Network topology control method based on holographic data and related equipment

Abstract

The invention provides a holographic data-based network topology control method and related equipment. The method comprises the following steps: receiving holographic data, determining a space-time fusion feature according to the holographic data, and determining a transmission path priority weight according to the space-time fusion feature; analyzing and processing the holographic data to obtain four-dimensional space-time coordinates, determining a three-dimensional density thermodynamic diagram of the ground base station according to the holographic data, and determining an optimal resource allocation strategy based on the three-dimensional density thermodynamic diagram; determining spatial fidelity and a multi-modal synchronization error of the holographic data, and determining a multi-objective optimization function based on the spatial fidelity and the multi-modal synchronization error; and determining a network topology control strategy according to the transmission path priority weight, the optimal resource allocation strategy and the multi-objective optimization function.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a network topology control method and related equipment based on holographic data. Background Technology

[0002] With the rapid development of holographic communication technology, immersive services based on 3D light field reconstruction and multimodal interaction are gradually being applied to various scenarios. However, there is a significant contradiction between the dynamic and heterogeneous network environment and the special requirements of holographic services, making it impossible to achieve precise adaptation between network resources and the 3D service space.

[0003] In view of this, how to achieve accurate matching between network resources and three-dimensional business space has become an urgent technical problem to be solved. Summary of the Invention

[0004] In view of this, the purpose of this disclosure is to propose a network topology control method and related equipment based on holographic data to solve or partially solve the above-mentioned technical problems.

[0005] To achieve the above objectives, the first aspect of this disclosure proposes a network topology control method based on holographic data, the method comprising: Upon receiving holographic data, determine spatiotemporal fusion features based on the holographic data, and determine transmission path priority weights based on the spatiotemporal fusion features; The holographic data is parsed to obtain four-dimensional spatiotemporal coordinates. Based on the holographic data, a three-dimensional density heat map of the ground base station is determined, and the optimal resource allocation strategy is determined based on the three-dimensional density heat map. Determine the spatial fidelity and multimodal synchronization error of the holographic data, and determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error; The network topology control strategy is determined based on the transmission path priority weight, the optimal resource allocation strategy, and the multi-objective optimization function.

[0006] Based on the same inventive concept, a second aspect of this disclosure proposes a network topology control device based on holographic data, comprising: The priority weight determination module is configured to receive holographic data, determine spatiotemporal fusion features based on the holographic data, and determine transmission path priority weights based on the spatiotemporal fusion features. The allocation strategy determination module is configured to parse and process the holographic data to obtain four-dimensional spatiotemporal coordinates, determine the three-dimensional density heat map of the ground base station based on the holographic data, and determine the optimal resource allocation strategy based on the three-dimensional density heat map. The optimization function determination module is configured to determine the spatial fidelity and multimodal synchronization error of the holographic data, and determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error; The control strategy determination module is configured to determine the network topology control strategy based on the transmission path priority weight, the optimal resource allocation strategy, and the multi-objective optimization function.

[0007] Based on the same inventive concept, a third aspect of this disclosure proposes an electronic device including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0008] Based on the same inventive concept, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium that stores computer instructions for causing a computer to perform the methods described above.

[0009] As described above, this disclosure provides a network topology control method and related equipment based on holographic data. Upon receiving holographic data, spatiotemporal fusion characteristics are determined, and transmission path priority weights are determined based on these characteristics. This enables the establishment of a real-time dynamic mapping mechanism between the spatial coordinates of service units and network topology parameters, allowing the network to understand the three-dimensional space of the holographic data and achieve precise matching between network resources and the three-dimensional service space. This fundamentally solves the dimensional mismatch problem by automatically allocating the highest priority transmission path through the determined transmission path priority weights. The holographic data is parsed to obtain four-dimensional spatiotemporal coordinates. A three-dimensional density heatmap of the ground base station is determined based on the holographic data, and the optimal resource allocation strategy is determined based on the three-dimensional density heatmap. This allows the states of all heterogeneous nodes to be transformed into a unified coordinate system, achieving precise alignment of resource supply and demand. The spatial fidelity and multimodal synchronization error of the holographic data are determined. A multi-objective optimization function is determined based on the spatial fidelity and multimodal synchronization error. This multi-objective optimization function is a quantitative evaluation system for multi-objective fusion, enabling optimization decisions to accurately match the multi-dimensional real needs of services. Determining network topology control strategies based on transmission path priority weights, optimal resource allocation strategies, and multi-objective optimization functions enables rapid decision-making for network topology control strategies. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in this disclosure or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of a network topology control method based on holographic data according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram of the structure of a network topology control device based on holographic data according to an embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0013] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0014] Based on the background description, with the rapid development of holographic communication technology, immersive services based on three-dimensional light field reconstruction and multimodal interaction are gradually being applied to high-value scenarios such as medical collaboration and industrial operation and maintenance. Holographic services achieve three-dimensional information presentation across physical spaces through precise spatial coordinate mapping and real-time data stream synchronization. This places unprecedentedly stringent requirements on communication networks: the need for continuous and stable transmission of multidimensional data streams containing depth information, and ensuring strict spatiotemporal consistency between different modal sensing signals. Traditional terrestrial networks face fundamental limitations in supporting such services; their planar topology is ill-suited to the three-dimensional spatial characteristics of holographic data streams, leading to problems such as decreased image reconstruction accuracy and disrupted interactive experiences.

[0015] The evolution of integrated air-space-ground networks provides new infrastructure support for wide-area coverage of holographic services. Theoretically, a three-dimensional transmission system built through satellite constellations, high-altitude platforms, and ground nodes can overcome geographical limitations to achieve full-area access. However, significant contradictions remain between the dynamic and heterogeneous network environment and the specific needs of holographic services: the periodic movement of satellite nodes conflicts with the spatial continuity requirements of holographic sessions, causing dynamic shifts in the three-dimensional coordinate reference system; the resource constraints of space-based platforms contradict the high-energy-efficiency transmission requirements of holographic data streams, affecting service continuity; and the tidal load characteristics of ground networks are difficult to match with the sudden access demands of holographic terminals, leading to fluctuations in service quality. These contradictions are particularly prominent in cross-air-space-ground collaborative scenarios. Current topology optimization methods often lack a deep understanding of the essential characteristics of holographic services, failing to achieve precise adaptation of network resources to the three-dimensional service space.

[0016] Current technological systems suffer from multiple shortcomings in addressing these challenges. Traditional network state awareness mechanisms only collect basic transmission parameters, failing to effectively capture the spatial correlation characteristics unique to holographic services, leading to a misalignment between resource allocation decisions and actual service requirements. A typical example is that in multi-view holographic video transmission, the network layer cannot recognize the continuity constraints of spatial coordinates, resulting in rendering gaps during viewpoint switching. While current topology optimization algorithms can respond to changes in node load, their two-dimensional optimization models suffer from a dimensional mismatch with the three-dimensional spatial distribution characteristics of holographic data streams, causing insufficient transmission stability of critical data paths. Furthermore, the dynamic access requirements of sudden holographic service flows clash sharply with the lag in network topology reconstruction, making it difficult to meet the rapid networking requirements in emergency scenarios.

[0017] As mentioned above, how to achieve accurate matching between network resources and three-dimensional business space has become an important research question.

[0018] Based on the above description, such as Figure 1 As shown in this embodiment, the network topology control method based on holographic data includes: Step 101: Receive holographic data, determine spatiotemporal fusion features based on the holographic data, and determine transmission path priority weights based on the spatiotemporal fusion features.

[0019] In practical implementation, a multimodal data stream spatial fingerprint extraction technology based on spatiotemporal joint coding is used to construct mapping rules between holographic service features and network transmission paths. Specifically, through deep packet inspection and spatiotemporal joint coding, key features are extracted from the original holographic data. For example, depth layers and haptic feedback signals are identified from the holographic data, and the spatial correlation between depth layers and haptic feedback signals is understood.

[0020] Feature fingerprints describe the encoding of spatial association patterns in data streams. Transmission path priority weights. It is the importance weight of different data streams on the network path, which is dynamically calculated based on feature fingerprints.

[0021] The calculated transmission path priority weights can serve as an important input feature for Graph Neural Network (GNN) models. When making routing decisions, GNNs not only consider physical attributes such as latency and bandwidth, but also take into account the transmission path priority weights at the service level, thereby intelligently selecting more stable and reliable transmission paths for critical holographic data (e.g., depth maps).

[0022] Step 102: The holographic data is parsed and processed to obtain four-dimensional spatiotemporal coordinates. The three-dimensional density heat map of the ground base station is determined based on the holographic data, and the optimal resource allocation strategy is determined based on the three-dimensional density heat map.

[0023] In practical implementation, a heterogeneous node spatiotemporal coding mapping technology based on a four-dimensional coordinate system is used to align and convert the resource status of air, space, and ground nodes with the requirements of holographic space. Specifically, the status of dynamic and heterogeneous network nodes such as satellites, drones, and ground stations is uniformly converted to the Earth-Centered Inertial Frame (ECI) to form a dynamic and unified four-dimensional spatiotemporal resource map.

[0024] Unified spatiotemporal coordinates of nodes represent the position and resource status of all network nodes in a unified coordinate system. 3D business density heatmap It is a demand distribution map generated based on the load and resource status of ground base stations.

[0025] A 3D service density heatmap is the foundation of GNN decision-making. GNN needs to know the entire network in order to optimize. The unified resource map is the source of attributes for the nodes and edges in the graph of the GNN model. For example, the location of nodes, resource status, and edge attributes such as distance and latency between nodes all come from this map.

[0026] Resource pre-locking technology requires knowledge of available resources (satellites, drones, etc.) within each grid, and this information is also provided by a unified resource map.

[0027] Step 103: Determine the spatial fidelity and multimodal synchronization error of the holographic data, and determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error.

[0028] In practical implementation, a quantitative evaluation system for spatial fidelity and service continuity is defined based on multi-objective fusion holographic QoS joint modeling technology. Specifically, the multi-objective optimization function defines a comprehensive evaluation system to quantify the service quality of holographic services, which not only focuses on latency and bandwidth, but also introduces holographic-specific indicators such as spatial fidelity (SFI) and multimodal synchronization error (MSE).

[0029] Multi-objective optimization function It is a mathematical formula that can calculate the current network service quality score.

[0030] The multi-objective optimization function is the core objective of the entire optimization decision-making process. The purpose of GNN's learning and inference is to find a network topology configuration that maximizes the score. In the framework of reinforcement learning, QoS can serve as a reward function, guiding the GNN policy network to make better decisions.

[0031] Step 104: Determine the network topology control strategy based on the transmission path priority weight, the optimal resource allocation strategy, and the multi-objective optimization function.

[0032] In practical implementation, spatiotemporal constraint-aware decision-making technology based on graph neural networks generates coordinated control commands for satellite-space-based-ground nodes. Specifically, this graph neural network-based spatiotemporal constraint-aware decision-making technology serves as the system's decision-making module, comprehensively utilizing all the aforementioned information to generate optimal topology control commands.

[0033] The input unified resource map is used as the network state, the input transmission path priority weight is used as the service requirement, and the input multi-objective optimization function QoS is used as the optimization objective.

[0034] Network topology control strategies include: coordinated control commands and correlation relationships. Coordinated control commands include: selecting which satellite link to use, activating which ground station to use, and adjusting which routing path to use, in order to form the optimal topology. Correlation relationships are a crucial step, consuming the output of the previous steps and generating the final general control strategy.

[0035] This disclosure addresses the technical bottlenecks mentioned in the background by proposing a holographic service-driven intelligent topology optimization method. It establishes a deep coupling mechanism between holographic service characteristics and network topology parameters by constructing a three-dimensional resource mapping model of a space-air-ground network. This method innovatively introduces a spatial coordinate-aware topology decision-making system, breaking through the dimensional limitations of traditional optimization models; it designs a multi-modal data flow synchronization guarantee strategy to solve the spatiotemporal consistency problem in heterogeneous network environments; and it develops a dynamically adaptive resource allocation algorithm to achieve a real-time balance between holographic service demands and network carrying capacity.

[0036] Through experimental simulation and actual system testing, the network topology optimization model of this disclosure can make decisions that are more in line with real-time network conditions, further ensuring low latency, high bandwidth and user service quality.

[0037] The holographic service feature-driven intelligent topology optimization technology disclosed in this embodiment effectively solves the adaptation problem between the needs of three-dimensional holographic services and dynamic heterogeneous resources in air-space-ground networks. By constructing a holographic data stream spatial feature modeling mechanism, it achieves real-time dynamic mapping between service three-dimensional spatial coordinates and network topology parameters for the first time, overcoming core problems such as depth information transmission distortion and poor multimodal stream synchronization caused by dimensional mismatch in traditional networks. At the same time, the topology self-optimization decision system based on multi-dimensional QoS constraints breaks through the contradiction between satellite-ground resource scheduling and the spatiotemporal continuity requirements of holographic services, significantly improving the service quality assurance capability of high-value holographic services. Compared with traditional solutions, this technology achieves breakthrough optimization in key indicators such as holographic spatial fidelity, burst service response speed, and cross-domain resource collaboration efficiency, providing reliable technical support for air-space-ground integrated networks to support holographic-level immersive services.

[0038] Through the above embodiments, holographic data is received, spatiotemporal fusion characteristics are determined based on the holographic data, and transmission path priority weights are determined based on these characteristics. This enables the establishment of a real-time dynamic mapping mechanism between the spatial coordinates of service units and network topology parameters based on holographic data. This allows the network to understand the three-dimensional space of the holographic data, achieving precise matching between network resources and the three-dimensional service space, fundamentally solving the dimensional mismatch problem. The highest priority transmission path is automatically allocated by determining the transmission path priority weights. The holographic data is parsed to obtain four-dimensional spatiotemporal coordinates. A three-dimensional density heatmap of the ground base station is determined based on the holographic data, and the optimal resource allocation strategy is determined based on the three-dimensional density heatmap. This allows the states of all heterogeneous nodes to be transformed into a unified coordinate system, achieving precise alignment of resource supply and demand. The spatial fidelity and multimodal synchronization error of the holographic data are determined. A multi-objective optimization function is determined based on the spatial fidelity and multimodal synchronization error. This multi-objective optimization function is a quantitative evaluation system for multi-objective fusion, enabling optimization decisions to accurately match the multi-dimensional real needs of services. Determining network topology control strategies based on transmission path priority weights, optimal resource allocation strategies, and multi-objective optimization functions enables rapid decision-making for network topology control strategies.

[0039] In some embodiments, step 101 includes: Step 1011: The holographic data is parsed and processed to obtain the encapsulation format of the holographic data.

[0040] Step 1012: Identify spatial coordinate identifiers from the encapsulation format using a deep packet inspection algorithm, and separate multiple modal components from the spatial coordinate identifiers.

[0041] Step 1013: Construct the spatiotemporal feature matrix of each modal component in the holographic data, perform fusion processing on the spatiotemporal feature matrix to obtain spatiotemporal fusion features, and determine the transmission path priority weight based on the spatiotemporal fusion features.

[0042] In practical implementation, in traditional network architectures, current network perception mechanisms primarily collect basic transmission parameters such as the Internet Protocol (IP) quintuple and ports. Their optimization algorithms are also mostly based on two-dimensional models, focusing on information such as node load and link quality. This two-dimensional, planar perception and optimization method cannot understand the essential three-dimensional spatial characteristics of holographic services and is ill-suited to the multimodal characteristics and three-dimensional spatial correlation requirements of holographic services. For example, when transmitting multi-view holographic video, the network layer cannot identify the continuity constraints of each viewpoint in spatial coordinates, leading to rendering gaps and distortions when switching viewpoints. Simultaneously, it cannot distinguish between ordinary video streams and three-dimensional model data streams carrying crucial depth information, easily causing mismatches in the transmission priority of critical data packets and resulting in 3D reconstruction failures.

[0043] In holographic communication scenarios, depth layer data and tactile feedback signals have a strict correspondence in spatial coordinates. However, current protocols lack the ability to parse spatial semantics, causing the network layer to be unable to recognize the spatiotemporal continuity constraints of key data streams. For example, in remote surgical teaching, the loss of depth information in the organ's vascular system will directly cause distortion in 3D reconstruction. Traditional routing algorithms, unable to distinguish between ordinary video streams and holographic depth streams, are prone to mismatching the transmission priority of critical data packets.

[0044] Therefore, the spatiotemporal joint coding multimodal feature extraction method of this disclosure does not treat the data stream as indiscriminate bits, but designs a four-dimensional spatiotemporal tensor representation model to represent the spatial coordinates of the holographic data stream. With timestamp The mapping is to a unified feature space.

[0045] In practice, the received holographic data packets are first parsed according to the protocol. An improved deep packet inspection technique is used to identify spatial coordinate identifiers in the encapsulation format, separating multimodal components such as depth layers and haptic feedback. By parsing the data packets using deep packet inspection, different modalities such as depth layers and haptic feedback are identified, and spatiotemporal joint coding is used to construct a feature fingerprint containing spatial semantics for each modality.

[0046] The above scheme parses and processes holographic data to obtain its encapsulation format. A deep packet inspection algorithm is used to identify spatial coordinate identifiers from the encapsulation format, and multiple modal components are separated from these identifiers. A spatiotemporal feature matrix is ​​constructed for each modal component in the holographic data. These spatiotemporal feature matrices are then fused to obtain spatiotemporal fusion features, and transmission path priority weights are determined based on these features. In this way, by establishing a real-time dynamic mapping mechanism between the three-dimensional spatial coordinates of the service and network topology parameters, the network can understand the three-dimensional spatial meaning of the holographic data stream, fundamentally solving the dimensionality mismatch problem.

[0047] In some embodiments, step 1013 includes: Step 1013A: Construct the spatiotemporal feature matrix of each modal component in the holographic data. , in, The spatiotemporal feature matrix for each modal component, For the preset metric space, Indicates three-dimensional spatial resolution. This represents the number of sampling points within the time window.

[0048] Step 1013B: The spatiotemporal feature matrix is ​​fused using a bilinear pooling algorithm to obtain spatiotemporal fused features. , in, For the spatiotemporal fusion feature, For spatial encoding weight matrix, The spatiotemporal feature matrix for each modal component, This indicates vectorization processing. For time-encoded weight matrix, It is the transpose of the time-encoding weight matrix. It is a non-linear activation function.

[0049] Step 1013C: Determine the transmission path priority weight based on the spatiotemporal fusion features. , in, The transmission path priority weight, For the spatiotemporal fusion feature, For nodes To the node Link feature vector, For nodes To the node The link feature vector.

[0050] In practice, a spatiotemporal feature matrix is ​​constructed for each modal component, wherein a preset metric space is defined. This represents a network resource, a certain metric, or a metric space under specific conditions. Spatiotemporal fusion features are obtained through bilinear pooling, and these features are used as feature fingerprints. Vectorization involves converting the matrix into column vectors in column order. Specifically, the spatiotemporal fusion features are determined based on the spatial encoding weight matrix and the temporal encoding weight matrix. The encoding process enables the network to automatically learn the spatial correlation patterns of holographic services. For example, in industrial equipment inspection scenarios, the encoder reinforces the attention weight distribution in key component areas of the equipment.

[0051] Furthermore, the transmission path priority weights for different data streams are dynamically calculated based on the generated feature fingerprints. This enables the network to intelligently identify depth information (e.g., the depth information of the organ's vascular system during remote surgery) and automatically allocate the highest priority transmission path to it, ensuring lossless transmission of critical 3D information. In 4K holographic video transmission tests, this mechanism reduced the depth layer packet loss rate from 0.8% to 0.05%, while the end-to-end latency standard deviation of the haptic feedback channel was reduced to ±0.7ms, significantly outperforming traditional routing strategies.

[0052] The above scheme constructs a spatiotemporal feature matrix for each modal component in the holographic data. This matrix is ​​then fused using a bilinear pooling algorithm to obtain spatiotemporal fusion features. Based on these features, transmission path priority weights are determined. By dynamically calculating the transmission path priority weights of the data stream, the network can intelligently identify depth information and automatically allocate the highest priority transmission path, ensuring lossless transmission of critical 3D information.

[0053] In some embodiments, step 102 includes: Step 1021: Determine the satellite's orbital parameters based on the holographic data, and determine the satellite's four-dimensional spatiotemporal coordinates based on the orbital parameters using an ephemeris calculation algorithm. , in, The four-dimensional spatiotemporal coordinates of the satellite, For at any time The satellite in the geocentric inertial coordinate system Axis coordinates For at any time The satellite in the geocentric inertial coordinate system Axis coordinates For at any time The satellite in the geocentric inertial coordinate system Axis coordinates This is the time offset compensation amount. This is a function for ephemeris calculation. Absolute timestamp, Right ascension of the ascending node, For the track inclination angle, The perigee tilt angle, For the major half-axis, For eccentricity, It is the angle closest to the point.

[0054] Step 1022: Determine the location matrix and resource state vector of the base station based on the holographic data; determine the three-dimensional density heat map of the base station based on the location matrix and the resource state vector. , in, The three-dimensional density heat map of the base station, For base stations The position matrix, For base stations The resource state vector, This represents the total number of cells in the spatial grid. This is a spatial interpolation function.

[0055] Step 1023: Determine the demand matrix of the holographic service space and the supply matrix of network resources from the three-dimensional density heat map; determine the optimal resource allocation strategy based on the demand matrix and the supply matrix. , in, The optimal resource allocation strategy is defined as follows. The demand matrix for holographic business space, For the supply matrix of network resources, This represents element-wise multiplication. For matrix norm, This indicates maximization.

[0056] In practical implementation, within the space-air-ground network, low-Earth orbit (LEO) satellites move at a high speed of approximately 7.8 km / s, while ground stations remain stationary, and drones exhibit variable attitudes. The spatiotemporal references for LEO satellites, ground stations, and drones are completely different. This high-speed motion of satellite nodes and the fixed deployment of ground base stations create a spatiotemporal reference discrepancy. Currently, traditional geographic coordinate systems are commonly used to represent network node locations. However, these systems struggle to uniformly represent the dynamic, heterogeneous resource states, leading to significant errors in predicting satellite coverage gaps and user movement trajectories. When a holographic terminal moves in three-dimensional space, this reference mismatch causes errors in satellite coverage gap prediction, resulting in image tortuosity. For example, when a user rotates their viewpoint, the current network cannot predict the spatial relationship between the satellite orbit and the terminal's trajectory, often causing a 3-5 second blackout period in the image.

[0057] To address this challenge, this disclosure establishes a four-dimensional spatiotemporal resource mapping model, which uniformly transforms satellite ephemeris parameters, UAV pose information, and ground node states to a geocentric inertial coordinate system (ECI). By constructing a unified four-dimensional spatiotemporal resource mapping model and transforming the states of all heterogeneous nodes to a unified coordinate system, precise alignment of resource supply and demand is achieved.

[0058] In practice, the first step is to determine the six orbital elements of the low-Earth orbit satellite (right ascension of the ascending node). Track inclination Perigeal argument Long half shaft eccentricity , and the near point angle Real-time analysis is performed, and four-dimensional spatiotemporal coordinates are generated using an ephemeris calculation algorithm. Four-dimensional spatiotemporal coordinates including the time dimension are generated for each node, and dynamic calibration is performed using a satellite-to-ground time-frequency synchronization signal. The time offset compensation amount... To correct for time-space synchronization errors caused by high-speed satellite movement, the ephemeris calculation function can calculate based on the input absolute timestamp. The satellite's four-dimensional spatiotemporal coordinates and absolute timestamp are output from the six elements of its orbit. The precise time used to calculate the satellite's position is dynamically calibrated using satellite-to-ground time and frequency synchronization signals, resulting in an absolute timestamp. Used for dynamically tracking satellite trajectories.

[0059] The load status and computing resources of ground base stations are mapped to a three-dimensional density heatmap. Through matrix operations, the supply side (each network node C_res) and the demand side are precisely matched. In this way, the system can accurately predict the relative position of terminals and satellites. Finally, resource supply and demand matching is achieved through matrix Hadamard product operations. Using this scheme, in industrial holographic inspection, the prediction error of satellite coverage gaps is controlled to the ±1.5cm level, and the image tomography rate is reduced from 12.7% to below 0.8%, significantly improving service continuity.

[0060] The above scheme determines satellite orbital parameters based on holographic data, and uses ephemeris calculation algorithms to determine the satellite's four-dimensional spatiotemporal coordinates based on these parameters. This transforms the states of all heterogeneous nodes into a unified coordinate system, achieving precise alignment of resource supply and demand. The scheme also determines the base station's location matrix and resource state vector based on holographic data, and then uses these to create a three-dimensional density heatmap of the base station. From the three-dimensional density heatmap, the demand matrix for the holographic service space and the supply matrix for network resources are determined, and the optimal resource allocation strategy is then established based on these matrices. This allows for accurate prediction of the relative positions of terminals and satellites, significantly improving service continuity.

[0061] In some embodiments, step 103 includes: Step 1031: Determine the transmitting end coordinate matrix and the receiving end coordinate matrix of the holographic data, and determine the spatial fidelity based on the transmitting end coordinate matrix and the receiving end coordinate matrix. , in, For the spatial fidelity, The coordinate matrix of the transmitting end, The coordinate matrix of the receiving end is... It represents the matrix norm.

[0062] Step 1032: Determine the first arrival timestamp of the first modal data stream and the second arrival timestamp of the second modal data stream in the holographic data; determine the multimodal synchronization error based on the first arrival timestamp and the second arrival timestamp. , in, The multimodal synchronization error is... For the first modal data stream, For the second modal data stream, The total number of modalities in the holographic data. The first arrival timestamp of the first modal data stream. This is the second arrival timestamp of the second modal data stream.

[0063] Step 1033: Determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error. , in, Let be the multi-objective optimization function. The first parameter to adjust is... For the spatial fidelity, This is the second adjustment parameter. The weights of the multimodal synchronization error are... The multimodal synchronization error is... This is the third adjustment parameter. This refers to the energy efficiency of network transmission.

[0064] In practice, traditional network optimization methods typically use single or a few basic transmission metrics such as bandwidth, latency, and packet loss rate as optimization targets, which are difficult to adapt to the multi-dimensional service quality requirements of holographic services, such as spatial fidelity and multimodal synchronization. Holographic services have multi-dimensional QoS requirements. For example, in remote industrial control scenarios, the absolute latency threshold of the haptic feedback channel must be below 15ms, while the elastic latency requirement of the visual layer can be relaxed to 50ms. The latency thresholds of the haptic feedback channel and the visual layer differ significantly. Traditional QoS models, lacking differentiated modeling capabilities, result in a critical data flow preemption failure rate as high as 34%.

[0065] To this end, this disclosure constructs a holographic-specific QoS quantification system, defining core indicators such as Spatial Fidelity (SFI) and Multimodal Synchronization Error (MSE), and building a holographic-specific, multi-objective QoS quantification evaluation system to enable optimization decisions to accurately match the multidimensional real needs of services. Specifically, Spatial Fidelity (SFI) and Multimodal Synchronization Error (MSE) are used to quantify the accuracy of 3D reconstruction and the consistency of multi-sensory experience.

[0066] A multi-objective optimization function is established by weighted fusion of basic transmission indicators and holographic characteristic indicators, integrating spatial fidelity (SFI), multimodal synchronization error (MSE), and energy efficiency into a single multi-objective optimization function. The first adjustment parameter... Second adjustment parameter and the third adjustment parameter The settings can be dynamically adjusted based on the type of service, for example, in a medical holographic consultation. , To enhance spatial accuracy, the above model reduced the rate of tactile feedback delay exceeding the standard from 22% to 1.2% in industrial equipment inspection, while improving energy efficiency by 35%.

[0067] The above scheme determines the coordinate matrices of the transmitter and receiver of the holographic data, and then determines the spatial fidelity based on these matrices. The first arrival timestamp of the first modality data stream and the second arrival timestamp of the second modality data stream are determined, and the multimodal synchronization error is calculated based on these timestamps. Finally, a multi-objective optimization function is determined based on the spatial fidelity and the multimodal synchronization error. This constructed multi-objective optimization function is a quantitative evaluation system that integrates multiple objectives, enabling optimization decisions to accurately match the multi-dimensional real needs of the business.

[0068] In some embodiments, step 104 includes: Step 1041: Determine the delay weight matrix and the distance weight matrix based on the transmission path priority weight.

[0069] Step 1042: Using a pre-trained graph neural network, heterogeneous graph nodes are determined based on the time delay weight matrix and the distance weight matrix. , in, For nodes In the heterogeneous graph nodes of the layer, For nodes The set of neighboring nodes, This is the time delay weight matrix. For nodes In the The feature quantity of the layer, This is the distance weight matrix. It is a non-linear activation function.

[0070] Step 1043: Determine the edge weights between nodes based on the transmission path priority weights, and determine the spatial continuity regularization term based on the edge weights. , in, For spatial continuity regularization, For a set of holographic session paths, For nodes spatial coordinates, For nodes spatial coordinates, For nodes With nodes Edge weights between them.

[0071] Step 1044: Determine the network topology control strategy based on the optimal resource allocation strategy, the multi-objective optimization function, and the spatial continuity regularization term.

[0072] In practical implementation, current reinforcement learning algorithms face the curse of state space dimensionality in dynamic space-air-ground topologies and struggle to handle the spatial continuity constraints of holographic services, resulting in slow decision-making and poor performance. When satellite switching occurs or sudden service disruptions occur (e.g., panoramic scanning of disaster sites), the lag in current network topology reconstruction becomes particularly pronounced. Taking satellite node routing as an example, traditional Q-learning algorithms only consider link quality indicators without considering the connection between satellite orbits and terminal trajectories, leading to image gaps exceeding 3 seconds during viewpoint switching and the inability to quickly establish deterministic transmission channels in emergency scenarios. For sudden service disruptions, cross-domain resource coordination is inefficient, failing to meet minute-level link establishment requirements.

[0073] This disclosure discloses a spatiotemporally constrained graph neural network architecture, the core of which lies in a heterogeneous graph encoder and a spatial regularization strategy. It employs a strategy combining conventional optimization and contingency planning. In conventional scenarios, the spatiotemporally constrained graph neural network (GNN) performs sub-second intelligent decision-making; in contingency scenarios, a resource pre-locking technology based on spatial gridding is activated to achieve rapid network deployment.

[0074] First, satellites, drones, and ground nodes are modeled as heterogeneous graph nodes, with edge attributes including latency. Spatial distance ,bandwidth .in, For the time delay adaptive weight matrix, This is the adaptive weight matrix for distance.

[0075] When outputting node activation probabilities, a spatial continuity regularization term is introduced into the policy network, enabling it to perceive the physical spatial location of nodes during decision-making, thereby avoiding the selection of links with excessive spatial jumps. Using this scheme, sub-second topology reconstruction (average 0.3 seconds) was achieved in emergency communication tests, reducing the image blackout time caused by satellite handover by 82%.

[0076] The above scheme determines the delay weight matrix and distance weight matrix based on transmission path priority weights. Using a pre-trained graph neural network, heterogeneous graph nodes are identified based on these matrices. Edge weights between nodes are determined according to transmission path priority weights, and spatial continuity regularization terms are used to determine these edge weights. A network topology control strategy is then determined based on the optimal resource allocation strategy, a multi-objective optimization function, and the spatial continuity regularization term. This allows the space-air-ground network to be modeled as a heterogeneous graph, leveraging the powerful graph information processing capabilities of graph neural networks to accurately determine the network topology control strategy. The spatial continuity regularization term enables decision-making based on the physical spatial location of nodes, avoiding the selection of links with excessive spatial jumps and reducing image blackout time caused by satellite handover.

[0077] In some embodiments, the method further includes: Step 105: Construct a spherical grid coordinate system centered on the holographic terminal based on the holographic data. , in, The coordinate system is a spherical grid centered on the holographic terminal. For the first sphere coordinate parameters, For the second spherical coordinate parameters, For the third sphere coordinate parameters, The total number of spatial grids, For the first A spatial grid, For the spatial coordinates of the holographic terminal, For the first The center point coordinates of each spatial grid is the grid radius.

[0078] Step 106: Determine the available resource quantity for each spatial grid based on the optimal resource allocation strategy, and determine the reserved resource quantity for each spatial grid based on the available resource quantity. , in, Reserved resource amount for each spatial grid. To reserve a coefficient for resources, For the first Class nodes in spatial grid The amount of available resources in Indicates the type of network resource. Indicates satellite resources, Indicates drone resources, This refers to ground base station resources.

[0079] In practical implementation, cross-domain resource pre-locking technology based on spatial gridding ensures the establishment of deterministic transmission channels for sudden holographic services. Specifically, cross-domain resource pre-locking technology based on spatial gridding is a fast channel mechanism designed for holographic services (e.g., disaster sites).

[0080] Available resources are determined based on a unified resource map and are used to calculate the amount of resources that can be reserved within each grid. Reserved resource quantity These are resource packages that are pre-reserved within each spatial grid and can be activated at any time. When a sudden service request is triggered, the reserved resources are activated directly, skipping complex real-time calculations and achieving a response time within seconds.

[0081] Cross-domain resource pre-locking and GNN decision-making are complementary. GNN decision-making handles fine-grained dynamic optimization in regular, predictable business scenarios. Cross-domain resource pre-locking, on the other hand, handles emergency scenarios requiring extremely high response speeds through pre-calculation and resource locking. It can be seen as an emergency plan that bypasses the complex reasoning of real-time GNN.

[0082] Sudden holographic services (such as panoramic scanning of disaster sites) require the network to establish deterministic transmission channels in a very short time. Traditional resource allocation mechanisms are inefficient due to their low cross-domain coordination and cannot meet the needs of establishing links within minutes.

[0083] This disclosure proposes a spatial gridded resource pre-locking method. First, a spherical grid coordinate system is constructed centered on a holographic terminal group, wherein the grid radius... The typical value is 500m. Satellite beams, UAV relays, and ground MEC resources are pre-allocated to each grid.

[0084] When a sudden business event is triggered, the pre-locked resource pool is directly activated, and the chain establishment latency is formulated as follows: , in, For total chain establishment latency, To fix the propagation and processing delay, Reserved resource amount for each spatial grid. This refers to the resource loading rate.

[0085] With the above solution, when disasters or other emergencies occur, the system directly activates the reserved resource pool of the corresponding grid, eliminating the need for complex real-time calculations and cross-domain coordination. In disaster drills, it can achieve 4K holographic coverage of a 20km² area within 10 seconds, which is 8 times faster than the traditional solution and has a bandwidth guarantee rate of 99.7%.

[0086] The above scheme constructs a spherical grid coordinate system centered on the holographic terminal based on holographic data.

[0087] The available resources for each spatial grid are determined based on the optimal resource allocation strategy, and the reserved resources for each spatial grid are determined based on the available resources. In this way, the reserved resources of the corresponding grid can be directly activated for sudden business needs, eliminating the need for complex real-time calculations and cross-domain coordination processes, and shortening the holographic coverage establishment time.

[0088] Through the above embodiments, holographic data is received, spatiotemporal fusion characteristics are determined based on the holographic data, and transmission path priority weights are determined based on these characteristics. This enables the establishment of a real-time dynamic mapping mechanism between the spatial coordinates of service units and network topology parameters based on holographic data. This allows the network to understand the three-dimensional space of the holographic data, achieving precise matching between network resources and the three-dimensional service space, fundamentally solving the dimensional mismatch problem. The highest priority transmission path is automatically allocated by determining the transmission path priority weights. The holographic data is parsed to obtain four-dimensional spatiotemporal coordinates. A three-dimensional density heatmap of the ground base station is determined based on the holographic data, and the optimal resource allocation strategy is determined based on the three-dimensional density heatmap. This allows the states of all heterogeneous nodes to be transformed into a unified coordinate system, achieving precise alignment of resource supply and demand. The spatial fidelity and multimodal synchronization error of the holographic data are determined. A multi-objective optimization function is determined based on the spatial fidelity and multimodal synchronization error. This multi-objective optimization function is a quantitative evaluation system for multi-objective fusion, enabling optimization decisions to accurately match the multi-dimensional real needs of services. Determining network topology control strategies based on transmission path priority weights, optimal resource allocation strategies, and multi-objective optimization functions enables rapid decision-making for network topology control strategies.

[0089] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0090] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] Based on the same inventive concept, corresponding to any of the above embodiments, this disclosure also provides a network topology control device based on holographic data.

[0092] refer to Figure 2 The network topology control device based on holographic data includes: The priority weight determination module 201 is configured to receive holographic data, determine spatiotemporal fusion features based on the holographic data, and determine transmission path priority weights based on the spatiotemporal fusion features. The allocation strategy determination module 202 is configured to parse and process the holographic data to obtain four-dimensional spatiotemporal coordinates, determine the three-dimensional density heat map of the ground base station based on the holographic data, and determine the optimal resource allocation strategy based on the three-dimensional density heat map. The optimization function determination module 203 is configured to determine the spatial fidelity and multimodal synchronization error of the holographic data, and determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error; The control strategy determination module 204 is configured to determine the network topology control strategy based on the transmission path priority weight, the optimal resource allocation strategy, and the multi-objective optimization function.

[0093] In some embodiments, the priority weight determination module 201 includes: The parsing and processing unit is configured to parse and process the holographic data to obtain the encapsulation format of the holographic data; The separation unit is configured to identify spatial coordinate identifiers from the encapsulation format using a deep packet inspection algorithm, and to separate multiple modal components from the spatial coordinate identifiers; The priority weight determination unit is configured to construct a spatiotemporal feature matrix for each modal component in the holographic data, perform fusion processing on the spatiotemporal feature matrix to obtain spatiotemporal fusion features, and determine the transmission path priority weight based on the spatiotemporal fusion features.

[0094] In some embodiments, the priority weight determination unit includes: The spatiotemporal feature matrix construction subunit is configured to construct the spatiotemporal feature matrix for each modal component in the holographic data. , in, The spatiotemporal feature matrix for each modal component, For the preset metric space, Indicates three-dimensional spatial resolution. This represents the number of sampling points within the time window. The fusion processing subunit is configured to perform fusion processing on the spatiotemporal feature matrix using a bilinear pooling algorithm to obtain spatiotemporal fusion features. , in, For the spatiotemporal fusion feature, For spatial encoding weight matrix, The spatiotemporal feature matrix for each modal component, This indicates vectorization processing. For time-encoded weight matrix, It is the transpose of the time-encoding weight matrix. It is a non-linear activation function; The priority weight determination subunit is configured to determine the transmission path priority weight based on the spatiotemporal fusion features. , in, The transmission path priority weight, For the spatiotemporal fusion feature, For nodes To the node Link feature vector, For nodes To the node The link feature vector.

[0095] In some embodiments, the allocation strategy determination module 202 includes: The four-dimensional spatiotemporal coordinate determination unit is configured to determine the satellite's orbital parameters based on the holographic data, and to determine the satellite's four-dimensional spatiotemporal coordinates based on the orbital parameters using an ephemeris calculation algorithm. , in, The four-dimensional spatiotemporal coordinates of the satellite, For at any time The satellite in the geocentric inertial coordinate system Axis coordinates For at any time The satellite in the geocentric inertial coordinate system Axis coordinates For at any time The satellite in the geocentric inertial coordinate system Axis coordinates This is the time offset compensation amount. This is a function for ephemeris calculation. Absolute timestamp, Right ascension of the ascending node, For the track inclination angle, The perigee tilt angle, For the major half-axis, For eccentricity, It is a near-point angle; The heatmap determination unit is configured to determine the location matrix and resource state vector of the base station based on the holographic data, and to determine a three-dimensional density heatmap of the base station based on the location matrix and the resource state vector. , in, The three-dimensional density heat map of the base station, For base stations The position matrix, For base stations The resource state vector, This represents the total number of cells in the spatial grid. It is a spatial interpolation function; The allocation strategy determination unit is configured to determine the demand matrix of the holographic service space and the supply matrix of network resources from the three-dimensional density heat map, and determine the optimal resource allocation strategy based on the demand matrix and the supply matrix. , in, The optimal resource allocation strategy is defined as follows. The demand matrix for holographic business space, For the supply matrix of network resources, This represents element-wise multiplication. For matrix norm, This indicates maximization.

[0096] In some embodiments, the optimization function determination module 203 includes: The spatial fidelity determination unit is configured to determine the transmitting end coordinate matrix and the receiving end coordinate matrix of the holographic data, and determine the spatial fidelity based on the transmitting end coordinate matrix and the receiving end coordinate matrix. , in, For the spatial fidelity, The coordinate matrix of the transmitting end, The coordinate matrix of the receiving end is... It is the matrix norm; The multimodal synchronization error determination unit is configured to determine a first arrival time stamp of the first modal data stream and a second arrival time stamp of the second modal data stream in the holographic data, and determine the multimodal synchronization error based on the first arrival time stamp and the second arrival time stamp. , in, The multimodal synchronization error is... For the first modal data stream, For the second modal data stream, The total number of modalities in the holographic data. The first arrival timestamp of the first modal data stream. This is the second arrival timestamp of the second modal data stream; The optimization function determination unit is configured to determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error. , in, Let be the multi-objective optimization function. The first parameter to adjust is... For the spatial fidelity, This is the second adjustment parameter. The weights of the multimodal synchronization error are... The multimodal synchronization error is... This is the third adjustment parameter. This refers to the energy efficiency of network transmission.

[0097] In some embodiments, the control strategy determination module 204 includes: The weight matrix determination unit is configured to determine the delay weight matrix and the distance weight matrix based on the transmission path priority weight; The heterogeneous graph node determination unit is configured to determine heterogeneous graph nodes based on the time delay weight matrix and the distance weight matrix using a pre-trained graph neural network. , in, For nodes In the heterogeneous graph nodes of the layer, For nodes The set of neighboring nodes, This is the time delay weight matrix. For nodes In the The feature quantity of the layer, This is the distance weight matrix. It is a non-linear activation function; The regularization term determination unit is configured to determine the edge weights between nodes based on the transmission path priority weights, and to determine the spatial continuity regularization term based on the edge weights. , in, For spatial continuity regularization, For a set of holographic session paths, For nodes spatial coordinates, For nodes spatial coordinates, For nodes With nodes Edge weights between them; The control strategy determination unit is configured to determine the network topology control strategy based on the optimal resource allocation strategy, the multi-objective optimization function, and the spatial continuity regularization term.

[0098] In some embodiments, the apparatus further includes: The coordinate system construction module is configured to construct a spherical grid coordinate system centered on the holographic terminal based on the holographic data. , in, The coordinate system is a spherical grid centered on the holographic terminal. For the first sphere coordinate parameters, For the second spherical coordinate parameters, For the third sphere coordinate parameters, The total number of spatial grids, For the first A spatial grid, For the spatial coordinates of the holographic terminal, For the first The center point coordinates of each spatial grid The grid radius; The reserved resource quantity determination module is configured to determine the available resource quantity for each spatial grid based on the optimal resource allocation strategy, and to determine the reserved resource quantity for each spatial grid based on the available resource quantity. , in, Reserved resource amount for each spatial grid. To reserve a coefficient for resources, For the first Class nodes in spatial grid The amount of available resources in Indicates the type of network resource. Indicates satellite resources, Indicates drone resources, This refers to ground base station resources.

[0099] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing this disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0100] The apparatus described above is used to implement the corresponding network topology control method based on holographic data in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0101] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the network topology control method based on holographic data as described in any of the above embodiments.

[0102] Figure 3 This embodiment illustrates a more specific hardware structure of an electronic device. The device may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0103] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0104] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0105] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0106] The communication interface 1040 is used to connect the communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB (Universal Serial Bus), network cable, etc.) or wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0107] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0108] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0109] The electronic devices described above are used to implement the corresponding network topology control methods based on holographic data in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0110] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the network topology control method based on holographic data as described in any of the above embodiments.

[0111] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0112] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the network topology control method based on holographic data as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0113] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the network topology control method based on holographic data as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0114] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0115] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations of this disclosed technical solution.

[0116] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0117] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0118] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0119] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0120] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0121] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of this disclosure. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A network topology control method based on holographic data, characterized in that, The method includes: Upon receiving holographic data, determine spatiotemporal fusion features based on the holographic data, and determine transmission path priority weights based on the spatiotemporal fusion features; The holographic data is parsed to obtain four-dimensional spatiotemporal coordinates. Based on the holographic data, a three-dimensional density heat map of the ground base station is determined, and the optimal resource allocation strategy is determined based on the three-dimensional density heat map. Determine the spatial fidelity and multimodal synchronization error of the holographic data, and determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error; The network topology control strategy is determined based on the transmission path priority weight, the optimal resource allocation strategy, and the multi-objective optimization function.

2. The method according to claim 1, characterized in that, The step of determining spatiotemporal fusion features based on the holographic data and determining transmission path priority weights based on the spatiotemporal fusion features includes: The holographic data is parsed and processed to obtain the encapsulation format of the holographic data; The spatial coordinate identifier is identified from the encapsulation format using a deep packet inspection algorithm, and multiple modal components are separated from the spatial coordinate identifier. A spatiotemporal feature matrix for each modal component in the holographic data is constructed, and the spatiotemporal feature matrix is ​​fused to obtain spatiotemporal fusion features. The transmission path priority weight is determined based on the spatiotemporal fusion features.

3. The method according to claim 2, characterized in that, The process of constructing a spatiotemporal feature matrix for each modal component in the holographic data, fusing the spatiotemporal feature matrices to obtain spatiotemporal fusion features, and determining transmission path priority weights based on the spatiotemporal fusion features includes: Construct the spatiotemporal feature matrix for each modal component in the holographic data. ， in, The spatiotemporal feature matrix for each modal component, For the preset metric space, Indicates three-dimensional spatial resolution. This represents the number of sampling points within the time window. The spatiotemporal feature matrix is ​​fused using a bilinear pooling algorithm to obtain spatiotemporal fused features. ， in, For the spatiotemporal fusion feature, For spatial encoding weight matrix, The spatiotemporal feature matrix for each modal component, This indicates vectorization processing. For time-encoded weight matrix, It is the transpose of the time-encoding weight matrix. It is a non-linear activation function; The transmission path priority weight is determined based on the spatiotemporal fusion characteristics. ， in, The transmission path priority weight, For the spatiotemporal fusion feature, For nodes To the node Link feature vector, For nodes To the node The link feature vector.

4. The method according to claim 1, characterized in that, The process of parsing and processing the holographic data to obtain four-dimensional spatiotemporal coordinates, determining a three-dimensional density heatmap of the ground base station based on the holographic data, and determining an optimal resource allocation strategy based on the three-dimensional density heatmap includes: Based on the holographic data, the satellite's orbital parameters are determined, and the satellite's four-dimensional spatiotemporal coordinates are determined using an ephemeris calculation algorithm based on these orbital parameters. ， in, The four-dimensional spatiotemporal coordinates of the satellite, For at any time The satellite in the geocentric inertial coordinate system Axis coordinates For at any time The satellite in the geocentric inertial coordinate system Axis coordinates For at any time The satellite in the geocentric inertial coordinate system Axis coordinates This is the time offset compensation amount. This is a function for ephemeris calculation. Absolute timestamp, Right ascension of the ascending node, For the track inclination angle, The perigee tilt angle, For the major half-axis, For eccentricity, It is a near-point angle; Based on the holographic data, the location matrix and resource state vector of the base station are determined, and based on the location matrix and resource state vector, a three-dimensional density heat map of the base station is determined. ， in, The three-dimensional density heat map of the base station, For base stations The position matrix, For base stations The resource state vector, This represents the total number of cells in the spatial grid. It is a spatial interpolation function; The demand matrix of the holographic service space and the supply matrix of network resources are determined from the three-dimensional density heat map. Based on the demand matrix and the supply matrix, the optimal resource allocation strategy is determined. ， in, The optimal resource allocation strategy is defined as follows. The demand matrix for holographic business space, For the supply matrix of network resources, This represents element-wise multiplication. For matrix norm, This indicates maximization.

5. The method according to claim 1, characterized in that, The process of determining the spatial fidelity and multimodal synchronization error of the holographic data, and determining a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error, includes: Determine the sending and receiving coordinate matrices of the holographic data, and determine the spatial fidelity based on the sending and receiving coordinate matrices. ， in, For the spatial fidelity, The coordinate matrix of the transmitting end, The coordinate matrix of the receiving end is... It is the matrix norm; The first arrival timestamp of the first modal data stream and the second arrival timestamp of the second modal data stream in the holographic data are determined, and the multimodal synchronization error is determined based on the first arrival timestamp and the second arrival timestamp. ， in, The multimodal synchronization error is... For the first modal data stream, For the second modal data stream, The total number of modalities in the holographic data. The first arrival timestamp of the first modal data stream. This is the second arrival timestamp of the second modal data stream; A multi-objective optimization function is determined based on the spatial fidelity and the multimodal synchronization error. ， in, Let be the multi-objective optimization function. The first parameter to adjust is... For the spatial fidelity, This is the second adjustment parameter. The weights of the multimodal synchronization error are... The multimodal synchronization error is... This is the third adjustment parameter. This refers to the energy efficiency of network transmission.

6. The method according to claim 1, characterized in that, The step of determining the network topology control strategy based on the transmission path priority weight, the optimal resource allocation strategy, and the multi-objective optimization function includes: The delay weight matrix and distance weight matrix are determined based on the transmission path priority weights; Using a pre-trained graph neural network, heterogeneous graph nodes are determined based on the time delay weight matrix and the distance weight matrix. ， in, For nodes In the heterogeneous graph nodes of the layer, For nodes The set of neighboring nodes, This is the time delay weight matrix. For nodes In the The feature quantity of the layer, This is the distance weight matrix. It is a non-linear activation function; The edge weights between nodes are determined based on the transmission path priority weights, and the spatial continuity regularization term is determined based on the edge weights. ， in, For spatial continuity regularization, For a set of holographic session paths, For nodes spatial coordinates, For nodes spatial coordinates, For nodes With nodes Edge weights between them; The network topology control strategy is determined based on the optimal resource allocation strategy, the multi-objective optimization function, and the spatial continuity regularization term.

7. The method according to claim 1, characterized in that, The method further includes: Based on the holographic data, a spherical grid coordinate system centered on the holographic terminal is constructed. ， in, The coordinate system is a spherical grid centered on the holographic terminal. For the first sphere coordinate parameters, For the second spherical coordinate parameters, For the third sphere coordinate parameters, The total number of spatial grids, For the first A spatial grid, For the spatial coordinates of the holographic terminal, For the first The center point coordinates of each spatial grid The grid radius; Based on the optimal resource allocation strategy, the available resource quantity for each spatial grid is determined, and based on the available resource quantity, the reserved resource quantity for each spatial grid is determined. ， in, Reserved resource amount for each spatial grid. To reserve a coefficient for resources, For the first Class nodes in spatial grid The amount of available resources in Indicates the type of network resource. Indicates satellite resources, Indicates drone resources, This refers to ground base station resources.

8. A network topology control device based on holographic data, characterized in that, include: The priority weight determination module is configured to receive holographic data, determine spatiotemporal fusion features based on the holographic data, and determine transmission path priority weights based on the spatiotemporal fusion features. The allocation strategy determination module is configured to parse and process the holographic data to obtain four-dimensional spatiotemporal coordinates, determine the three-dimensional density heat map of the ground base station based on the holographic data, and determine the optimal resource allocation strategy based on the three-dimensional density heat map. The optimization function determination module is configured to determine the spatial fidelity and multimodal synchronization error of the holographic data, and determine a multi-objective optimization function based on the spatial fidelity and the multimodal synchronization error; The control strategy determination module is configured to determine the network topology control strategy based on the transmission path priority weight, the optimal resource allocation strategy, and the multi-objective optimization function.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the program, implements the method as claimed in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing a computer to perform the method according to any one of claims 1 to 7.

Images