Beam adjusting method and electronic equipment

Abstract

The invention discloses a beam adjusting method and electronic equipment. The method comprises the steps that a terminal accesses a network and collects target information; determining a beam direction corresponding to the terminal through beam scanning; determining a data fusion result and a beam adjustment strategy through the control platform; and adjusting a target beam according to the beam adjustment strategy.

Description

Technical Field

[0001] This application belongs to the field of wireless communication networks, and specifically relates to a method for adjusting beams and an electronic device. Background Technology

[0002] As the core infrastructure for mobile communication technology innovation and efficient data transmission, the technological evolution of cellular networks directly affects the network carrying capacity in the era of the Internet of Everything.

[0003] Related solutions introduce beamforming to control antenna direction in order to focus energy and improve communication performance. However, their core is to adjust the base station's antenna array, or for a single terminal to make single-point adjustments based on its own perception, lacking a strategy mechanism for adjusting the antenna direction of each terminal globally. Because the beamforming algorithm on the terminal side cannot perceive the global situation, it cannot perceive the actual effects such as base station load, and only makes single-point adjustments, failing to achieve dynamic optimization. Summary of the Invention

[0004] The purpose of this application is to provide a method and electronic device for adjusting beams, which solves the problem that beamforming algorithms cannot perceive the global situation, thus failing to perceive the actual effects such as base station load and thus failing to form dynamic optimization.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows: In a first aspect, embodiments of this application provide a method for adjusting a beam, comprising: a terminal accessing a network and collecting target information; determining the beam direction corresponding to the terminal through beam scanning; determining the data fusion result and beam adjustment strategy through a control platform; and adjusting the target beam according to the beam adjustment strategy.

[0006] In a second aspect, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0007] Thirdly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0008] Fourthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.

[0009] In this embodiment, the target information is collected by the terminal accessing the network; the beam direction corresponding to the terminal is determined by beam scanning; the data fusion result and beam adjustment strategy are determined by the control platform; and the target beam is adjusted according to the beam adjustment strategy. This can solve the problem that the beamforming algorithm cannot perceive the actual effects such as base station load due to its inability to perceive the global situation, and thus cannot form dynamic optimization. Attached Figure Description

[0010] Figure 1 This is a flowchart illustrating a method for adjusting a beam according to an embodiment of this application; Figure 2-3 This is a schematic diagram of the scene provided in the embodiments of this application; Figure 4 This is a schematic diagram showing that the antenna radiation pattern provided in the embodiments of this application presents uniform omnidirectional coverage; Figure 5 This is a schematic diagram of omnidirectional detection provided in an embodiment of this application; Figure 6 This is a schematic diagram illustrating the receipt of data messages sent from various IoT terminals and base stations, provided in an embodiment of this application. Figure 7 This is a schematic diagram of a beam adjustment device provided in an embodiment of this application; Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0011] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0013] The embodiments of this application will be described in detail below with reference to the accompanying drawings and specific examples and application scenarios.

[0014] Figure 1This diagram illustrates a flowchart of a method for determining a scene graph according to an embodiment of this application. Figure 1 As shown, the method includes: S102: The terminal accesses the network and collects target information.

[0015] Optionally, network camping can be performed on the antenna; the channel quality and service load of the serving cell and neighboring cells can be recorded synchronously; spatial spectrum scanning can be initiated during service idle periods; the signal characteristics of base stations in each direction can be periodically detected; a network state matrix can be constructed based on four-dimensional spatiotemporal frequency data through the control platform; and a beam pointing strategy for a future time slot can be generated for each terminal by predicting the service traffic distribution through a machine learning model.

[0016] Combination Figure 2-3 As shown, optionally, this process is executed by the IoT terminal, the network infrastructure layer (including base stations and the core network), and the control platform. The terminal layer is responsible for data acquisition and status monitoring, and executes beamforming commands issued by the control platform. The network infrastructure layer provides base station load information and channel quality parameters, and constructs control signaling transmission channels. The control platform, as a global resource optimization engine, integrates terminal-reported data and network-side operating indicators, runs multi-dimensional parameter optimization algorithms to generate terminal access strategies and beamforming schemes, and is also compatible with the injection and execution of manual intervention commands.

[0017] The beam intelligent control mechanism constructed in this application includes four closed-loop execution stages: during the initial terminal access stage, an omnidirectional antenna is used to perform conventional network camping, synchronously recording status parameters such as channel quality and service load of the serving cell and neighboring cells and uploading them to the control platform; during service idle periods, spatial spectrum scanning is initiated to periodically detect the signal characteristics of base stations in each direction; the control platform constructs a network state matrix based on spatiotemporal frequency and service four-dimensional data, predicts service traffic distribution through machine learning models, and generates the optimal beam pointing strategy for each terminal for a future time slot; finally, beam adjustment commands are sent to the terminal through the downlink channel, forming a dynamic optimization loop of "perception-decision-execution".

[0018] The core algorithm used in this application matches the optimal frequency point f and the beamforming parameters of the antenna array to the terminal using various types of information. The beamforming parameters are divided into the antenna direction θ and the beamwidth. Its core formula is the array factor (AF):

[0019] Where N is the number of array elements, In is the excitation amplitude of the nth array element, k is the wave number, d is the element spacing, and θ is the pitch angle. The azimuth angle is denoted by 'In'. By optimizing In and phase, a high-gain main lobe can be formed while suppressing sidelobes.

[0020] Combination Figure 4 As shown, optionally, when the IoT terminal device is powered on, the antenna control module initializes the antenna parameters to omnidirectional mode parameters, at which time the antenna radiation pattern presents uniform omnidirectional coverage.

[0021] The terminal's signal transceiver module begins scanning the surrounding available cellular base station frequency bands, searching for base stations with signal strength reaching a certain threshold. Once an accessible base station is found, the access process is completed according to the cellular network's access protocol, establishing a communication connection.

[0022] During the establishment of a communication connection, the terminal's network status monitoring unit records network status parameters such as the cell number, frequency, signal strength, and signal quality of the currently accessed base station. During the operation of the terminal's services, whenever a service request or data transmission occurs, it records information such as service volume, request time, and response time. By calculating the frequency of service requests per unit time, communication success rate (calculated based on the number of successfully received response data packets and the total number of sent data packets), and latency (calculated based on the time difference between request sending time and response receiving time), service indicators are also stored in the local data buffer.

[0023] Some of the parameters required in this application are shown in Table 1.

[0024] Table 1. Parameter values ​​for the IoT terminal required for this application.

[0025] The terminal collects multiple parameters such as communication uplink and downlink rates, duration, intervals, location information, and data volume. These parameter values ​​accurately reflect information about different terminals in terms of communication behavior, location patterns, and data transmission. However, sampling involves multiple sampling values, so data processing is required to determine one or a set of representative valid values. For example, signal strength varies slightly or has sudden changes, while the strength value representing the signal received by the terminal is usually fixed. Therefore, data collected at different time points needs to undergo preprocessing steps such as data cleaning, transformation, and normalization to eliminate noise, fill in missing values, and unify the data format to determine a valid value. Data processing is applied to each parameter of each IoT terminal, and the processed data can construct its parameter value set. This application uses an averaging method to process the data, with the specific formula as follows: Suppose that n values ​​of parameter m are collected and denoted as dataset X={x1,x2,…,xn}. For each extracted parameter value, calculate its average value over the entire dataset.

[0026]

[0027] in, It is the i-th value of parameter m, and n is the number of samples. This is the calculated mean.

[0028] The above method is used to statistically analyze service and network parameters within a unit time T and construct the parameter set for the terminal. A sliding window algorithm is then used to update the data in real time. Taking the collection of service volume V, frequency F, latency D, and communication success rate SR as an example, the service feature vector B is constructed as follows:

[0029] When the preset information reporting cycle is reached, the terminal's communication unit extracts the terminal parameter feature set from the local storage unit and data buffer, and sends it to the control platform through the data channel of the cellular network.

[0030] S104: Determine the beam direction corresponding to the terminal through beam scanning.

[0031] If no new service requests need to be processed within the predetermined service idle time and the previous service transmission has been completed for more than a certain period of time, the antenna beam scanning process is triggered; according to the preset beam scanning strategy, the antenna azimuth angle and beamwidth are adjusted sequentially; for each beam direction and width combination, base station search is performed, the base station signal pointing down the beam is detected, and the corresponding detection data is measured and recorded; the processed detection data is sent to the control platform.

[0032] Combination Figure 5 As shown, beam scanning achieves omnidirectional detection of space signals by dynamically adjusting antenna pattern parameters. Its core idea is to generate beams with different directions by changing the excitation phase of array elements, and to measure the signal quality and communication status in each beam direction, reporting this data to the control platform. This allows for the analysis of received signal characteristics (such as spectrum occupancy and signal strength fluctuations) to determine the access and beam direction strategy for each terminal.

[0033] The terminal's service scheduling unit determines that it is currently in a service gap, that is, there are no new service requests to be processed within the set service idle time length and the previous service transmission has been completed for more than a certain period of time, and triggers the antenna beam scanning process.

[0034] The antenna control module adjusts the antenna's azimuth and beamwidth sequentially according to a preset beam scanning strategy. For example, the initial azimuth is 0° and the beamwidth is 30°. Then, the azimuth is increased by 15° each time, and the beamwidth is adjusted to different values ​​such as 30°, 60°, and 90° for combined scanning.

[0035] After the terminal activates beam scanning mode, the scanning parameters include: Azimuth ∈[0°,360°], step Δ ; Pitch angle θ∈[0°,90°], step Δθ; Beamwidth Δ ∈[30°,120°], achieved by adjusting the phase of the array elements.

[0036] Beam pattern function F(θ, By optimizing the phase of array elements m generation:

[0037] Where d is the element spacing, λ is the wavelength, and m is the element number.

[0038] For each beam direction and width combination, the signal transceiver module re-performs the base station search, detects the base station signal pointing down to that beam, and measures and records the corresponding network parameter information such as signal strength, signal quality, base station ID, and frequency.

[0039] Meanwhile, the terminal initiates small-batch test tasks in each direction, such as continuously sending 10 ping packets to the base station or a specific test server, counting the number of ping packets that are successfully received to calculate the communication success rate, recording the round-trip latency of each ping packet and calculating business indicators such as average latency, and storing them in the local data buffer.

[0040] After summarizing the parameters of various types of IoT terminals, some of the parameters required in this application are extracted as shown in Table 2.

[0041] Table 2 Parameter values ​​for IoT terminals required for this application

[0042] Similar to the access phase, the terminal collects multi-dimensional parameters such as cell and network information during idle periods. This sampling involves multiple values ​​from multiple samplings, necessitating data processing to determine one or a set of representative valid values. For example, signal strength varies slightly or experiences sudden changes, while the strength value representing the terminal's received signal is usually fixed. Therefore, preprocessing steps such as data cleaning, transformation, and normalization are required for data collected at different times to eliminate noise, fill in missing values, and standardize the data format, ultimately determining a valid value. Data processing is applied to each parameter of each IoT terminal, and the processed data constructs its parameter value set. This application uses an averaging method to process the data, with the specific formula as follows: Suppose we collect n values ​​of parameter m, denoted as dataset X = {x1, x2, ..., xn}. For each extracted parameter value, calculate its average value over the entire dataset.

[0043]

[0044] in, It is the i-th value of parameter m, and n is the number of samples. This is the calculated mean.

[0045] Upon completion of each beam scan (scanning according to all preset combinations of azimuth angles and beamwidths) or upon reaching the preset scan information reporting cycle, the terminal's communication unit integrates and packages the network information, service information, and interference source information collected in this scan, and reports them to the control platform in the same manner as before.

[0046] S106: Determine the data fusion results and beam adjustment strategy through the control platform.

[0047] Receive input parameters or commands; The data fusion result and beam adjustment strategy are determined based on the input parameters or instructions.

[0048] The control platform determines the data fusion result and beam adjustment strategy based on the detection data and the received input parameters or instructions.

[0049] Determine instruction priority; Receive operation logs.

[0050] Combination Figure 6 As shown, the control platform monitors the network channel in real time, receiving data messages from various IoT terminals and base stations. The received data is categorized and stored according to key information such as terminal ID, base station ID, and timestamp, constructing a multi-dimensional database covering various information including terminal location, services, network status, and base station load.

[0051] The data analysis and processing submodule periodically (e.g., once per hour) initiates the data processing flow. First, it analyzes the business information reported by the terminals and statistically analyzes the characteristics of each terminal in different time periods, such as peak business volume, average latency, and communication success rate trends. Then, it summarizes the network status information.

[0052] At the same time, the control platform obtains information such as the number of terminal accesses, service processing capacity usage, and service load of each frequency point from the base station network management system and updates the data records of the corresponding base stations in the database.

[0053] Based on the comprehensive data foundation mentioned above, the data analysis and processing submodule establishes a network performance prediction model to predict changes in the service demands of various terminals and the service load of base stations within a certain period of time (such as the next 24 hours).

[0054] Based on the prediction results, the strategy formulation and distribution submodule constructs an optimization model aimed at maximizing the overall network communication efficiency, comprehensively considering factors such as base station capacity limitations, terminal service quality requirements, and frequency resource allocation. By solving this optimization model, the frequency points to be allocated to each terminal in different future time periods, the base stations to be accessed, and the corresponding antenna beam pointing strategies are obtained.

[0055] The control platform packages the pre-defined policies into instruction messages according to terminal ID and time sequence, and sends them to the corresponding IoT terminals. Simultaneously, the policy formulation and distribution submodule continuously monitors the actual network operation and policy execution effectiveness. If it detects that the policy needs adjustment (e.g., a large deviation between actual business volume and forecasts), it triggers a re-analysis and policy formulation process, promptly updating and distributing the new policy.

[0056] The control platform collects data reported by terminals, base station load information Si, and frequency utilization Uf to construct a network state matrix N. The matrix has N×M dimensions, where N is the number of terminals and M is the feature dimension (such as signal strength RSRP, arrival delay TA, etc.). An example of matrix construction is shown below:

[0057] The core of this application's algorithm is to calculate the beamforming direction parameters based on the information reported by each terminal and base station. To balance local temporal parameters and key parameters, this application uses an LSTM-Attention model to implement data processing and beamforming direction calculation. The key steps of the algorithm implementation are as follows: Key features refer to parameters that have a significant impact on the final result. In the LSTM-Attention model, they are used for the calculation of the Attention part. In this solution, the main key features are divided into four categories: time domain, frequency domain, spatial domain, and business domain. Typical parameters are shown below.

[0058] Business volume change rate: Calculates the derivative of business volume over time to reflect the dynamic changes in business volume.

[0059]

[0060] Where V(t) represents the traffic volume at time t, and Δt represents the time interval.

[0061] Signal strength change rate: Calculates the derivative of signal strength over time to reflect the dynamic changes in signal strength.

[0062]

[0063] Where P(t) represents the signal strength at time t.

[0064] Signal strength fluctuation: Calculate the standard deviation of signal strength over time to measure the stability of signal strength.

[0065]

[0066] Where Pi represents the signal strength at time i, μP represents the average signal strength, and N represents the number of time points.

[0067] Spectrum occupancy: Statistics on spectrum resource usage to reflect the scarcity of spectrum resources.

[0068] in, I ( f i ) indicates frequency point f i An indicator function for whether a frequency is occupied (1 for occupied, 0 for unoccupied), where M represents the total number of frequency points.

[0069] Channel Quality Indicator (CQI) distribution: Statistics on the frequency of occurrence of different CQI levels to assess the overall channel quality.

[0070]

[0071] Where Nk represents the number of times CQI level k occurs, and Ntotal represents the total number of occurrences.

[0072] Spatial feature extraction: Neighboring cell base station signal strength matrix: Collect and statistically analyze the signal strength of neighboring cell base stations to construct a signal strength matrix to reflect the spatial signal distribution.

[0073]

[0074] Where Pi,j represents the signal strength of the j-th neighboring base station at the i-th sample time, Nsample represents the number of samples, and NBS represents the number of neighboring base stations.

[0075] Beam spatial response matrix: The signal reception quality of the terminal in different beam directions is sorted out to construct the beam spatial response matrix.

[0076]

[0077] Where Ri,j represents the signal reception quality in the j-th beam direction at the i-th sample time, and Nbeam represents the number of beam directions.

[0078] Business Feature Extraction: QoS requirement parameters: Extract QoS requirement parameters such as latency, packet loss rate, and bandwidth of the service as an important reference for optimization objectives.

[0079]

[0080] Where Dreq represents the maximum allowed latency, Lreq represents the maximum allowed packet loss rate, and Breq represents the minimum required bandwidth.

[0081] Build a predictive model LSTM layer: Inputs: time-domain features (rate of change of traffic volume, rate of change of signal strength, signal strength fluctuation), frequency-domain features (spectrum occupancy, CQI distribution), spatial-domain features (signal strength matrix of neighboring base stations, beam spatial response matrix), and service features (service type coding, QoS requirement parameters).

[0082] Processing: The time-series dependencies in the input features are captured through the memory cells and gating mechanism of the LSTM unit. The calculation formula for the LSTM unit is as follows:

[0083]

[0084]

[0085]

[0086]

[0087]

[0088] Where ft, it, and ot represent the activation vectors of the forget gate, input gate, and output gate, respectively. Let Ct represent the cell state candidate value, ht represent the hidden state, Wf, Wi, WC, and Wo represent the weight matrix, bf, bi, bC, and bo represent the bias vector, σ represent the sigmoid function, and ⊙ represent element-wise multiplication.

[0089] Output: Generate a hidden state sequence H=[h1,h2,…,hT], where T represents the number of time steps and contains historical information of the input data.

[0090] Attention mechanism: Input: The hidden state sequence H of the LSTM layer.

[0091] Processing: Calculate the importance weight of each hidden state, focusing on the historical moments that have the greatest impact on the prediction result. The formula for calculating the attention mechanism is as follows:

[0092]

[0093]

[0094] Where et represents the attention score of the hidden state ht, v, Wh, and bh represent the parameters of the attention mechanism, αt represents the attention weight of the hidden state ht, and c represents the context vector.

[0095] Output: The weighted hidden state representation c, which serves as the input to the fully connected layer.

[0096] Fully connected layer and output: Input: The output c of the attention mechanism.

[0097] Processing: A fully connected layer is used to perform a nonlinear transformation, mapping the high-dimensional features to a low-dimensional space. The calculation formula for the fully connected layer is as follows:

[0098] Where Wy represents the weight matrix and by represents the bias vector.

[0099] Output: The predicted optimal beam direction angle (θpred), which indicates the beam direction that the terminal should point towards in the future.

[0100] Model training and evaluation: Training data: Use historical datasets for model training. The datasets should contain input features and corresponding optimal beam direction angle labels.

[0101] Loss function: The mean squared error (MSE) is used as the loss function to measure the difference between the predicted value and the true value.

[0102]

[0103] Where N represents the number of samples, θpred,i represents the predicted beam direction angle of the i-th sample, and θtrue,i represents the true beam direction angle of the i-th sample.

[0104] Evaluation metrics: Accuracy, recall, and F1 score are used to evaluate model performance. Since the beam direction angle is a continuous value, root mean square error (RMSE) and mean absolute error (MAE) can be used as evaluation metrics.

[0105]

[0106]

[0107] In the optimization calculation phase, based on the optimal beam direction predicted by the model, and combined with a multi-objective optimization function, an optimization algorithm is used to calculate the optimal beam direction angle (θopt) and beamwidth (θopt) for each terminal. opt).

[0108] Construction of multi-objective optimization function: Objective function: Considering multiple objectives such as service latency, packet loss rate, signal strength, and base station resource utilization, a multi-objective optimization function is constructed.

[0109]

[0110] Where D(θ, L(θ, ) represents the service latency. ) represents the packet loss rate, Psignal(θ, ) represents the signal strength, ηBS(θ, ) represents the base station resource utilization rate, and α, β, γ, and δ are weighting coefficients used to balance the importance of different objectives.

[0111] Constraints: Physical limitations on beam direction angle and width, as well as the limited availability of base station resources.

[0112]

[0113]

[0114]

[0115] Where θmin and θmax represent the minimum and maximum values ​​of the beam direction angle, respectively. min and `max` represents the minimum and maximum beamwidth, respectively, PRBi(θ, () indicates the beam direction angle θ and width Below, CBS represents the number of PRBs occupied by the i-th terminal, where CBS represents the total number of PRBs in the base station, and M represents the number of terminals.

[0116] Optimization algorithm selection: Optimization algorithms can be chosen from sources such as genetic algorithms and particle swarm optimization (PSO). The following explanation uses PSO as an example. PSO searches for the optimal solution space by simulating the foraging behavior of bird flocks. The calculation process is as follows.

[0117] Initialize the particle swarm: Randomly generate a set of combinations of beam direction angle and width as particles, each particle having position and velocity attributes.

[0118] Velocity update: Update the particle velocity based on the individual optimal position and the group optimal position.

[0119]

[0120] Where vi(t) represents the velocity of the i-th particle at time t, ω represents the inertia weight, c1 and c2 represent learning factors, r1 and r2 represent random numbers, pbest,i represents the individual optimal position of the i-th particle, gbest represents the group optimal position, and xi(t) represents the position of the i-th particle at time t.

[0121] Position Update: Adjust the particle's position based on the updated velocity.

[0122]

[0123] Iterative optimization: Repeat the velocity update and position update steps until the termination condition is met.

[0124] 3) Adjustment strategy distribution The optimal beam orientation angle (θopt) and beam width are calculated by the algorithm. The opt) is used as the decision output of the control platform and sent to the corresponding terminal.

[0125] In special circumstances (such as receiving a specific terminal communication protection instruction from network administrators through the manual intervention submodule, or encountering an emergency such as a natural disaster that damages some base stations), the manual intervention submodule will prioritize handling these special needs, manually adjust the antenna beam direction of the relevant terminals to ensure the normal operation of important communications, and the adjusted parameters will also be updated to the policy database in sync, without affecting the subsequent automatic policy formulation process.

[0126] 1) Manual control strategy The control platform provides a web interface and includes the following functional modules: Terminal Status Panel: Displays information such as the current beam direction, traffic volume, and interference source direction of the selected terminal.

[0127] Manual adjustment panel: Provides a slider or numerical input box, supporting adjustments θ∈[0°,360°]. ∈[0°,90°]、Δ ∈[30°,120°] and frequency point f.

[0128] The manual command is sent through the base station. After receiving the command, the terminal immediately interrupts the automatic adjustment process, executes beam parameter configuration, and sends back a confirmation message. 2) Priority arbitration mechanism Manual Instructions > Automatic Strategy: When a manual instruction is issued, the terminal pauses automatic thread adjustment and prioritizes the execution of manual parameters.

[0129] Conflict resolution: If multiple instructions target the same terminal, the later instruction overrides the earlier instruction (Last WriteWins).

[0130] 3) Validity period management S108: Adjust the target beam according to the beam adjustment strategy.

[0131] Therefore, the beam adjustment mechanism in this application relies on the terminal's own algorithm design. Its implementation and design quality are constrained by the software design strategies of various manufacturers, leading to inconsistent adjustment effects in actual deployment. Furthermore, traditional terminals cannot perceive the overall network status, and beam direction adjustments can easily result in terminals concentrating on pointing at specific base stations, causing uneven capacity distribution among base stations, poor overall network communication performance, and low overall network resource utilization. This application's embodiment disruptively adopts a control platform as the execution entity for the beam adjustment strategy, uniformly managing the terminals' beams. This fundamentally avoids the problem of low wireless resource utilization efficiency caused by improper terminal beam adjustment, significantly improving overall network performance and user experience.

[0132] The terminal's beam direction design employs both adaptive and manual adjustment methods. In adaptive adjustment, the terminal periodically scans the network status, and the control platform generates access policies based on a multi-objective optimization algorithm, improving overall communication efficiency. In manual adjustment, the operator can directly adjust the terminal's beam direction, width, and frequency through the control platform's visual interface, providing QoS guarantees for sudden traffic surges and emergencies, and enhancing network emergency response capabilities.

[0133] Traditional beamforming strategies rely solely on signal strength and quality, lacking key feature parameters, resulting in low accuracy. The proposed implementation's control platform, based on acquired terminal and base station operational data, introduces an LSTM-Attention model to calculate the most suitable beamforming parameters for each terminal. This comprehensively considers information from the time, frequency, spatial, and service domains, and incorporates key feature parameters. The LSTM-Attention model algorithm can more accurately predict the most suitable beamforming direction for future time periods.

[0134] Figure 7 The diagram shows a structural schematic of a beam adjustment device provided in an embodiment of this application. The device 300 includes: an access module 310, a first determination module 320, a second determination module 330, and an adjustment module 340.

[0135] Access module 310 accesses the network and collects target information; first determination module 320 determines the beam direction corresponding to the terminal through beam scanning; second determination module 330 determines the data fusion result and beam adjustment strategy through the control platform; adjustment module 340 adjusts the target beam according to the beam adjustment strategy.

[0136] The process of determining the data fusion result and beam adjustment strategy through the control platform includes: Receive input parameters or commands; The data fusion result and beam adjustment strategy are determined based on the input parameters or instructions.

[0137] Optionally, the terminal accesses the network and collects target information, including: Network camping is performed using an omnidirectional antenna; Simultaneously record the channel quality and traffic load of the serving cell and neighboring cells; Initiate spatial spectrum scanning during periods of business downtime; Periodically detect the signal characteristics of base stations in all directions; A network state matrix is ​​constructed based on four-dimensional spatiotemporal frequency data through a control platform; By predicting the distribution of business traffic through machine learning models, a beam pointing strategy for a future time slot is generated for each terminal.

[0138] Optionally, determining the beam direction corresponding to the terminal through beam scanning includes: If no new service requests need to be processed within the predetermined service idle time and the previous service transmission has been completed for more than a certain period of time, the antenna beam scanning process is triggered. According to the preset beam scanning strategy, the antenna's azimuth angle and beamwidth are adjusted sequentially; For each beam direction and width combination, perform base station search, detect the base station signal pointing downwards by the beam, and measure and record the corresponding detection data; The processed detection data is sent to the control platform.

[0139] Optionally, determining the data fusion result and beam adjustment strategy through the control platform includes: The control platform determines the data fusion result and beam adjustment strategy based on the detection data and the received input parameters or instructions.

[0140] Optionally, receiving input parameters or instructions includes: Determine instruction priority; Receive operation logs.

[0141] The device 300 provided in this application embodiment can execute the methods described in the preceding method embodiments and achieve the functions and beneficial effects of the methods described in the preceding method embodiments, which will not be repeated here.

[0142] Figure 8The diagram illustrates the hardware structure of an electronic device implementing the embodiments of this application. Referring to the diagram, at the hardware level, the electronic device includes a processor and optionally, an internal bus, a network interface, and a memory. The memory may include RAM, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0143] The processor, network interface, and memory can be interconnected via an internal bus, which can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be categorized as an address bus, data bus, control bus, etc. For ease of illustration, only a single bidirectional arrow is used in this diagram, but this does not imply that there is only one bus or one type of bus.

[0144] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0145] The above is as stated in this application. Figure 1The methods disclosed in the illustrated embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0146] Therefore, the electronic device provided in the embodiments of this application can execute the methods described in the foregoing method embodiments and achieve the functions and beneficial effects of the methods described in the foregoing method embodiments, which will not be repeated here.

[0147] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0148] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0149] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0150] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0151] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0152] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part 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, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0153] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for adjusting a beam, comprising: The terminal accesses the network and collects target information; The beam direction corresponding to the terminal is determined by beam scanning; The data fusion results and beam adjustment strategies are determined through the control platform. Adjust the target beam according to the beam adjustment strategy.

2. The method according to claim 1, characterized in that, The process of determining the data fusion result and beam adjustment strategy through the control platform includes: Receive input parameters or commands; The data fusion result and beam adjustment strategy are determined based on the input parameters or instructions.

3. The method according to claim 1, characterized in that, The terminal accesses the network and collects target information, including: Network camping is performed using an omnidirectional antenna; Simultaneously record the channel quality and traffic load of the serving cell and neighboring cells; Initiate spatial spectrum scanning during periods of business downtime; Periodically detect the signal characteristics of base stations in all directions; A network state matrix is ​​constructed based on four-dimensional spatiotemporal frequency data through a control platform; By predicting the distribution of business traffic through machine learning models, a beam pointing strategy for a future time slot is generated for each terminal.

4. The method according to claim 1, characterized in that, The step of determining the beam direction corresponding to the terminal through beam scanning includes: If no new service requests need to be processed within the predetermined service idle time and the previous service transmission has been completed for more than a certain period of time, the antenna beam scanning process is triggered. According to the preset beam scanning strategy, the antenna's azimuth angle and beamwidth are adjusted sequentially; For each beam direction and width combination, perform base station search, detect the base station signal pointing downwards by the beam, and measure and record the corresponding detection data; The processed detection data is sent to the control platform.

5. The method according to claim 2, characterized in that, The process of determining the data fusion result and beam adjustment strategy through the control platform includes: The control platform determines the data fusion result and beam adjustment strategy based on the detection data and the received input parameters or instructions.

6. The method according to claim 2, characterized in that, The receiving of input parameters or instructions includes: Determine instruction priority; Receive operation logs.

7. A beam-adjusting device, comprising: The access module connects to the network and collects target information; The first determining module determines the beam direction corresponding to the terminal through beam scanning; The second determining module determines the data fusion results and beam adjustment strategy through the control platform; The adjustment module adjusts the target beam according to the beam adjustment strategy.

8. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, use the processor to perform the steps of the method for determining a scene graph as described in any one of claims 1-6.

9. A computer-readable medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the steps of the beam adjustment method according to any one of claims 1-6.

10. A computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, perform the steps of the beam adjustment method according to any one of claims 1-6.

Images