponding number of current users and number of mobile users; a timing determination module, used to determine the scanning time corresponding to each wave position according to the first graph structure through a timing prediction model, wherein the scanning time is used to indicate the time length of the beam scanning each wave position in the next time period predicted by the timing prediction model; and a scheme determination module, used to match a preset timing scheme with the scanning time, and determine a final timing scheme that matches the scanning time.

[0007] According to another aspect of an embodiment of the present application, a beam scanning timing matching device is also provided, including: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: obtaining the number of current users communicating with the satellite in multiple wave positions corresponding to the beam at a first moment; obtaining the number of mobile users between the multiple wave positions communicating with the satellite within a predetermined time period starting from the first moment; taking the multiple wave positions as multiple graph nodes, and constructing a first graph structure according to the corresponding number of current users and the number of mobile users; determining the scanning time corresponding to each wave position according to the first graph structure through a time prediction model, wherein the scanning time is used to indicate the time length of the beam scanning each wave position in the next time period predicted by the time prediction model; and matching the preset timing plan with the scanning time to determine a final timing plan that matches the scanning time.

[0008] According to another aspect of an embodiment of the present application, an integrated electronic system is also provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0009] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0010] In an embodiment of the present application, the satellite collects the current number of users and the number of mobile users at each wave position, and then determines the scanning time for each wave position based on the current number of users and the number of mobile users at the wave position to provide communication resources. Therefore, this technical solution not only takes into account the current number of users at the wave position, but also introduces the number of mobile users. Therefore, the scanning resources corresponding to each wave position can be adjusted according to the mobile user communication situation, so that each wave position obtains the appropriate scanning time, avoiding the situation where the beam scanning resources for each wave position are unevenly distributed. In addition, this technical solution obtains the number of mobile users and the current number of users between adjacent wave positions in real time and maps them to graph nodes and connecting edges to construct a graph structure with spatiotemporal correlation, which can comprehensively reflect the user distribution situation. Then, using the time prediction model, the scanning time for each wave position is output based on this graph structure, thereby achieving accurate resource scheduling. This solves the technical problem of uneven beam resource allocation caused by user mobility in satellite communications in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0012] Figure 1 This is a hardware structure block diagram for implementing the satellite according to Example 1 of the present application;

[0013] Figure 2 is a schematic diagram of a satellite communication system according to Example 1 of the present application;

[0014] Figure 3 1 is a flow chart of a beam scanning timing matching method according to the first aspect of Example 1 of the present application;

[0015] Figure 4 is a schematic diagram of the graph structure according to Example 1 of the present application;

[0016] Figure 5 is a schematic diagram of the second diagram structure according to Example 1 of the present application;

[0017] Figure 6 is a schematic diagram of a graph structure corresponding to a predetermined time period according to embodiment 1 of the present application;

[0018] Figure 7 is a schematic diagram of the graph neural network model according to Example 1 of the present application;

[0019] Figure 8 is a schematic diagram of the weight values of the graph structure according to Example 1 of the present application;

[0020] Figure 9 is a schematic diagram of the time usage prediction model according to Example 1 of the present application;

[0021] Figure 10 is a schematic diagram of a timing matching device for beam scanning according to embodiment 2 of the present application; and

[0022] Figure 11 This is a schematic diagram of a timing matching device for beam scanning according to Example 3 of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Example 1

[0026] Figure 1 A schematic diagram showing the hardware architecture of the satellite. Figure 1 As shown, the satellite 100 includes an integrated electronic system, which includes: a processor, a memory, a bus management module and a communication interface. The memory is connected to the processor, so that the processor can access the memory, read the program instructions stored in the memory, read data from the memory or write data to the memory. The bus management module is connected to the processor and is also connected to a bus such as a CAN bus. The processor can communicate with the onboard peripherals connected to the bus through the bus managed by the bus management module. In addition, the processor is also connected to devices such as cameras, star sensors, measurement and control transponders, and data transmission equipment via the communication interface. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0027] It should be noted that Figure 1 The one or more processors and / or other data processing circuits shown in the figure may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be fully or partially integrated into any of the other components of the computing device. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0028] Figure 1 The memory shown in the figure can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the beam scanning timing matching method in the embodiments of the present application. The processor executes the software programs and modules stored in the memory to perform various functional applications and data processing, thereby implementing the beam scanning timing matching method of the application described above. The memory can include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0029] It should be noted that, in some optional embodiments, the above Figure 1 The devices shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the apparatus described above.

[0030] Figure 2 Schematic diagram of the satellite communication system according to this embodiment. Figure 2 As shown, the system includes: a satellite 100.

[0031] Satellite 100 can use multiple beams to scan different positions in the ground coverage area at the same time. For the sake of convenience, this embodiment only uses one beam to illustrate the scanning of different positions in the ground coverage area. For example, the area covered by the beam corresponds to the position S 1~ S 7, so that the beam is used to align the wave position S 1~ S7 scans and can be directed to the covered wave position S 1~ S 7 provides satellite communication services. Thus, the satellite 100 can switch between corresponding beam positions through beams and provide satellite communication services for each corresponding beam position in a time-division manner.

[0032] In addition, for ease of understanding, this example only uses wave position S 1~ S 7 is used to illustrate the communication process between the satellite 100 and the wave position, but the number of the wave position is not limited to this and can be set according to actual conditions.

[0033] Under the above operating environment, according to the first aspect of this embodiment, a beam scanning timing matching method is provided. Figure 2 The satellite 100 shown in FIG. Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:

[0034] S302: Obtaining the current number of users communicating with the satellite in multiple beam positions corresponding to the beam at a first moment;

[0035] S304: Obtaining the number of mobile users between multiple wave positions communicating with the satellite within a predetermined time period starting from the first moment;

[0036] S306: Using the multiple wave positions as multiple graph nodes, and constructing a first graph structure according to the corresponding number of current users and number of mobile users;

[0037] S308: Determine the scanning time corresponding to each beam position according to the first graph structure using the time prediction model, wherein the scanning time indicates the time taken by the beam to scan each beam position in the next time period as predicted by the time prediction model; and

[0038] S310: Match the preset timing plan with the scanning time to determine a final timing plan that matches the scanning time.

[0039] Specifically, the beam of the satellite 100 continuously scans each wave position S1 to S7 within the coverage area of the ground within n predetermined time periods before the current time, thereby providing satellite communication services to users at each wave position S1 to S7. Among the n predetermined time periods, the i-th predetermined time period includes the first moment t i,1 and the second moment t at the end time i,2 , i=1~n. For example, the first moment of the first scheduled period is t 1,1 , the second moment is t 1,2 ; The first moment of the second scheduled period is t 2,1 , the second moment is t2,2 ; ...; The first moment of the nth scheduled period is t n,1 , the second moment is t n,2 . And for two adjacent scheduled time periods, the second moment of the previous scheduled time period is also the first moment of the next scheduled time period. For example, the second moment of the first scheduled time period is t 1,2 and the first moment t of the second scheduled period 2,1 is the same time; the second time t of the second scheduled period 2,2 and the first moment t of the third scheduled period 3,1 is the same time; the second time t of the n-1th scheduled period n-1,2 and the first moment t of the nth scheduled period n,1 It's the same moment.

[0040] Then the satellite 100 acquires the first time t i,1 , satellite 100 is each wave position S j The current number of users SI providing communication services j,i After that, satellite 100 counts the first moment t i,1 At the second moment t i,2 The number of mobile users SL between multiple wave positions (i.e., within the i-th predetermined time period) j,r,i . Among them SL j,r,i Indicates that in the i-th predetermined period, the wave position S j The user to wave position S r The number of users who moved. Where r = 1 to 7, j = 1 to 7, j ≠ r. For example, in the i-th predetermined period, the user at wave position S1 moved SL to wave position S2. 1,2,i For example, in the i-th predetermined period, the user of wave position S2 flows SL to wave position S1 2,1,i users.

[0041] Furthermore, the satellite 100 uses the wave positions S1 to S7 as graph nodes A1 to A7, and constructs connection edges L between the graph nodes A1 to A7 corresponding to adjacent wave positions. j,r . Where L j,r Indicates wave position S j The user flow to wave position S r There are two connection edges between two graph nodes, including an inflow connection edge and an outflow connection edge. For example, wave positions S1 and S2 are adjacent, so a connection edge L is constructed between the corresponding graph nodes A1 and A2. 1,2 and L 2,1 . Where L 1,2 Indicates that users at wave position S1 flow to wave position S2, L 2,1The user flow from wavelet S2 to wavelet S1 is shown in FIG1 . Thus, for A1, an incoming connection edge L is included to indicate that the user from wavelet S2 flows into wavelet S1. 2,1 , and the outflow connection edge L representing the user flowing from wave position S1 to wave position S2 1,2 For A2, it includes an inbound connection edge L for indicating that the user of wave position S1 flows into wave position S2 1,2 , and the outgoing connection edge L representing the user flowing from wave position S2 to wave position S1 2,1 .

[0042] Then the satellite 100 will be in the i-th predetermined period with the wave position S j The corresponding current number of users SI j,i As the graph node value AI of the corresponding graph node j,i , and the wave position S in the i-th predetermined time period j and S r The number of user flows between j,r,i As the corresponding graph node A j and A r The connecting edge L between j,r The connection edge value AL j,r,i Thus, the satellite 100 connects each adjacent graph node through the connection edges between each other, and determines the corresponding graph node value and connection edge value, thereby constructing a first graph structure.

[0043] Furthermore, the satellite 100 is pre-configured with a time prediction model for predicting the duration of the beam scanning of each beam position in the next period. Thus, the satellite 100 inputs the first graph structure into the time prediction model, processes the first graph structure through the time prediction model, and determines the scanning time Q corresponding to each beam position: [q1, q1, ..., q7] T , where q j Indicates the wave position S j The scanning time is used to indicate the time taken by the time prediction model to scan each position of the beam in the next period.

[0044] Furthermore, the satellite 100 is pre-set with a plurality of timing schemes for scanning each wave position, so that the satellite 100 outputs the scanning time Q=[q1,q1,...,q7] output by the timing prediction model. T With each time plan G x =[g 1,x ,g 2,x ,...,g 7,x ] T Match to determine the scan time Q=[q1,q1,...,q7] T The best matching time plan is taken as the final time plan. xIndicates the x-th preset time plan. g j,x Represents the wave position S in the x-th time plan j Thus, in the next period, the beam of satellite 100 scans each position with the final timing plan.

[0045] As described in the background, satellite communication systems provide services to users in sparsely populated areas, such as vast expanses like the Gobi Desert or grasslands, through beam scanning. Typically, satellites count the number of users requiring communication services at each beam location within a specific area and allocate resources for beam scanning accordingly. However, due to the high mobility of users, they may move rapidly from one beam location to another. In this dynamic environment, if beams are still allocated and scanned based on the last count of users, some beam locations currently without users may be overserved, while other beam locations with user needs may not receive sufficient attention, resulting in uneven distribution of scanning resources across beam locations.

[0046] To address the technical issues described above, through the technical solutions of the embodiments of the present application, the satellite collects the current number of users and the number of mobile users at each beam position, thereby determining the scanning time for each beam position based on the current and mobile user numbers of the beam position to provide communication resources. This technical solution not only takes into account the current number of users at the beam position, but also incorporates the number of mobile users. This allows the scanning resources corresponding to each beam position to be adjusted based on the mobile user communication situation, ensuring that each beam position receives the appropriate scanning time, thereby avoiding uneven distribution of scanning resources for each beam position. Furthermore, this technical solution obtains the number of mobile users and current users between adjacent beam positions in real time and maps them to graph nodes and connecting edges, constructing a graph structure with spatiotemporal correlation that can comprehensively reflect user distribution. A time prediction model is then used to output the scanning time for each beam position based on this graph structure, thereby achieving precise resource scheduling. This solves the technical problem of uneven beam resource allocation caused by user mobility in satellite communications, which exists in the prior art.

[0047] Optionally, multiple wave positions are used as multiple graph nodes, and the operation of constructing a first graph structure according to the corresponding number of current users and the number of mobile users includes: using the current number of users as the graph node values of multiple graph nodes, and using the number of mobile users as the connection edge value of the connection edges between the corresponding graph nodes; connecting adjacent graph nodes through connecting edges to generate a second graph structure with graph node values and connection edge values; and processing the second graph structure through a graph neural network model to generate a first graph structure.

[0048] Specifically, the satellite 100 will be in the ith predetermined period and the wave position S jThe corresponding current number of users SI j,i As the graph node value AI of the corresponding graph node j,i , and the wave position S in the i-th predetermined time period j and S r The number of user flows between j,r,i As the connecting edges L of the corresponding graph nodes j,r The connection edge value AL j,r,i Thus, the satellite 100 connects each adjacent graph node through the connection edges between each other, and determines the corresponding graph node value and connection edge value, thereby constructing Figure 4 and Figure 5 The second graph structure SWA shown i . Among them, reference Figure 6 As shown, SWA i represents the second graph structure corresponding to the i-th predetermined time period.

[0049] Furthermore, the satellite 100 is pre-set with a graph neural network model, so that the second graph structure is input into the graph neural network model, and the second graph structure is processed by the graph neural network model to output the corresponding first graph structure.

[0050] Therefore, this technical solution processes the graph structure through a graph neural network model, thereby mining complex topological relationships and semantic features, and accurately capturing the spatiotemporal correlation of cross-wavelength user flows.

[0051] Optionally, the operation of processing the second graph structure through the graph neural network model to generate the first graph structure includes: performing a convolution operation on the second graph structure through the graph convolution module in the graph neural network model to generate the first graph structure.

[0052] Specifically, refer to Figure 7 As shown in the figure, the graph neural network model is equipped with m graph convolution modules, including graph convolution module 1 to graph convolution module m.

[0053] Satellite 100 sends the second image structure SWA i Input the graph neural network model, and the graph neural network model will receive the second graph structure SWA i Input graph convolution module 1, and update the second graph structure SWA according to the graph node weight value and the connection edge weight value through graph convolution module 1 i The graph node values and connection edge values in , thereby generating a graph structure SWA i '.

[0054] More specifically, for updating the graph node value, the graph convolution module 1 obtains each graph node A j The graph node weight value w j,1 , and each graph node A jThe corresponding connection edge weight value w j,r,1 . The graph node weight value w j,1 For graph node A j , the graph node weight value of graph convolution module 1. Connection edge weight w j,r,1 For the connecting edge L j,r , the connection edge weight value of the graph convolution module 1. Thus, the graph convolution module 1 calculates the connection edge weight value of the graph node A according to the connection edge weight value of the graph convolution module 1. j Graph node value AI j,i and the graph node weight w j,1 , and graph node A j The corresponding connection edge value and connection edge weight value are updated to update the graph node A j Graph node value AI j,i , thereby generating the updated graph node A j Graph node value AI j,i '.

[0055] refer to Figure 8 As shown, for example, for graph node A1, graph convolution module 1 obtains graph node value AI of graph node A1 1,i And the corresponding graph node weight value w 1,1 . And the connection edges associated with graph node A1 include L 1,2 , L 2,1 , L 3,1 , L 1,3 , L 1,4 and L 4,1 . Thus, the graph convolution module 1 obtains the connection edge L 1,2 The connection edge value AL 1,2,i And the connecting edge weight value w 1,2,1 , connecting edge L 2,1 The connection edge value AL 2,1,i And the connecting edge weight value w 2,1,1 , connecting edge L 3,1 The connection edge value AL 3,1,i And the connecting edge weight value w 3,1,1 , connecting edge L 1,3 The connection edge value AL 1,3,i And the connecting edge weight value w 1,3,1 , connecting edge L 1,4 The connection edge value AL 1,4,i And the connecting edge weight value w 1,4,1 , connecting edge L 4,1 The connection edge value AL 4,1,i And the connecting edge weight value w 4,1,1 .

[0056] Then the graph convolution module 1 performs the graph node value AI according to the graph node value, graph node weight value, corresponding connection edge value and connection edge weight value of the graph node A1.1,i Update and generate graph node value AI 1,i ':

[0057] AI 1,i '=AI 1,i w 1,1 +AL 1,2,i w 1,2,1 +AL 2,1,i w 2,1,1 +AL 1,3,i w 1,3,1 +AL 3,1,i w 3,1,1 +AL 1,4,i w 1,4,1 +AL 4,1,i w 4,1,1 .

[0058] Thus, the graph convolution module 1 can update and generate the graph node values AI of other graph nodes A2~A7 according to the above-mentioned method of updating the graph node value of A1. 2,i '~AI 7,i ', no further details will be given here.

[0059] Furthermore, for the update of the connection edge, the graph convolution module 1 obtains each connection edge L j,r The corresponding weight value w j,r,1 , and each connecting edge L j,r The graph node weight value w of the corresponding graph node j,1 . The graph node weight value w j,1 For graph node A j , the graph node weight value of graph convolution module 1. The connection edge weight value w j,r,1 For the connecting edge L j,r , the connection edge weight value of the graph convolution module 1. Thus, the graph convolution module 1 calculates the connection edge weight value according to each connection edge L j,r The connection edge weight value w j,r,1 , and the connecting edge L j,r The graph node weight value of the corresponding graph node, update the connection edge L j,r The connection edge value AL j,r,i , thereby generating the updated connection edge L j,r The connection edge value AL j,r,i '.

[0060] For example, for the connecting edge L 1,2 , graph convolution module 1 obtains the connection edge L 1,2The connection edge value AL 1,2,i and the connecting edge weight w 1,2,1 . And connected with edge L 1,2 The relevant graph nodes include A1 and A2. Thus, the graph convolution module 1 obtains the graph node value AI of the graph node A1 1,i and the graph node weight w 1,1 , graph node value AI of graph node A2 2,i and the graph node weight w 2,1 .

[0061] Then the graph convolution module 1 is connected according to the edge L 1,2 The connection edge value AL 1,2,i , the connection edge weight value w 1,2,1 , the corresponding graph node value and graph node weight value, the connection edge value AL 1,2,i Update and generate connection edge value AL 1,2,i ':

[0062] AL 1,2,i '=AL 1,2,i w 1,2,1 +AI 1,i w 1,1 +AI 2,i w 2,1 .

[0063] Thus, the graph convolution module 1 can update the connection edge L according to the above 1,2 The connection edge value method of is used to update and generate the connection edge values of other connection edges, which will not be described in detail here.

[0064] Furthermore, the graph convolution module 1 generates graph node A j Graph node value AI j,i ' and connecting edge L j,r The connection edge value AL j,r,i 'Afterwards, according to the graph node A j , the corresponding graph node value AI j,i ', connecting edge L j,r and the corresponding connection edge value AL j,r,i 'Build graph structure SWA i '. Thus the graph structure SWA i 'Include graph node value as AI j,i 'Graph node A j And the connecting edge value is AL j,r,i 'Connecting edge L j,r .

[0065] Furthermore, the graph neural network model transforms the graph structure SWA output by the graph convolution module 1 i'Input graph convolution module 2, graph convolution module 2 updates the graph structure SWA according to the graph node weight value and the connection edge weight value i 'The graph node values and connection edge values in the graph are used to generate the graph structure .

[0066] More specifically, for updating the graph node value, the graph convolution module 2 obtains each graph node A j The graph node weight value w j,2 , and each graph node A j The corresponding connection edge weight value w j,r,2 . The graph node weight value w j,2 For graph node A j , the graph node weight value of graph convolution module 2. Connection edge weight w j,r,2 For the connecting edge L j,r , the connection edge weight value of the graph convolution module 2. Thus, the graph convolution module 2 calculates the connection edge weight value of the graph node A according to the connection edge weight value of the graph convolution module 2. j Graph node value AI j,i 'And the graph node weight value w j,2 , and graph node A j The corresponding connection edge value and connection edge weight value are updated to update the graph node A j Graph node value AI j,i ', thereby generating the updated graph node A j The graph node value of .

[0067] For example, for graph node A1, graph convolution module 2 obtains the graph node value AI of graph node A1 1,i 'And the corresponding graph node weight value w 1,2 . And the connection edges associated with graph node A1 include L 1,2 , L 2,1 , L 3,1 , L 1,3 , L 1,4 and L 4,1 . Thus, the graph convolution module 2 obtains the connection edge L 1,2 The connection edge value AL 1,2,i 'And the connecting edge weight value w 1,2,2 , connecting edge L 2,1 The connection edge value AL 2,1,i 'And the connecting edge weight value w 2,1,2 , connecting edge L 3,1 The connection edge value AL 3,1,i 'And the connecting edge weight value w 3,1,2 , connecting edge L 1,3 The connection edge value AL 1,3,i 'And the connecting edge weight value w 1,3,2 , connecting edge L1,4 The connection edge value AL 1,4,i 'And the connecting edge weight value w 1,4,2 , connecting edge L 4,1 The connection edge value AL 4,1,i 'And the connecting edge weight value w 4,1,2 .

[0068] The graph convolution module 2 performs convolution on the graph node value AI according to the graph node value, graph node weight value, corresponding connection edge value and connection edge weight value of the graph node A1. 1,i 'Update and generate graph node value AI 1,i '':

[0069] AI 1,i ''=AI 1,i ' w 1,2 +AL 1,2,i ' w 1,2,2 +AL 2,1,i ' w 2,1,2 +AL 1,3,i ' w 1,3,2 +AL 3,1,i ' w 3,1,2 +AL 1,4,i ' w 1,4,2 +AL 4,1,i ' w 4,1,2 .

[0070] Thus, the graph convolution module 2 can update and generate the graph node values AI of other graph nodes A2~A7 according to the above-mentioned method of updating the graph node value of A1. 2,i ''~AI 7,i '', no further details will be given here.

[0071] Furthermore, for the update of the connection edge, the graph convolution module 2 obtains each connection edge L j,r The corresponding weight value w j,r,2 , and each connecting edge L j,r The graph node weight value w of the corresponding graph node j,2 . The graph node weight value w j,2 For graph node A j , the graph node weight value of graph convolution module 2. Connection edge weight w j,r,2 For the connecting edge L j,r , the connection edge weight value of the graph convolution module 2. Thus, the graph convolution module 2 calculates the connection edge weight value according to each connection edge L j,r The connection edge weight value w j,r,2, and the connecting edge L j,r The graph node weight value of the corresponding graph node, update the connection edge L j,r The connection edge value AL j,r,i ', thereby generating the updated connection edge L j,r The connection edge value AL j,r,i ''.

[0072] For example, for the connecting edge L 1,2 , graph convolution module 2 obtains the connection edge L 1,2 The connection edge value AL 1,2,i ' and the connecting edge weight value w 1,2,2 . And connected with edge L 1,2 The relevant graph nodes include A1 and A2. Thus, the graph convolution module 2 obtains the graph node value AI of the graph node A1 1,i 'And the graph node weight value w 1,2 , graph node value AI of graph node A2 2,i 'And the graph node weight value w 2,2 .

[0073] Graph convolution module 2 is based on the connection edge L 1,2 The connection edge value AL 1,2,i ', connection edge weight value w 1,2,2 , the corresponding graph node value and graph node weight value, the connection edge value AL 1,2,i 'Update and generate connection edge value AL 1,2,i '':

[0074] AL 1,2,i ''=AL 1,2,i ' w 1,2,2 +AI 1,i ' w 1,2 +AI 2,i ' w 2,2 .

[0075] Thus, the graph convolution module 2 can update the connection edge L according to the above 1,2 The connection edge value method of is used to update and generate the connection edge values of other connection edges, which will not be described in detail here.

[0076] Furthermore, the graph convolution module 2 generates graph node A j Graph node value AI j,i '' and connecting edge L j,r The connection edge value AL j,r,i ''After that, according to the graph node A j , the corresponding graph node value AI j,i '', connecting edge L j,r and the corresponding connection edge value ALj,r,i ''Building graph structure SWA i ''. Thus the graph structure SWA i ''Including graph node value is AI j,i '' graph node A j And the connecting edge value is AL j,r,i '' connecting edge L j,r .

[0077] Similarly, graph convolution module 3 to graph convolution module m update the graph structure according to the method of graph convolution module 1 and graph convolution module 2, and use the corresponding graph node weight values and connection edge weight values to update the graph structure in turn, so that the graph convolution module m finally outputs the first graph structure SWA i '''.

[0078] Therefore, this technical solution extracts features from the graph structure through multiple graph convolution modules, thereby capturing deeper feature information and making the obtained feature information more accurate.

[0079] Optionally, the operation of determining the scanning time corresponding to each wave position according to the first graph structure through the time prediction model includes: splicing the feature vectors corresponding to the first graph structure corresponding to multiple predetermined time periods to generate fused feature information; and determining the scanning time corresponding to each wave position according to the fused feature information through the time prediction model.

[0080] Specifically, the graph neural network model sequentially outputs the first graph structure SWA i ''' (i.e., SWA1'''~SWA n ''') corresponding eigenvector. i ''' represents the first graph structure corresponding to the i-th predetermined period. Then the satellite 100 converts n feature vectors (ie, SWA1'''~SWA n '''corresponding feature vectors) are spliced to generate fused feature information E.

[0081] Furthermore, the satellite 100 inputs the fused feature information into the time prediction model, processes the fused feature information through the time prediction model, and outputs the scanning time corresponding to each wave position.

[0082] This technical solution thus concatenates the feature vectors for all time periods to generate a fused feature map containing information from all time periods. This allows the time-of-use prediction model to simultaneously consider the characteristics of different time periods, thereby more comprehensively reflecting the actual situation. The time-of-use prediction model then outputs the scanning time for each wave position within the corresponding time period based on this fused feature map. Because the fused feature map already includes comprehensive information from multiple time periods, the prediction results are more accurate and reliable.

[0083] Optionally, the operation of determining the scanning time corresponding to each wave position based on the fused feature information is performed through the time prediction model, including: performing a convolution operation on the fused feature information through the convolution layer of the time prediction model to generate corresponding first feature information; performing feature extraction on the first feature information through the fully connected layer to generate second feature information; and classifying the second feature information through a classifier to generate the scanning time corresponding to each wave position.

[0084] Specifically, refer to Figure 9 As shown in Figure 2, the time prediction model includes a convolutional layer, a fully connected layer, and a classifier.

[0085] The satellite 100 inputs the fused feature information E into the usage time prediction model. The usage time prediction model inputs the received fused feature information into a convolution layer, performs a convolution operation on the fused feature information through the convolution layer, and outputs first feature information.

[0086] Furthermore, the time prediction model inputs the first feature information into a fully connected layer, performs a feature extraction operation on the first feature information through the fully connected layer, and outputs second feature information;

[0087] Furthermore, the time prediction model inputs the second feature information into the classifier, and the classifier classifies the second feature information to generate the scanning time Q=[q1,q1,...,q7] corresponding to each wave position. T , where q j Indicates the beam position S j Scan time.

[0088] Therefore, this technical solution uses the time prediction model to process the fused feature information, and realizes the accurate prediction of the time required for the satellite to scan different wave positions in different time periods.

[0089] Optionally, the preset timing plan is compared with the scanning time to determine the final timing plan that matches the scanning time, including: calculating the distance between the scanning time and the preset timing plan respectively, and taking the timing plan with the smallest distance as the final timing plan that matches the scanning time.

[0090] Specifically, the satellite 100 is pre-set with multiple timing schemes for scanning each wave position, so that the satellite 100 outputs the scanning time Q=[q1,q1,...,q7] output by the timing prediction model. T With each time plan G x =[g 1,x ,g 2,x ,...,g 7,x ] T Perform matching, for example, calculate the scan time Q=[q1,q1,...,q7] TWith each time plan G x =[g 1,x ,g 2,x ,...,g 7,x ] T The distance d x , where the distance d of satellite 100 is calculated by the following formula x :

[0091] .

[0092] Then the satellite 100 will be multiple distances d x Compare and thus from G x =[g 1,x ,g 2,x ,...,g 7,x ] T The timing plan with the smallest distance from the scan time Q is selected as the final timing plan that matches the scan time.

[0093] Therefore, this technical solution compares the distance between the scanning time and each preset solution and selects the solution with the smallest distance as the final time solution, ensuring a high degree of fit between actual needs and resource allocation.

[0094] In addition, according to a second aspect of this embodiment, an integrated electronic system is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0095] In addition, according to a third aspect of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0096] According to this embodiment, the satellite collects the number of current users and mobile users at each beam position. Based on this number, the scanning time for each beam position is determined to provide communication resources. This technical solution not only considers the current number of users at the beam position but also the number of mobile users. This allows the scanning resources corresponding to each beam position to be adjusted based on the mobile user communication situation, ensuring that each beam position receives the appropriate scanning time, thus avoiding uneven distribution of scanning resources across beam positions. Furthermore, this technical solution obtains the number of mobile users and current users between adjacent beam positions in real time and maps them to graph nodes and connecting edges, constructing a graph structure with spatiotemporal correlation that comprehensively reflects user distribution. A time prediction model is then used to output the scanning time for each beam position based on this graph structure, thereby achieving precise resource scheduling. This solves the technical problem of uneven beam resource allocation caused by user mobility in satellite communications, which exists in the prior art.

[0097] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0098] Through the description of the above embodiments, those skilled in the art will clearly understand that the methods according to the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0099] Example 2

[0100] Figure 10 FIG2 shows a beam scanning timing matching device 1000 according to this embodiment, which corresponds to the method according to the first aspect of embodiment 1. Figure 10 As shown, the device 1000 includes: a first quantity acquisition module 1010, used to obtain the number of current users communicating with the satellite in multiple wave positions corresponding to the beam at a first moment; a second quantity acquisition module 1020, used to obtain the number of mobile users between the multiple wave positions communicating with the satellite within a predetermined time period starting from the first moment; a graph structure construction module 1030, used to use the multiple wave positions as multiple graph nodes, and construct a first graph structure according to the corresponding number of current users and the number of mobile users; a time determination module 1040, used to determine the scanning time corresponding to each wave position according to the first graph structure through a time prediction model, wherein the scanning time is used to indicate the time length predicted by the time prediction model for the beam to scan each wave position in the next time period; and a scheme determination module 1050, used to match the preset timing scheme with the scanning time, and determine a final timing scheme that matches the scanning time.

[0101] Optionally, the graph structure construction module 1030 includes: a first determination submodule, used to use the current number of users as the graph node value of multiple graph nodes, and the number of mobile users as the connection edge value of the connection edge between the corresponding graph nodes; a first generation submodule, used to connect adjacent graph nodes through connection edges to generate a second graph structure with graph node values and connection edge values; and a second generation submodule, used to process the second graph structure through a graph neural network model to generate a first graph structure.

[0102] Optionally, the second generation submodule includes: a first generation unit, used to perform a convolution operation on the second graph structure through a graph convolution module in the graph neural network model to generate a first graph structure.

[0103] Optionally, the timing determination module 1040 includes: a third generation submodule, used to splice the feature vectors corresponding to the first graph structure corresponding to multiple predetermined time periods to generate fused feature information; and a second determination submodule, used to determine the scanning time corresponding to each wave position based on the fused feature information through a timing prediction model.

[0104] Optionally, the second determination submodule includes: a second generation unit, used to perform a convolution operation on the fused feature information through the convolution layer of the time prediction model to generate corresponding first feature information; a third generation unit, used to perform feature extraction on the first feature information through the fully connected layer to generate second feature information; and a fourth generation unit, used to classify the second feature information through a classifier to generate scanning times corresponding to each wave position.

[0105] Optionally, the solution determination module 1050 includes: a calculation submodule, configured to calculate the distances between the scanning times and the preset timing solutions, and use the timing solution with the smallest distance as the final timing solution that matches the scanning time.

[0106] According to this embodiment, the satellite collects the number of current users and mobile users at each beam position. Based on this number, the scanning time for each beam position is determined to provide communication resources. This technical solution not only considers the current number of users at the beam position but also the number of mobile users. This allows the scanning resources corresponding to each beam position to be adjusted based on the mobile user communication situation, ensuring that each beam position receives the appropriate scanning time, thus avoiding uneven distribution of scanning resources across beam positions. Furthermore, this technical solution obtains the number of mobile users and current users between adjacent beam positions in real time and maps them to graph nodes and connecting edges, constructing a graph structure with spatiotemporal correlation that comprehensively reflects user distribution. A time prediction model is then used to output the scanning time for each beam position based on this graph structure, thereby achieving precise resource scheduling. This solves the technical problem of uneven beam resource allocation caused by user mobility in satellite communications, which exists in the prior art.

[0107] Example 3

[0108] Figure 11 FIG2 shows a beam scanning timing matching device 1100 according to this embodiment, which corresponds to the method according to the first aspect of embodiment 1. Figure 11 As shown, the device 1100 includes: a processor 1110; and a memory 1120, which is connected to the processor 1110 and is used to provide the processor 1110 with instructions for processing the following processing steps: obtaining the number of current users communicating with the satellite in multiple wave positions corresponding to the beam at a first moment; obtaining the number of mobile users between the multiple wave positions communicating with the satellite within a predetermined time period starting from the first moment; taking the multiple wave positions as multiple graph nodes, and constructing a first graph structure according to the corresponding number of current users and the number of mobile users; determining the scanning time corresponding to each wave position according to the first graph structure through a time prediction model, wherein the scanning time is used to indicate the time taken by the time prediction model to scan each wave position in the next time period; and matching the preset timing plan with the scanning time to determine a final timing plan that matches the scanning time.

[0109] Optionally, multiple wave positions are used as multiple graph nodes, and the operation of constructing a first graph structure according to the corresponding number of current users and the number of mobile users includes: using the current number of users as the graph node values of multiple graph nodes, and using the number of mobile users as the connection edge value of the connection edges between the corresponding graph nodes; connecting adjacent graph nodes through connecting edges to generate a second graph structure with graph node values and connection edge values; and processing the second graph structure through a graph neural network model to generate a first graph structure.

[0110] Optionally, the operation of processing the second graph structure through the graph neural network model to generate the first graph structure includes: performing a convolution operation on the second graph structure through the graph convolution module in the graph neural network model to generate the first graph structure.

[0111] Optionally, the operation of determining the scanning time corresponding to each wave position according to the first graph structure through the time prediction model includes: splicing the feature vectors corresponding to the first graph structure corresponding to multiple predetermined time periods to generate fused feature information; and determining the scanning time corresponding to each wave position according to the fused feature information through the time prediction model.

[0112] Optionally, the operation of determining the scanning time corresponding to each wave position based on the fused feature information is performed through the time prediction model, including: performing a convolution operation on the fused feature information through the convolution layer of the time prediction model to generate corresponding first feature information; performing feature extraction on the first feature information through the fully connected layer to generate second feature information; and classifying the second feature information through a classifier to generate the scanning time corresponding to each wave position.

[0113] Optionally, the preset timing plan is matched with the scanning time to determine the final timing plan that matches the scanning time, including: calculating the distance between the scanning time and the preset timing plan respectively, and taking the timing plan with the smallest distance as the final timing plan that matches the scanning time.

[0114] According to this embodiment, the satellite collects the number of current users and mobile users at each beam position. Based on this number, the scanning time for each beam position is determined to provide communication resources. This technical solution not only considers the current number of users at the beam position but also the number of mobile users. This allows the scanning resources corresponding to each beam position to be adjusted based on the mobile user communication situation, ensuring that each beam position receives the appropriate scanning time, thus avoiding uneven distribution of scanning resources across beam positions. Furthermore, this technical solution obtains the number of mobile users and current users between adjacent beam positions in real time and maps them to graph nodes and connecting edges, constructing a graph structure with spatiotemporal correlation that comprehensively reflects user distribution. A time prediction model is then used to output the scanning time for each beam position based on this graph structure, thereby achieving precise resource scheduling. This solves the technical problem of uneven beam resource allocation caused by user mobility in satellite communications, which exists in the prior art.

[0115] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0116] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0118] The units described as separate components may or may not be physically separate, and the components shown as units 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0119] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0120] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), a mobile hard drive, a magnetic disk, or an optical disk.

[0121] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A beam scanning timing matching method, characterized in that: include: Obtaining, at a first moment, the number of current users communicating with the satellite in a plurality of beam positions corresponding to the beam; Obtaining the number of mobile users between the plurality of beam positions communicating with the satellite within a predetermined time period starting from the first moment; Taking the multiple wave locations as multiple graph nodes, and constructing a first graph structure according to the number of current users of the multiple wave locations and the number of mobile users between the multiple wave locations; Determining, by means of a time prediction model and based on the first graph structure, a scanning time corresponding to each beam position, wherein the scanning time indicates a duration predicted by the time prediction model for the beam to scan each beam position in the next time period; as well as Matching the preset timing plan with the scanning time to determine a final timing plan that matches the scanning time, and wherein, The operation of constructing a first graph structure by using the multiple wave positions as multiple graph nodes and according to the corresponding number of current users and the number of mobile users includes: using the number of current users as the graph node values of the multiple graph nodes, and using the number of mobile users as the connection edge value of the connection edge between the corresponding graph nodes; connecting adjacent graph nodes through the connection edge to generate a second graph structure having the graph node value and the connection edge value; and processing the second graph structure through a graph neural network model to generate the first graph structure, and wherein, The operation of processing the second graph structure through a graph neural network model to generate the first graph structure includes: performing a convolution operation on the second graph structure through a graph convolution module in the graph neural network model to generate the first graph structure, and wherein, The operation of matching the preset timing plan with the scanning timing and determining the final timing plan that matches the scanning timing includes: calculating the distance between the scanning timing and the preset timing plan respectively, and taking the timing plan with the smallest distance as the final timing plan that matches the scanning timing.

2. The method according to claim 1, characterized in that The operation of determining the scanning time corresponding to each wave position according to the first graph structure using the time prediction model includes: Performing a splicing operation on the feature vectors corresponding to the first graph structure corresponding to the plurality of predetermined time periods to generate fused feature information; and The scanning time corresponding to each wave position is determined by the time prediction model according to the fusion feature information.

3. The method according to claim 2, characterized in that The operation of determining the scanning time corresponding to each of the wave positions according to the fusion feature information by using the time prediction model includes: Performing a convolution operation on the fused feature information through a convolution layer of the time usage prediction model to generate corresponding first feature information; Performing feature extraction on the first feature information through a fully connected layer to generate second feature information; and The second feature information is classified by a classifier to generate scanning times corresponding to the respective wave positions.

4. A beam scanning timing matching device, characterized in that: include: A first number acquisition module is used to acquire, at a first moment, the number of current users communicating with the satellite in multiple beam positions corresponding to the beam; A second number acquisition module is configured to acquire the number of mobile users between the plurality of wave positions communicating with the satellite within a predetermined period starting from the first moment; A graph structure building module, configured to use the plurality of wave locations as a plurality of graph nodes and build a first graph structure according to the number of current users of the plurality of wave locations and the number of mobile users between the plurality of wave locations; a time determination module, configured to determine a scanning time corresponding to each beam position according to the first graph structure using a time prediction model, wherein the scanning time indicates a duration predicted by the time prediction model for the beam to scan each beam position in the next time period; as well as A scheme determination module is used to match a preset timing scheme with the scanning timing, determine a final timing scheme that matches the scanning timing, and wherein, The graph structure construction module includes: a first determination submodule, used to: use the current number of users as the graph node value of the multiple graph nodes, and use the number of mobile users as the connection edge value of the connection edge between the corresponding graph nodes; a first generation submodule, used to connect adjacent graph nodes through the connection edge to generate a second graph structure with the graph node value and the connection edge value; and a second generation submodule, used to process the second graph structure through a graph neural network model to generate the first graph structure, and wherein, The second generation submodule includes: a first generation unit, configured to perform a convolution operation on the second graph structure through a graph convolution module in the graph neural network model to generate the first graph structure, and wherein, The scheme determination module includes: a calculation submodule, which is used to calculate the distance between the scanning time and the preset timing schemes, and use the timing scheme with the smallest distance as the final timing scheme matching the scanning time.

5. A timing matching device for beam scanning, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Obtaining, at a first moment, the number of current users communicating with the satellite in a plurality of beam positions corresponding to the beam; Obtaining the number of mobile users between the plurality of beam positions communicating with the satellite within a predetermined time period starting from the first moment; Taking the multiple wave locations as multiple graph nodes, and constructing a first graph structure according to the number of current users of the multiple wave locations and the number of mobile users between the multiple wave locations; Determining, by means of a time prediction model and based on the first graph structure, a scanning time corresponding to each beam position, wherein the scanning time indicates a duration predicted by the time prediction model for the beam to scan each beam position in the next time period; as well as Matching the preset timing plan with the scanning time to determine a final timing plan that matches the scanning time, and wherein, The operation of constructing a first graph structure by using the multiple wave positions as multiple graph nodes and according to the corresponding number of current users and the number of mobile users includes: using the number of current users as the graph node values of the multiple graph nodes, and using the number of mobile users as the connection edge value of the connection edge between the corresponding graph nodes; connecting adjacent graph nodes through the connection edge to generate a second graph structure having the graph node value and the connection edge value; and processing the second graph structure through a graph neural network model to generate the first graph structure, and wherein, The operation of processing the second graph structure through a graph neural network model to generate the first graph structure includes: performing a convolution operation on the second graph structure through a graph convolution module in the graph neural network model to generate the first graph structure, and wherein, The operation of matching the preset timing plan with the scanning timing and determining the final timing plan that matches the scanning timing includes: calculating the distance between the scanning timing and the preset timing plan respectively, and taking the timing plan with the smallest distance as the final timing plan that matches the scanning timing.

6. An integrated electronic system comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to claim 1.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images