Antenna beamforming method, storage medium, electronic device, and computer program product

Abstract

Embodiments of the present disclosure provide an antenna beamforming method, a storage medium, an electronic device, and a computer program product. The method comprises: acquiring received signal strength information of an antenna array, and determining a target beam direction on the basis of the received signal strength information; on the basis of the target beam direction and a preset neural network model, determining a control signal parameter corresponding to the target beam direction; and on the basis of the control signal parameter, adjusting the amount of phase shift of a phase shift module connected to the antenna array, so as to control the phase or phase difference of a first transmitted signal of the antenna array, so that the antenna array performs beamforming in the target beam direction.

Description

Antenna beamforming methods, storage media, electronic devices, and computer program products

[0001] Cross-reference to related applications

[0002] This disclosure is based on and claims priority to Chinese Patent Application No. 2024114061930, filed on October 9, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of communications, and more specifically, to a beamforming method for an antenna, a storage medium, an electronic device, and a computer program product. Background Technology

[0004] When the terminal is too far from the base station or there are obstacles between the terminal and the base station, such as in subways, high-speed trains and parking garages, the received signal becomes unstable, resulting in a decrease in network speed or even network outage.

[0005] Currently, most mobile terminals support multi-antenna transmission and reception technology. This technology can improve receiver sensitivity. When a mobile terminal is in a weak signal environment, the transmitter first performs joint encoding on the data to reduce signal attenuation and noise interference, and then maps it to multiple antennas for transmission through space-time mapping. At the receiver, the received signals from each antenna are space-time decoded to restore the data. This improves reception sensitivity. At the same time, the base station can estimate channel parameters through the terminal's SRS, optimize downlink scheduling, and enhance connection stability. However, current terminal devices typically only perform uplink transmission on one antenna. Since each antenna operates independently, the overall antenna gain is not improved, thus limiting the improvement in connection distance.

[0006] There is currently no effective solution to the problem that when a terminal is too far from a base station or there are obstacles between the terminal and the base station, the base station cannot effectively receive the transmitted signal from the terminal, resulting in a decrease in the terminal's network speed or even a network outage. Summary of the Invention

[0007] This disclosure provides a beamforming method for an antenna, a storage medium, an electronic device, and a computer program product to at least solve the problem in the related art where the terminal's transmitted signal is blocked when the terminal is too far from the base station or when there are obstacles between the terminal and the base station, resulting in a decrease in the terminal's network speed or even a network outage.

[0008] According to one embodiment of this disclosure, a beamforming method for an antenna is provided, comprising:

[0009] The system acquires the received signal strength information of the antenna array and determines the target beam direction based on the received signal strength information. Based on the target beam direction and a preset neural network model, it determines the control signal parameters corresponding to the target beam direction. Based on the control signal parameters, it adjusts the phase shift of the phase shift module connected to the antenna array, thereby controlling the phase or phase difference of the first transmitted signal of the antenna array so that the antenna array can be beamformed in the target beam direction.

[0010] According to yet another embodiment of this disclosure, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0011] According to yet another embodiment of this disclosure, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0012] According to yet another embodiment of this disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps in any of the above method embodiments. Attached Figure Description

[0013] Figure 1 is a hardware structure block diagram of the mobile terminal operating in the embodiments of the method disclosed herein;

[0014] Figure 2 is a block diagram of a MIMO antenna feeding system according to an embodiment of the present disclosure;

[0015] Figure 3 is a flowchart of a beamforming method for an antenna according to an embodiment of the present disclosure;

[0016] Figure 4 is a BP neural network structure diagram according to an embodiment of the present disclosure;

[0017] Figure 5 is a structural block diagram of a phase shift module according to an embodiment of the present disclosure;

[0018] Figure 6 is a schematic diagram of the S-parameters of a 90-degree bridge of a branch line coupler according to an embodiment of the present disclosure;

[0019] Figure 7 is a structural block diagram of a reflective phase shifter according to an embodiment of the present disclosure;

[0020] Figure 8 is a schematic diagram of the beamforming control process of an antenna according to an embodiment of the present disclosure;

[0021] Figure 9 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0022] The embodiments of this disclosure will be described in detail below with reference to the accompanying drawings and examples.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0024] To address the technical problem of unstable signal reception and even network outages caused by the terminal being too far from the base station or by obstacles between the terminal and the base station, such as in subways, high-speed trains, and parking garages, this disclosure proposes a beamforming method for an antenna. The technical concept involves calculating the required target beam direction and the control voltage needed to achieve it. By controlling the phase shift of the phase shift module using the control voltage, the phase of different phase signals is adjusted, enabling the antenna array to form a beam in the target beam direction. This improves the terminal antenna gain, enhancing signal reception and transmission performance, especially in weak signal environments. This solves the problem of unstable received signals, reduced network speed, and even network outages in related technologies when the terminal is too far from the base station or when obstacles exist between the terminal and the base station.

[0025] The method embodiments provided in this disclosure can be executed in a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, FIG1 is a hardware structure block diagram of a mobile terminal running in the method embodiments of this disclosure. As shown in FIG1, the mobile terminal may include one or more (only one is shown in FIG1) processors 102 (processor 102 may include, but is not limited to, processing devices such as microprocessors MCUs or programmable logic devices FPGAs) and a memory 104 for storing data. The mobile terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that the structure shown in FIG1 is only illustrative and does not limit the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than shown in FIG1, or have a different configuration than shown in FIG1.

[0026] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the antenna beamforming method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0028] Figure 2 is a block diagram of a MIMO antenna feeding system according to an embodiment of the present disclosure. The embodiment of the present disclosure can operate on the system architecture shown in Figure 2. As shown in Figure 2, the system architecture includes: a phase shift module, a multiple-in-multiple-out (MIMO) antenna array, a beamforming module, and an AI parameter controller. The functions and interaction relationships of the phase shift module, MIMO antenna array, beamforming module, and AI parameter controller are as follows:

[0029] The phase shift module can be used to decompose the conducted signal output from the RF front end (i.e. the input signal to the phase shift module) into multiple equal-amplitude, out-of-phase signals through corresponding phase shifting operations, and then feed them to the MIMO antenna array.

[0030] MIMO antenna arrays can be used to transmit multiple equal-amplitude, out-of-phase signals, after phase shifting, along the target direction. This achieves beamforming of the transmitted signals along the target beam direction and provides the received signal strength to the beamforming module. A MIMO antenna array can include multiple antenna elements, each capable of transmitting and receiving radio frequency signals. By supplying signals of different phases through the phase shifting module, the MIMO antenna can achieve beamforming along the target beam direction, enhancing the signal strength in that direction. This maintains network connection stability and improves data transmission rates in weak signal environments.

[0031] The beam calculation module can be used to obtain the received signal strength of the MIMO antenna array (e.g., Received Signal Strength Indication (RSSI) / Reference Signal Receiving Power (RSRP)) and other related parameters (such as antenna gain, antenna relative position, etc.) to calculate the target beam direction, and send the calculated target beam direction as a parameter to the AI ​​parameter controller.

[0032] The AI ​​parameter controller can output control signals based on the target beam direction and other relevant parameters provided by the beam calculation module. The control signals can be used to control the phase shift module to dynamically adjust the phase shift of the signal, thereby achieving phase control and precise adjustment of the beam direction of the MIMO antenna.

[0033] The beam calculation module can determine the direction of the beam to be generated. Its hardware can be implemented using existing receiving antennas, radio frequency front-end devices, demodulation chips, etc. in the terminal device.

[0034] AI parameter controllers can use deep neural networks (such as BP neural networks) to map the relationship between physical parameters, the phase shift amount of the phase shift module, and the beamforming direction. During operation, the AI ​​parameter controller can calculate the control signal for controlling the phase shift amount of the phase shift module based on the target beam direction provided by the beam calculation module and related hardware and signal parameters (such as antenna directivity, signal frequency, network environment parameters, etc.), so as to precisely adjust the beam direction.

[0035] AI parameter controllers can be implemented using feedforward neural networks, feedback neural networks, or graph neural networks, including but not limited to the following technologies: CNN convolutional neural networks, BP neural networks, RNN recurrent neural networks, Hopfield networks, Boltzmann machines, etc.

[0036] This embodiment provides a beamforming method for an antenna operating on the above-described mobile terminal or system architecture. Figure 3 is a flowchart of the beamforming method for an antenna according to an embodiment of this disclosure. As shown in Figure 3, the process may include the following steps:

[0037] Step S301: Obtain the received signal strength information of the antenna array, and determine the target beam direction based on the received signal strength information.

[0038] For example, the locations of high and low received signal strength can be determined based on the received signal strength information of the antenna array, thereby determining the beam direction to be generated. The beam direction can be from the location of low received signal strength to the location of high received signal strength.

[0039] In one exemplary embodiment, determining the target beam direction based on the received signal strength information includes:

[0040] Determine the uplink and downlink communication modes of the received signals for each antenna element of the antenna array;

[0041] According to the uplink and downlink communication mode of the received signal, the received signal strength information at the location of each antenna element is corrected;

[0042] The target beam direction is determined based on the corrected received signal strength information.

[0043] As an example, in order to more accurately evaluate the performance of the antenna during transmission, the received signal strength at the antenna array can be corrected for different uplink and downlink communication methods. Based on the corrected received signal strength, the target beam direction can be calculated, which can yield a more accurate target beam direction, thereby improving the accuracy and reliability of beamforming.

[0044] As an example, received signal strength information may include at least one of the following: Received Signal Strength Indication (RSSI) and Reference Received Signal Strength (RSRP).

[0045] As an example, uplink and downlink communication methods may include, but are not limited to, Frequency Division Duplexing (FDD) and Time Division Duplexing (TDD).

[0046] The following uses FDD and TDD uplink and downlink communication methods as examples to further explain the correction process of received signal strength information in the embodiments of this disclosure:

[0047] In one exemplary embodiment, the received signal strength information is used to indicate the signal strength value of the received signal, and the step of correcting the received signal strength information at each antenna element location according to the uplink / downlink communication mode of the received signal includes:

[0048] For each antenna element, when the uplink and downlink communication mode of the received signal is time-division duplex communication, the signal strength value is subtracted from the preset antenna receiving efficiency of the antenna element to obtain the corrected received signal strength information; or,

[0049] When the uplink and downlink communication mode of the received signal is frequency division duplex communication, the efficiency difference between the preset antenna receiving efficiency and the preset antenna transmitting efficiency is determined, and the signal strength value is subtracted from the preset antenna receiving efficiency of the antenna element and the efficiency difference to obtain the corrected received signal strength information.

[0050] As an example, antenna efficiency refers to an antenna's ability to convert input radio frequency power into radiated power, reflecting its performance. Antenna efficiency typically doesn't reach 100%, so in practical applications, the signal strength received by an antenna is affected by its own efficiency. If the RSRP / RSSI values ​​are used directly to determine beam direction without considering antenna efficiency, then an antenna element with a high signal strength might simply have higher efficiency, rather than truly high signal strength. Therefore, to eliminate differences in antenna efficiency and ensure accurate beam direction determination, the influence of the antenna efficiency of each individual antenna element can be removed from its signal strength value. Antenna efficiency can be obtained beforehand from an experimental environment.

[0051] As an example, for a TDD band received signal, after receiving the signal, the terminal can demodulate the signal strength value (e.g., RSSI or RSRP) received by each antenna element, subtract its own antenna receiving efficiency from the signal strength value received by the antenna element, and obtain the corrected signal strength value at the location of each antenna element (i.e., the actual signal strength value at the location of each antenna element). Thus, the direction of the beam to be generated can be determined based on the signal strength value at the location of each antenna element.

[0052] As an example, in an FDD system, signals are transmitted and received using different frequencies, meaning that antenna elements have different performance in the transmission and reception bands. Antenna efficiency typically depends on its operating frequency; therefore, the efficiency of the same antenna element when transmitting signals differs from its efficiency when receiving signals.

[0053] For example, if antenna element 1 has low efficiency in the transmission frequency band but high efficiency in the reception frequency band, then when calculating the received signal strength, the strength value of antenna element 1 will reflect its higher efficiency in the reception frequency band, without removing its low efficiency in the transmission frequency band. This will lead to the mistaken assumption that antenna element 1 performs better than the actual performance in all directions when calculating the target beam direction, resulting in incorrect beam pointing.

[0054] To accurately evaluate antenna performance during transmission, the received signal strength value can be corrected. This can be done by subtracting the preset antenna receiving efficiency of the antenna elements, and then further subtracting the difference between the receiving and transmitting efficiency. In other words, the actual efficiency of the antenna elements in the transmission frequency band is considered during the calculation. This ensures that the beamforming module can calculate the beam direction based on the true efficiency of all antenna elements in the transmission frequency band, thereby improving the accuracy and reliability of beamforming.

[0055] In one exemplary embodiment, determining the target beam direction based on the corrected received signal strength information includes:

[0056] The received signal strength information at each of the corrected antenna element locations is analyzed to determine the locations of the highest and lowest signal strength values.

[0057] The direction from the location of the lowest signal strength value to the location of the highest signal strength value is determined as the target beam direction.

[0058] As an example, after calibration, the received signal strength information at each antenna element location can be compared and analyzed to determine the maximum and minimum signal strength values. For example, this can be achieved by comparing the RSSI or RSRP values ​​of the received signals from each antenna element.

[0059] As an example, the target beam direction can be determined based on the extreme values ​​of the antenna's received signal strength. The beam should be pointed towards the location with the highest signal strength to enhance signal reception at that location while minimizing the impact of the location with the lowest signal strength, thereby improving overall signal quality.

[0060] As an example, in practical applications, the direction from the location with the highest signal strength to the location with the lowest signal strength can be the location of the base station or an area with historically good signal quality. Especially in extreme cases where all antennas cannot receive a signal, the location of previously good signal strength can be calculated using gyroscopes and displacement sensors for backtracking.

[0061] For example, if all antenna elements of the antenna array cannot receive a signal, the area where there was a previous signal connection can be calculated based on the gyroscope and displacement sensor, and the generated beam direction can be directed towards that area.

[0062] In one exemplary embodiment, it further includes:

[0063] The channel parameter information of each antenna element is obtained, and the channel attenuation value of each antenna element is determined based on the channel parameter information;

[0064] Calculate the difference between the channel attenuation value of the target antenna element and the channel attenuation value of each antenna element other than the target antenna element;

[0065] If the difference is greater than a preset difference threshold, it is determined that the received signal strength information of the target antenna element is not used for determining the target beam direction.

[0066] As an example, the target beam direction can be adjusted based on channel parameter information. This channel parameter information can be obtained from base station scheduling information and includes, but is not limited to, channel attenuation information, transmission phase information, multipath fading information, and interference information. For instance, when an object blocks a certain antenna element, the channel attenuation value of that antenna element will be significantly increased compared to other antenna elements. In this case, the target beam pointing towards that antenna element's location can be excluded.

[0067] As an example, the channel attenuation value of the target antenna element can be calculated as the difference between the channel attenuation value of each antenna element other than the target antenna element. If the difference is greater than a preset difference threshold, the beam pointing of the target antenna element can be excluded and not used for determining the target beam direction.

[0068] Step S302: Determine the control signal parameters corresponding to the target beam direction based on the target beam direction and the preset neural network model.

[0069] For example, the target beam direction can be input into a pre-trained neural network model to obtain the control signal parameters corresponding to the target beam direction output by the pre-trained neural network model. The control signal parameters can be used to control the phase shift amount of the phase shift module.

[0070] As an example, the types of preset neural network models may include, but are not limited to, CNN convolutional neural networks, BP neural networks, RNN recurrent neural networks, Hopfield networks, Boltzmann machines, etc.

[0071] In one exemplary embodiment, determining the control signal parameters corresponding to the target beam direction based on the target beam direction and a preset neural network model includes:

[0072] Obtain the current model parameter information, and determine the control signal parameters corresponding to the target beam direction based on the target beam direction, the preset neural network model, and the model parameter information;

[0073] The model parameter information includes the relative position of the antenna elements, the type of modulation signal, and the preset antenna element directivity function.

[0074] As an example, a pre-defined antenna element directivity function can be used to indicate the relative magnitude of the antenna element's radiated field in various directions, describing the relative distribution of the antenna's radiated field in space; the antenna element directivity function can be measured in advance in an anechoic chamber.

[0075] As an example, when a mobile terminal is in a weak signal environment, the goal of beamforming is to concentrate the signal transmission in a specific direction to improve gain. The input of the directivity function helps the model understand how the individual antenna elements work together to achieve maximum gain in the target beam direction.

[0076] As an example, the relative position of antenna elements can refer to the relative positions between individual antenna elements. For instance, one antenna element in the antenna array can be selected as the reference antenna, and the relative position of the antenna elements is the position of the remaining antenna elements relative to the radiation center of the reference antenna. The relative positions between different antenna elements in the antenna array can affect the calculation of the phase difference of the phase shift module, and thus affect the direction of beamforming.

[0077] As an example, the type of modulation signal can include, but is not limited to, Binary Phase Shift Keying (BPSK), Quadrature Phase Shift Keying (QPSK), Orthogonal Frequency Division Multiplexing (OFDM), etc. Signals with different modulation types have different spatial radiation characteristics.

[0078] As an example, different modulation signal types (such as BPSK, QPSK, OFDM, etc.) have different spectral and temporal characteristics, which can affect the phase change and amplitude attenuation of the antenna transmitted signal during transmission. For instance, precise phase control is particularly important for wide-bandwidth OFDM signals because the broad spectrum leads to phase distortion in different frequency components, thus affecting signal demodulation. Therefore, using the modulation signal type as input can help the model learn how to adjust the phase according to a specific signal type to reduce phase distortion and maintain signal integrity, thereby achieving optimal beamforming.

[0079] As an example, the control signal parameter in this embodiment of the present disclosure can be a control voltage. The above-mentioned model parameter information and target beam direction can be input into a preset neural network model to obtain the control voltage output by the preset neural network model. The phase shift amount of the phase shift module can be adjusted according to the output control voltage.

[0080] In one exemplary embodiment, the model parameter information further includes at least one of the following: antenna element gain, antenna element received signal strength, electrical length and insertion loss of the conducted signal to each antenna port, modulation signal frequency and bandwidth, network environment parameters, and received signal-to-noise ratio.

[0081] As an example, antenna element gain can be represented as the ratio of the radiated power density produced by the antenna to that of an ideal omnidirectional antenna at the same location in space. Similar to the directivity function, it characterizes the strength of the antenna's directivity.

[0082] As an example, the signal strength received by an antenna element can indicate the average signal strength (RSSI) received by the terminal device receiver. The RSSI received by each antenna is different, and different network standards and signal bandwidths define the strength of RSSI differently.

[0083] As an example, the electrical length and insertion loss of the signal transmitted to each antenna port are different because the signal path and loss from the power amplifier to each antenna element are different, resulting in different phase shifts and amplitude attenuations. Therefore, the electrical length Len (line) and insertion loss Loss (line) can be used as parameters to characterize the differences in hardware circuits.

[0084] As an example, the modulation signal frequency and bandwidth can be used as input parameters for neural network models. Signals of different frequencies will produce different phase shifts when passing through the same length of transmission line. For signals with large bandwidth, phase distortion is more likely to occur.

[0085] As an example, network environment parameters may include channel attenuation information, transmission phase information, multipath fading information, and interference information obtained from the base station.

[0086] As an example, the signal-to-noise ratio (SNR) of a received signal can represent the ratio of the useful signal strength to the noise strength. It can be demodulated and calculated by a demodulation chip and can be used as a parameter characterizing signal quality.

[0087] In one exemplary embodiment, before obtaining the current model parameter information, the method further includes:

[0088] Obtain historical target beam directions, historical model parameter information, and the true values ​​of control signal parameters corresponding to the historical target beam directions;

[0089] Using the historical target beam direction and the historical model parameter information as inputs to a preset initial neural network model, the predicted values ​​of the control signal parameters output by the initial neural network model are obtained.

[0090] The model loss function is determined based on the true values ​​of the control signal parameters and the predicted values ​​of the control signal parameters.

[0091] The initial neural network model is iteratively trained according to the model loss function to adjust the weight coefficients of the initial neural network model, and the trained preset neural network model is obtained when the model loss function meets the convergence condition.

[0092] As an example, this disclosure uses a backpropagation (BP) neural network to illustrate the model training process before obtaining the current model parameter information:

[0093] For example, Figure 4 is a BP neural network structure diagram according to an embodiment of the present disclosure. As shown in Figure 4, the BP neural network structure may include an input layer, an output layer and multiple hidden layers.

[0094] Historical target beam directions, historical model parameter information (such as preset antenna element directivity functions, relative positions of antenna elements, modulation signal types, etc.) and true values ​​of control signal parameters corresponding to historical target beam directions can be obtained from the system's records (for example, the voltage values ​​Vα, Vβ, and Vγ required to adjust the phase shifter in practical applications, where Vα, Vβ, and Vγ are used to adjust the phase shift amount of different phase shifting units in the phase shifting module, respectively).

[0095] Initialize the BP neural network model (i.e., the preset initial neural network model). The BP neural network model includes an input layer, an output layer, and multiple hidden layers in between. Initial values ​​can be randomly assigned to the neurons and weight coefficients ω(F(z)) in each layer.

[0096] Using historical target beam directions and historical model parameter information from historical data as input, the forward propagation algorithm is used to calculate the values ​​of latent variables at each layer until the final predicted values ​​of control signal parameters (e.g., predicted control voltage values ​​V1α, V1β, V1γ) are obtained. The predicted values ​​are calculated based on the current weighting coefficient ω(F(z)) and can represent the predicted control signal parameters of the system under the current model parameter configuration.

[0097] A loss function measures the difference between the model's predicted values ​​(V1α, V1β, V1γ) and the true values ​​(Vα, Vβ, Vγ) of the control signal parameters in historical data. For example, the loss function can be the mean squared error (MSE) between the predicted and true values. The smaller the value of the loss function, the closer the model's predictions are to reality, and the better the model's performance.

[0098] After obtaining the loss function, iterative model training can be performed. As shown in Figure 4, the error can be propagated from the output layer to the input layer using the backpropagation algorithm. During backpropagation, the weight coefficients ω(F(z)) of each neuron can be adjusted using gradient descent to minimize the value of the loss function. The training process will repeatedly execute forward and backward propagation until the model loss function meets the convergence condition, i.e., the change in the loss function value is less than a preset threshold, or the preset number of training epochs is reached.

[0099] After training, the trained neural network model has adjusted its weight coefficients ω(F(z)) based on historical data, ensuring that, for input historical target beam direction and model parameter information, the predicted values ​​of the control signal parameters output by the model approximate the true values ​​of the control signal parameters in the historical data as closely as possible. In other words, the neural network model has learned how to precisely control the phase shift module based on the input parameters to achieve optimal beamforming performance.

[0100] Through the above process, the BP neural network continuously adjusts its internal parameters to adapt to changes in antenna characteristics and signal environment in the system, ultimately providing a highly accurate prediction of control signal parameters. In practical use, this enables the phase shifter to be controlled quickly and accurately, achieving precise beam pointing of terminal equipment in weak signal environments and improving communication quality and stability.

[0101] Step S303: Adjust the phase shift of the phase shift module connected to the antenna array according to the control signal parameters, thereby controlling the phase or phase difference of the first transmitted signal of the antenna array so that the antenna array can be beamformed in the target beam direction.

[0102] As an example, phase shift refers to the change in the phase of a signal during transmission. In radio frequency communication systems, such as antenna arrays and beamforming technologies, when electromagnetic signals are transmitted through transmission lines or between different elements of an antenna array, the arrival time of the signal at each antenna element varies due to differences in transmission path length, thus causing a phase shift. This phase shift can be controlled and adjusted using phase shifters to control the beam direction.

[0103] As an example, by controlling the signal phase shift of each antenna element, the antenna array can form a main lobe (i.e., the direction with the strongest signal) in a specific direction, while forming side lobes or suppressing the signal in other directions, thereby achieving directional transmission of the signal, enhancing the strength of the received signal, and improving communication quality.

[0104] According to the embodiments of this disclosure, the phase shift of the phase shift module can be adjusted according to the control signal parameters output by the neural network model, such as the control voltage. In turn, the phase or phase difference of the first transmitted signal of the antenna array can be adjusted according to the phase shift to achieve beamforming in the target beam direction and improve the efficiency and stability of signal transmission.

[0105] In one exemplary embodiment, the phase shift module includes a plurality of cascaded phase shift units, each of the phase shift units including a first coupler and a phase shifter, the first coupler and the phase shifter being electrically connected;

[0106] The step of adjusting the phase shift of the phase shift module connected to the antenna array according to the control signal parameters, thereby controlling the phase or phase difference of the first transmitted signal of the antenna array, includes:

[0107] The first coupler divides the input signal into multiple second transmitted signals with different phases.

[0108] According to the control signal parameters, the phase shift of the phase shifter is adjusted, and the phase shifter is controlled to adjust the phase of the plurality of second transmitted signals with different phases or the phase difference between the plurality of second transmitted signals according to the phase shift, so as to obtain a plurality of first transmitted signals with different phases after adjustment;

[0109] The first coupler feeds the plurality of first transmitted signals to the corresponding antenna elements of the antenna array.

[0110] As an example, a phase-shifting module may include multiple cascaded phase-shifting units, each of which may include a first coupler and a phase shifter, the coupler and the phase shifter being electrically connected. The type of the first coupler in this embodiment may include, but is not limited to, a branch-line coupler, a microstrip line coupler, a waveguide coupler, a ring coupler, a directional coupler, etc.; the type of phase shifter may include, but is not limited to, a mechanical phase shifter, a voltage-controlled phase shifter, a microwave solid-state phase shifter, a reflective phase shifter, a distributed phase shifter, etc.

[0111] This disclosure uses a branch-line coupler as the first coupler and a reflective phase shifter as an example for illustration.

[0112] As an example, multiple phase-shifting units in this embodiment are connected in a cascaded manner, with each phase-shifting unit consisting of a branch-line coupler and a reflective phase shifter. In the phase-shifting module, the output port of the branch-line coupler can be connected to the input port of the reflective phase shifter, and the output port of the reflective phase shifter can be fed back to the reflection port of the branch-line coupler, forming a closed-loop signal path. The connection method between the branch-line coupler and the reflective phase shifter ensures that the phase change of the signal through the reflective phase shifter can affect the output signal of the branch-line coupler, thereby affecting the overall phase distribution of the phase shift.

[0113] As an example, a branch-line coupler is a directional coupler with a 90-degree phase shift, which can be used to split an input signal (i.e., the conducted signal in Figure 2) into two outputs, with the two output signals (i.e., the second transmitted signal) having a 90-degree phase difference. In a phase-shifting module, the branch-line coupler can be used as the basic unit for signal distribution. After the first input signal enters from the input terminal, it is split into two paths by the branch-line coupler, and each path is then connected to a reflective phase shifter.

[0114] As an example, a reflective phase shifter can change the phase of a signal by controlling an internal varactor diode. In a reflective phase shifter, the input signal interacts with a circuit with a variable capacitance value. This circuit is typically designed as a reflective circuit, so the signal will have a different phase after reflection. The capacitance value of the varactor diode can be adjusted by an applied voltage, thereby changing the phase shift of the reflective phase shifter.

[0115] For example, Figure 5 is a structural block diagram of a phase shifting module according to an embodiment of the present disclosure. Taking a 4-antenna array as an example, as shown in Figure 5, the phase shifting module can be composed of multiple cascaded phase shifting units. Each phase shifting unit may include a branch-line directional coupler (branch-line coupler, 90-degree bridge) and a reflective phase shifter. The cascaded structure of the phase shifting units in the embodiments of the present disclosure allows the input signal to be distributed and phase shifted multiple times, ultimately forming multiple signals with specific phase differences (as shown in Figure 5, four signals with specific phase differences are formed).

[0116] As shown in Figure 5, the two output terminals of phase shifting unit 1 are connected to the input terminals of phase shifting unit 2 and phase shifting unit 3, respectively. The two output terminals of phase shifting unit 2 and the two output terminals of phase shifting unit 3 are connected to the corresponding antenna units. In this way, through the cascaded network, the input signal is divided into four paths, and each path of the signal will undergo different phase adjustments, thereby realizing the beamforming of the antenna.

[0117] A branch-line coupler can split an input signal into two signals with a 90° phase difference. This 90° bridge allows the signal to be evenly distributed across two distinct output paths, while simultaneously introducing a phase difference to form a beam.

[0118] For example, Figure 6 is a schematic diagram of the S-parameters of a 90-degree bridge of a branch line coupler according to an embodiment of the present disclosure. The S-parameters (i.e., scattering parameters) can be mathematical models describing the reflection and transmission behavior of signals in a multi-port network. As shown in Figure 6, for a branch line coupler, the S-parameters may include [S11], [S21], [S31], and [S41], where [S11] = [-∞], [S21] = [-3db∠-90°], [S31] = [-3db∠-180°], and [S41] = [-∞].

[0119] Wherein, S11 represents the voltage reflection coefficient of input port 1, that is, the ratio of reflected power to incident power of input port 1; S21, S31, and S41 represent the voltage transmission coefficients to ports 2, 3, and 4 respectively when there is a signal input at port 1.

[0120] A reflective phase shifter can control the signal phase by adjusting the capacitance of its internal varactor diode. The capacitance of the varactor diode is affected by the control voltage; changes in voltage cause changes in capacitance, which in turn cause a change in phase. As shown in Figure 5, control voltages Vα, Vβ, and Vγ can be used to adjust reflective phase shifter 1, reflective phase shifter 2, and reflective phase shifter 3, respectively.

[0121] It should be noted that Figure 5 of this embodiment shows an antenna array with 4 antenna elements, which is only one example of this embodiment. The method of this embodiment can support antenna arrays with more or fewer antenna elements. For example, based on the hardware design in Figure 5, the number of cascaded phase shifting units can be increased to support 6 antennas, 8 antennas or more.

[0122] In this embodiment of the disclosure, the phase shift of the phase shifter can be dynamically controlled by the AI ​​parameter controller according to parameters such as the target beam direction and signal type to ensure that the signal phase meets the requirements of beamforming.

[0123] The following further explains the process of feeding signals to the antenna array, which may include the following steps:

[0124] 1) The conducted signal can be used as the input signal to the first-stage coupler, and the first-stage coupler will split it into two second transmission signals;

[0125] 2) Each of the two second transmitted signals is processed by a reflective phase shifter, wherein the phase shift amount of the reflective phase shifter can be adjusted by the voltage output by the AI ​​parameter controller;

[0126] 3) The phase-shifted signal can be distributed to the next stage coupler. This process is repeated until four first transmission signals with different phases are obtained after being adjusted by each stage of the phase-shifting unit. The four first transmission signals with different phases can be distributed to all four antenna elements respectively.

[0127] 4) Throughout the process, the AI ​​parameter controller can dynamically adjust the phase shift of each phase shifter according to the control voltage output in the target beam direction, so as to meet the required angle and direction of the beam in space.

[0128] 5) The four first transmission signals that are finally formed each have a specific phase difference related to the target beam direction and are fed to each antenna element of the antenna array respectively.

[0129] The above steps allow for precise control of the signal phase, enabling the antenna array to form the main beam in the desired direction, thereby improving signal transmission efficiency and communication quality.

[0130] In one exemplary embodiment, the phase shifter includes a second coupler and varactor diodes respectively connected to the through terminal and the coupling terminal of the second coupler; adjusting the phase shift of the phase shifter includes:

[0131] The phase shift of the phase shifter is adjusted by adjusting the capacitance values ​​of the varactor diodes connected to the through end and the coupling end of the second coupler, respectively.

[0132] As an example, a phase shifter may include a varactor diode connected to the through end and the coupling end of a second coupler, respectively.

[0133] The pass-through port serves as a path for both signal input and output. When a signal enters the second coupler from the input port, it can be transmitted through the pass-through port without being coupled to other ports. The pass-through port can be connected to a varactor diode in the phase shifter. By changing the capacitance value of the varactor diode, the phase of the signal passing through the pass-through port is changed, thereby achieving the phase shift function.

[0134] The coupling terminal can be used to extract a portion of the signal from the through path. In a coupler, there is a certain phase difference between the signal at the coupling port and the signal at the through port. This phase difference is determined by the design of the second coupler (such as coupling degree, physical dimensions, etc.). The coupling terminal can also be connected to a varactor diode of a phase shifter. By controlling the varactor diode at the coupling port, the phase of the signal coupled to that port can be changed, and the phase shift of the phase shifter can be further adjusted.

[0135] For example, Figure 7 is a block diagram of a reflective phase shifter according to an embodiment of the present disclosure. As shown in Figure 7, the reflective phase shifter may include a Lange coupler (i.e., a second coupler) and two varactor diodes. The Lange coupler is a commonly used component in microwave / RF circuits, which couples a portion of the energy of an input signal to an adjacent transmission line. The Lange coupler includes two ports: a through port and a coupled port. In Figure 7, the input signal enters from the input port of the Lange coupler, with a portion transmitted through the through port and the other portion transmitted through the coupled port.

[0136] A varactor diode, as a nonlinear element, has a capacitance that changes with the voltage applied across its terminals. In the reflective phase shifter shown in Figure 7, varactor diodes are connected to both the through-terminal and coupling terminals of the coupler. This means that the varactor diodes can change the phase of the coupler's output signal by altering their capacitance. When a voltage is applied to the varactor diode, its capacitance changes, affecting the signal path through the through-terminal and coupling terminals, thus causing a change in the signal phase.

[0137] As shown in Figure 7, a varactor diode can be equivalent to a series connection of internal resistance, controlled capacitance, and self-inductance. Assuming the effects of internal resistance and self-inductance are ignored, the varactor diode can be equivalent to a voltage-controlled capacitor. For example, the adjustable capacitance range of the varactor diode can be from 10... -1 Up to 10pF.

[0138] In this embodiment, by acquiring the received signal strength information of the antenna array, the target beam direction is determined based on the received signal strength information; based on the target beam direction and a preset neural network model, the control signal parameters corresponding to the target beam direction are determined; the phase shift of the phase shift module connected to the antenna array is adjusted according to the control signal parameters, thereby controlling the phase or phase difference of the first transmitted signal of the antenna array, so that the antenna array beamforms in the target beam direction. This solves the problem in related technologies where the received signal is unstable, the network speed decreases, or even the network is disconnected when the terminal is too far from the base station or when there are obstacles between the terminal and the base station. It greatly improves the antenna performance of the terminal device, optimizes the network connection stability and data throughput of the terminal device in weak signal scenarios, increases the communication distance of the terminal device, improves the satellite communication performance of the terminal device, optimizes network coverage and signal quality, and improves the overall performance of the terminal communication system.

[0139] The following example further illustrates the control flow of the antenna beamforming method according to an embodiment of this disclosure.

[0140] Example 1

[0141] For example, Figure 8 is a schematic diagram of the beamforming control process of an antenna according to an embodiment of the present disclosure. As shown in Figure 8, it may specifically include the following steps:

[0142] 1) Software initialization, setting initial phase shift values;

[0143] For example, when the device is started or the software is activated, an initialization operation can be performed first to set the initial parameters of the antenna feeding system, which may include the initial weights of the neural network in the AI ​​parameter controller and the initial phase shift value of the variable phase shift, etc.

[0144] For example, the initial phase shift value can be set based on the device's initial beam direction or antenna configuration so that the system can react quickly after receiving a signal and adjust to the optimal signal reception state.

[0145] 2) Determine whether a useful signal can be received;

[0146] For example, the signal strength in the surrounding environment can be monitored by an antenna array to determine whether there is a useful signal with sufficient strength to be received; if a signal can be received, step 3) can be executed; if a useful signal cannot be received (e.g., the signal is too weak or there is no signal), step 5 can be executed.

[0147] 3) If a useful signal is received, read the receiving antenna RSSI / RSRP and channel parameter information:

[0148] For example, when a useful signal is received, the received signal strength of each antenna element, such as RSSI or RSRP, can be read, as well as channel parameter information obtained from the base station, such as attenuation, phase, multipath information, and interference.

[0149] This information can be used to calculate the actual signal strength distribution and environmental impact, providing data support for subsequent beam direction calculations.

[0150] 4) Calculate the target beam direction based on the channel parameter information;

[0151] For example, the optimal beam direction, i.e. the direction in which the signal is most stable and has the highest intensity, can be calculated by analyzing the channel parameter information obtained above.

[0152] 5) If no useful signal is received, the beam direction is estimated based on the displacement sensor;

[0153] For example, if a useful signal of sufficient strength cannot be received, displacement sensor and gyroscope data on the terminal device can be used to estimate the best direction in which the signal may exist based on the device's direction of movement and historical signal reception.

[0154] 6) The AI ​​parameter controller calculates the beam direction;

[0155] For example, the AI ​​parameter controller can calculate the corresponding control voltage, such as the control voltages Vα, Vβ, and Vγ in Figure 5, based on all the information collected in steps 1) to 5) above, including the target beam direction, antenna directivity function, antenna relative position, signal strength, hardware circuit difference parameters, signal type, frequency and bandwidth, and network environment parameters, through a trained neural network model.

[0156] The control voltage can be used to adjust the capacitance value of the varactor diode in the variable phase shift, thereby precisely controlling the phase of the antenna array and generating the target beam direction.

[0157] 7) The phase shift module outputs a feed signal to generate a beam in the target beam direction and executes step 2:

[0158] For example, after receiving the control voltage output by the AI ​​parameter controller, the phase shift module can divide and adjust the phase of the signal output by the RF front end by adjusting the phase shift amount of each phase shift unit, and finally generate four equal-amplitude, out-of-phase signals to supply the antenna.

[0159] For example, the generated beam can be further adjusted or optimized based on the calculated target beam direction to improve signal reception and transmission efficiency and enhance communication performance.

[0160] After this step is completed, you can return to step 2) to continue monitoring the signal reception, forming a closed-loop control, adjusting the beam direction in real time to cope with environmental changes, and maintaining stable and efficient signal transmission.

[0161] The control flow in Example 1 is a dynamic, cyclical process that can be automatically triggered and adjusted during operation. The beamforming module continuously calculates new target beam directions, processes them through an AI model, and outputs multiple control voltages. These voltages control the capacitance values ​​of the corresponding varactor diodes in the phase-shifting module. The phase-shifting module then conducts signal power division and phase shifting into multiple signals with different phase differences, which are fed to the corresponding antenna elements. This ultimately achieves beamforming of the target beam direction, resulting in good antenna gain and precise beam pointing. This ensures that the device can continuously optimize antenna performance in different communication environments, achieving optimal signal reception and transmission.

[0162] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to 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 disclosure, 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 device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this disclosure.

[0163] Embodiments of this disclosure also provide a computer-readable storage medium storing a computer program configured to perform the steps in any of the above method embodiments when executed.

[0164] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0165] Figure 9 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. As shown in Figure 9, an embodiment of the present disclosure also provides an electronic device 90, including a memory 901 and a processor 902. The memory 901 stores a computer program, and the processor 902 is configured to run the computer program to perform the steps in any of the above method embodiments.

[0166] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0167] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0168] Embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the steps in any of the method embodiments described above.

[0169] It is obvious to those skilled in the art that the modules or steps of this disclosure described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this disclosure is not limited to any particular combination of hardware and software.

[0170] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A beamforming method for an antenna, comprising: Obtain the received signal strength information of the antenna array, and determine the target beam direction based on the received signal strength information; Based on the target beam direction and the preset neural network model, determine the control signal parameters corresponding to the target beam direction; The phase shift of the phase shift module connected to the antenna array is adjusted according to the control signal parameters, thereby controlling the phase or phase difference of the first transmitted signal of the antenna array so that the antenna array can be beamformed in the target beam direction.

2. The method according to claim 1, wherein, The phase shift module includes multiple cascaded phase shift units, each of the phase shift units including a first coupler and a phase shifter, wherein the first coupler and the phase shifter are electrically connected; The step of adjusting the phase shift of the phase shift module connected to the antenna array according to the control signal parameters, thereby controlling the phase or phase difference of the first transmitted signal of the antenna array, includes: The first coupler divides the input signal into multiple second transmitted signals with different phases. According to the control signal parameters, the phase shift of the phase shifter is adjusted, and the phase shifter is controlled to adjust the phase of the plurality of second transmitted signals with different phases or the phase difference between the plurality of second transmitted signals according to the phase shift, so as to obtain a plurality of first transmitted signals with different phases after adjustment; The first coupler feeds the plurality of first transmitted signals to the corresponding antenna elements of the antenna array.

3. The method according to claim 2, wherein, The phase shifter includes a second coupler and varactor diodes respectively connected to the through terminal and the coupling terminal of the second coupler; adjusting the phase shift of the phase shifter includes: The phase shift of the phase shifter is adjusted by adjusting the capacitance values ​​of the varactor diodes connected to the through end and the coupling end of the second coupler, respectively.

4. The method according to claim 1, wherein, Determining the target beam direction based on the received signal strength information includes: Determine the uplink and downlink communication modes of the received signals for each antenna element of the antenna array; According to the uplink and downlink communication mode of the received signal, the received signal strength information at the location of each antenna element is corrected; The target beam direction is determined based on the corrected received signal strength information.

5. The method according to claim 4, wherein, The received signal strength information is used to indicate the signal strength value of the received signal. The step of correcting the received signal strength information at each antenna element location according to the uplink / downlink communication mode of the received signal includes: For each antenna element, when the uplink and downlink communication mode of the received signal is time-division duplex communication, the signal strength value is subtracted from the preset antenna receiving efficiency of the antenna element to obtain the corrected received signal strength information; or, When the uplink and downlink communication mode of the received signal is frequency division duplex communication, the efficiency difference between the preset antenna receiving efficiency and the preset antenna transmitting efficiency is determined, and the signal strength value is subtracted from the preset antenna receiving efficiency of the antenna element and the efficiency difference to obtain the corrected received signal strength information.

6. The method according to claim 4, wherein, Determining the target beam direction based on the corrected received signal strength information includes: The received signal strength information at each of the corrected antenna element locations is analyzed to determine the locations of the highest and lowest signal strength values. The direction from the location of the lowest signal strength value to the location of the highest signal strength value is determined as the target beam direction.

7. The method according to claim 4, wherein, Also includes: The channel parameter information of each antenna element is obtained, and the channel attenuation value of each antenna element is determined based on the channel parameter information; Calculate the difference between the channel attenuation value of the target antenna element and the channel attenuation value of each antenna element other than the target antenna element; If the difference is greater than a preset difference threshold, it is determined that the received signal strength information of the target antenna element is not used for determining the target beam direction.

8. The method according to any one of claims 1 to 7, wherein, The step of determining the control signal parameters corresponding to the target beam direction based on the target beam direction and a preset neural network model includes: Obtain the current model parameter information, and determine the control signal parameters corresponding to the target beam direction based on the target beam direction, the preset neural network model, and the model parameter information; The model parameter information includes the relative position of the antenna elements, the type of modulation signal, and the preset antenna element directivity function.

9. The method according to claim 8, wherein, The model parameter information also includes at least one of the following: antenna element gain, antenna element received signal strength, electrical length and insertion loss of the conducted signal to each antenna port, modulation signal frequency and bandwidth, network environment parameters, and received signal-to-noise ratio.

10. The method according to claim 8, wherein, Before obtaining the current model parameter information, the following is also included: Obtain historical target beam directions, historical model parameter information, and the true values ​​of control signal parameters corresponding to the historical target beam directions; Using the historical target beam direction and the historical model parameter information as inputs to a preset initial neural network model, the predicted values ​​of the control signal parameters output by the initial neural network model are obtained. The model loss function is determined based on the true values ​​of the control signal parameters and the predicted values ​​of the control signal parameters. The initial neural network model is iteratively trained according to the model loss function to adjust the weight coefficients of the initial neural network model, and the trained preset neural network model is obtained when the model loss function meets the convergence condition.

11. A computer-readable storage medium storing a computer program, wherein, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1 to 10.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the steps of the method according to any one of claims 1 to 10.

13. A computer program product comprising a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1 to 10.

Images