Beam tracking method and device

Abstract

This invention discloses a beam tracking method and apparatus. The method includes: acquiring the relative displacements of beams transmitted by a base station to a terminal at multiple historical moments prior to the current moment, and the spatial positions of beam receiving points, wherein the relative displacement information is the displacement of the beam at a historical moment relative to the beam at the previous historical moment; determining the candidate beam search range at the current moment based on the relative displacements and spatial positions of the beams at multiple historical moments; when the candidate beam search range includes multiple candidate beams, measuring the multiple candidate beams based on preset measurement indicators to obtain the corresponding measurement values ​​for each candidate beam; and determining the target transmission beam within the candidate beam search range based on the corresponding measurement values ​​for the multiple candidate beams. This invention solves the technical problem of unsatisfactory beam tracking accuracy in obstructed environments in related technologies.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and more specifically, to a beam tracking method and apparatus. Background Technology

[0002] Currently, due to the often narrow beamwidth of millimeter-wave antenna arrays, efficient beam tracking algorithms are needed to ensure that the beams of the transmitting and receiving ends are always aligned to avoid data transmission interruptions. Existing beam tracking methods are typically only applicable to line-of-sight alignment in unobstructed environments. Considering that in real-world communication environments, there are often irregular objects such as trees, buildings, tables, and chairs, if the random movement of the transmitting and receiving ends causes their line-of-sight paths to be blocked by these objects, beam tracking will fail, resulting in communication interruptions with the terminal.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a beam tracking method and apparatus to at least solve the technical problem that the beam tracking accuracy of related technologies is not ideal in obstructed environments.

[0005] According to one aspect of the present invention, a beam tracking method is provided, comprising: acquiring relative displacements corresponding to beams transmitted by a base station to a terminal at multiple historical moments prior to the current moment, and spatial positions corresponding to the previous moment of the current moment, wherein the relative displacement is the displacement of the beam at a historical moment relative to the beam at the previous moment, and the spatial position is the transmission position of the beam transmitted by the base station; determining a candidate beam search range at the current moment based on the relative displacements corresponding to the beams at the multiple historical moments and the spatial position corresponding to the previous moment of the current moment; when the candidate beam search range includes multiple candidate beams, measuring the multiple candidate beams based on preset measurement indicators to obtain measurement values ​​corresponding to the multiple candidate beams respectively; and determining a target transmission beam in the candidate beam search range based on the measurement values ​​corresponding to the multiple candidate beams respectively.

[0006] According to another aspect of the present invention, an electronic device is provided, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any of the beam tracking methods described above.

[0007] In this embodiment of the invention, the relative displacements of the beams transmitted by the base station to the terminal at multiple historical moments prior to the current moment, and the spatial position corresponding to the previous moment of the current moment are obtained. The relative displacement is the displacement of the beam at a historical moment relative to the beam at the previous historical moment, and the spatial position is the transmission position of the beam transmitted by the base station. Based on the relative displacements of the beams at the multiple historical moments and the spatial position corresponding to the previous moment of the current moment, a candidate beam search range for the current moment is determined. If the candidate beam search range includes multiple candidate beams, the multiple candidate beams are measured based on preset measurement indicators to obtain corresponding measurement values ​​for each candidate beam. Based on the corresponding measurement values ​​for each candidate beam, the target transmission beam within the candidate beam search range is determined. This achieves the goal of identifying beam change patterns in obstructed environments, thereby improving communication stability and improving beam tracking accuracy. It also solves the technical problem of unsatisfactory beam tracking accuracy in obstructed environments associated with related technologies. Attached Figure Description

[0008] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0009] Figure 1 This is a flowchart of an optional beam tracking method provided according to an embodiment of the present invention;

[0010] Figure 2 This is a schematic diagram of an optional beam tracking method provided according to an embodiment of the present invention;

[0011] Figure 3a and Figure 3b This is a schematic diagram showing the result of an optional beam tracking method provided according to an embodiment of the present invention;

[0012] Figure 4 This is a schematic diagram of an optional beam tracking device provided according to an embodiment of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Millimeter-wave bands possess abundant idle spectrum resources, supporting transmission rates exceeding 10 Gbps (Gbps represents 1 billion bits per second), making them a key technology for building future wireless communication systems. However, millimeter-wave signals experience significant transmission attenuation, necessitating beamforming techniques using massive MIMO antenna arrays to enhance signal gain and establish stable data transmission links. Since millimeter-wave antenna arrays often have narrow beamwidths, efficient beam tracking algorithms are required to ensure consistent beam alignment between the transmitter and receiver, preventing data transmission interruptions. Existing beam tracking methods typically only apply to line-of-sight alignment in unobstructed environments. Considering the often irregular objects present in real-world communication environments, such as trees, buildings, and furniture, random movement of the transmitter and receiver can obstruct their line-of-sight paths, leading to loss of beam tracking, communication interruption, and reduced robustness of the communication system.

[0016] To address the aforementioned problems, this invention provides a method embodiment for beam tracking. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0017] Figure 1 This is a flowchart of a beam tracking method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0018] Step S102: Obtain the relative displacements of the beams transmitted by the base station to the terminal at multiple historical moments before the current moment, and the spatial position corresponding to the previous moment of the current moment. The relative displacements are the displacements of the beams at the historical moments relative to the beams at the previous moments of the corresponding historical moments, and the spatial positions are the transmission positions of the beams transmitted by the base station.

[0019] It's understandable that the number of beams a base station transmits to a terminal is limited; this can be viewed as a finite number, not an infinite number, of selectable transmission paths. At any given historical moment before the current moment, the base station transmits a preset number of beams for communication with the terminal. Due to significant signal attenuation, the beams need to be tracked based on the terminal's movement to obtain a high-gain channel state and ensure communication stability. To improve beam tracking accuracy, the base station needs to utilize the relative displacement of beams at historical moments and the spatial position of the beams in the previous moment to sense the terminal's motion state, which helps improve beam tracking accuracy.

[0020] Optionally, the aforementioned relative displacement can be a relative displacement vector, consisting of the relative displacement of the beam in the horizontal and vertical directions at each moment.

[0021] Optionally, the aforementioned spatial location can be used as a parameter for adjusting the attitude of the base station's transmitted beam, such as the transmission angle, which can be the pitch angle, horizontal angle, polarization angle, etc.

[0022] Step S104: Based on the relative displacements corresponding to the beams at the multiple historical moments and the spatial position corresponding to the previous moment of the current moment, determine the candidate beam search range for the current moment.

[0023] It is understandable that multiple historical moments reflect the dynamic changes in beam tracking. Based on the relative displacement of the beam at the corresponding historical moment and the spatial position at the previous moment of the current moment, it provides support for determining the candidate beam search range at the current moment, which is beneficial for determining the candidate beam search range with strong signal gain and improving communication stability.

[0024] In one optional embodiment, determining the candidate beam search range for the current moment based on the relative displacements corresponding to the beams at the plurality of historical moments and the spatial position corresponding to the previous moment of the current moment includes: acquiring a preset relative displacement tracking model and a preset spatial position tracking model; inputting the relative displacements corresponding to the plurality of historical moments into the relative displacement tracking model for processing to obtain a first beam search range; inputting the spatial position corresponding to the previous moment of the current moment into the spatial position tracking model for processing to obtain a second beam search range; and determining the candidate beam search range based on the first beam search range and the second beam search range.

[0025] It is understandable that beam tracking is performed using a model training method to improve tracking performance. To enhance communication stability and beam tracking accuracy for dynamic terminals, models are established from both relative displacement and spatial position perspectives. These corresponding models are then used for tracking processing to obtain the first and second beam search ranges, thus determining candidate beam search ranges. Through this process, the input data for the relative displacement tracking model and the spatial position tracking model are different, resulting in different processing capabilities. The first search range is obtained from the perspective of relative motion, while the second search range is obtained from the perspective of spatial position. Using the first and second beam search ranges improves the accuracy of obtaining the candidate beam search ranges.

[0026] In an optional embodiment, the above-mentioned inputting the relative displacements corresponding to the plurality of historical moments into the relative displacement tracking model for processing to obtain the first beam search range includes: when the number of beams transmitted by the base station to the terminal is a preset number, based on the relative displacements corresponding to the preset number of beams at each of the plurality of historical moments, processing is performed using the relative displacement tracking model to obtain the first search value corresponding to the preset number of beams at the current moment, wherein the first search value corresponding to the preset number of beams is used to characterize the impact of the displacement of the preset number of beams at the current moment compared to the previous moment on the quality of signal transmission; and the first beam search range is obtained based on the first search value corresponding to the preset number of beams.

[0027] It is understandable that, given a preset number of beams transmitted from the base station to the terminal, each of the preset number of beams corresponds to a relative displacement within multiple historical moments. This can be considered as reflecting the terminal's motion change pattern through a time dimension. The preset number of beams is used to select the first beam search range. A relative displacement tracking model is used to process the data, obtaining the first search value corresponding to the preset number of beams at the current moment. This first search value, obtained after processing by the relative displacement tracking model, characterizes the impact of the displacement of the preset number of beams transmitted by the base station to the terminal at the current moment compared to the previous moment on the signal transmission performance. Based on the first search value corresponding to the preset number of beams, the first beam search range is obtained. Through the above processing, the preset number of beams at each moment reflects the terminal's motion pattern, and the relative displacement tracking model identifies this motion pattern, which is beneficial for obtaining an accurate first beam search range for tracking the terminal's motion changes.

[0028] In one optional embodiment, obtaining the first beam search range based on the first search value corresponding to the preset number of beams includes: sorting the first search values ​​corresponding to the preset number of beams according to a predetermined first sorting method to obtain a first sorting result; determining a first number of beams in the first sorting result whose first search value is greater than a preset first value threshold; and obtaining the first beam search range based on the first number of beams.

[0029] It is understandable that the corresponding beams are sorted according to the first search value to obtain the first sorting result of the beams. The beams with the first search value greater than the first value threshold are regarded as the first number of selected beams. The first number of beams are combined to obtain the first beam search range.

[0030] Optionally, the first sorting method can be ascending or descending.

[0031] In an optional embodiment, the above-mentioned inputting the spatial location corresponding to the previous time of the current time into the spatial location tracking model for processing to obtain the second beam search range includes: when the number of beams transmitted by the base station to the terminal is a preset number, processing the spatial location based on the spatial locations corresponding to the preset number of beams in the previous time of the current time using the spatial location tracking model to obtain the second search value corresponding to the preset number of beams at the current time, wherein the second search value corresponding to the preset number of beams is used to characterize the influence of the beam receiving point corresponding to the preset number of beams at the current time on the signal transmission effect; and obtaining the second beam search range based on the second search value corresponding to the preset number of beams.

[0032] It is understandable that when the base station transmits a preset number of beams to the terminal, the spatial positions corresponding to each preset number of beams in the previous timeframe are considered. This can be viewed as reflecting the terminal's transition patterns and determining the characteristics of its location by observing the changes in the spatial positions of the beams between the previous and current times. It should be noted that, unlike relative displacement, the positions corresponding to some beams are special and require a significant jump in the next timeframe to ensure communication continuity. This allows for a rapid jump to the reflection path to maintain communication in the event of obstruction. The preset number of beams is used to select the second beam search range. A spatial position tracking model is used to obtain the second search value corresponding to each preset number of beams at the current time. This second search value, obtained after processing by the spatial position tracking model, characterizes the impact of the spatial positions corresponding to each preset number of beams at the current time on the signal transmission performance. Based on the second search value corresponding to each preset number of beams, the second beam search range is obtained. Through the above processing, by using a preset number of beams from the previous time to reflect the possible motion changes that the terminal's positional characteristics may cause, the spatial position tracking model can identify the specific locations where jumps may occur, which is beneficial for obtaining the second beam search range for accurately tracking the terminal's motion changes.

[0033] Optionally, the spatial location corresponding to the preset number of beams at the current moment may have various effects on the signal transmission performance, such as the impact of spatial location on signal gain, signal-to-noise ratio, received power, bit error rate, and data transmission rate.

[0034] In one optional embodiment, obtaining the second beam search range based on the second search values ​​corresponding to the preset number of beams includes: sorting the second search values ​​corresponding to the preset number of beams according to a predetermined second sorting method to obtain a second sorting result; determining a second number of beams whose second search values ​​are greater than a preset second value threshold in the second sorting result; and obtaining the second beam search range based on the second number of beams.

[0035] It can be understood that the corresponding beams are sorted according to the second search value to obtain the second sorting result of the beams. Beams with a second search value greater than the second value threshold are considered as the second number of selected beams. The second number of beams are combined to obtain the second beam search range.

[0036] Optionally, the second sorting method can be ascending or descending.

[0037] In one optional embodiment, determining the candidate beam search range based on the first beam search range and the second beam search range includes: determining a first decision weight corresponding to the relative displacement tracking model and a second decision weight corresponding to the spatial position tracking model; determining a first beam selection number within the first beam search range based on the first decision weight; determining a second beam selection number within the second beam search range based on the second decision weight; selecting the first beam selection number of beams within the first beam search range; selecting the second beam selection number of beams within the second beam search range; and determining the candidate beam search range based on the first beam selection number of beams and the second beam selection number of beams.

[0038] It is understandable that, in order to combine relative displacement and spatial position, a first decision weight corresponding to the relative displacement tracking model and a second decision weight corresponding to the spatial position tracking model are determined. The first decision weight indicates the number of first beams selected within the first beam search range, and is considered as a selection of candidate beams that prioritizes relative displacement angles. The second decision weight indicates the number of second beams selected within the second beam search range, and is considered as a selection of candidate beams that prioritizes spatial position angles. Based on the number of beams selected in the first and second beam selections, candidate beam search ranges are determined. Through the above processing, the resulting candidate beam search ranges can be designed to selectively favor relative displacement and spatial position.

[0039] In an optional embodiment, determining the first decision weight corresponding to the relative displacement tracking model and the second decision weight corresponding to the spatial position tracking model includes: obtaining the first historical weight of the relative displacement tracking model at the previous time in the current time and the second historical weight of the spatial position tracking model at the previous time in the current time; determining the previous transmission beam in which the base station transmitted to the terminal at the previous time in the current time, and the first beam search range and the second beam search range corresponding to the previous time in the current time; and determining the first decision weight and the second decision weight based on the previous transmission beam, the first historical weight, the second historical weight, and the first beam search range and the second beam search range corresponding to the previous time in the current time.

[0040] It is understandable that the first decision weight and the second decision weight are dynamically changing. They are adjusted based on the previous transmission beam selected at the previous moment. Based on the previous transmission beam, the first historical weight, the second historical weight, and the first and second beam search ranges corresponding to the previous moment, the first decision weight and the second decision weight are determined.

[0041] Optionally, a preset decision fusion model is used to process the process of determining the candidate beam search range based on the first beam search range and the second beam search range. The decision fusion model stores the first historical weight and the second historical weight.

[0042] In an optional embodiment, determining the first decision weight and the second decision weight based on the previous transmission beam, the first historical weight, the second historical weight, and the first beam search range and the second beam search range corresponding to the previous time of the current time includes: when the previous transmission beam is from the first beam search range corresponding to the previous time of the current time, using the first historical weight as the first decision weight and the second historical weight as the second decision weight.

[0043] It is understandable that the choice between the first and second beam search ranges determined from the previous time point determines how the weights are adjusted. If the previous beam originated from the first beam search range corresponding to the time point before the current time point (i.e., the first beam search range obtained from the relative displacement tracking model), then no weight update is required; the first historical weight is used as the first decision weight, and the second historical weight is used as the second decision weight.

[0044] In an optional embodiment, determining the first decision weight and the second decision weight based on the previous transmission beam, the first historical weight, the second historical weight, and the first beam search range and the second beam search range corresponding to the previous time of the current time includes: updating the first historical weight to obtain an updated first historical weight when the previous transmission beam is from the second beam search range corresponding to the previous time of the current time; updating the second historical weight to obtain an updated second historical weight; using the updated first historical weight as the first decision weight; and using the updated second historical weight as the second decision weight.

[0045] It is understandable that, if the previous transmission beam originates from the second beam search range corresponding to the previous time step, then the weight values ​​need to be updated to obtain the updated first historical weights, and the second historical weights also need to be updated to obtain the updated second historical weights. The updated first historical weights are used as the first decision weights, and the updated second historical weights are used as the second decision weights. Through this process, the tracking results obtained in the previous time step are added to the tracking processing in the form of weights, which is beneficial for timely adjustment of beam tracking and improves tracking accuracy.

[0046] Step S106: When the above candidate beam search range includes multiple candidate beams, the multiple candidate beams are measured based on preset measurement indicators to obtain the measurement values ​​corresponding to the multiple candidate beams respectively.

[0047] It is understandable that the above-mentioned measurement is based on preset measurement indicators, and multiple candidate beams are measured to obtain the actual measurement values ​​corresponding to the multiple candidate beams respectively, which are used to predict the effect of beam tracking.

[0048] Optionally, the above measurement indicators may include multiple parameters, such as signal-to-noise ratio, signal gain, etc.

[0049] Step S108: Based on the actual measurement values ​​corresponding to the above multiple candidate beams, determine the target transmission beam in the above candidate beam search range.

[0050] It is understandable that by processing the actual measurement values ​​corresponding to multiple candidate beams, the target transmission beam in the candidate beam search range is determined and regarded as the best beam for transmitting signals to the terminal at the current moment.

[0051] In one optional embodiment, the above-mentioned measurement of multiple candidate beams included in the candidate beam search range based on preset measurement indicators, and determination of the target transmission beam in the candidate beam search range, includes: converting the measurement values ​​corresponding to the multiple candidate beams respectively to obtain the equivalent values ​​corresponding to the multiple candidate beams at the current time; and determining the beam with the largest equivalent value among the multiple candidate beams as the target transmission beam.

[0052] It is understandable that the measured values ​​corresponding to multiple candidate beams are transformed to remove the influence of dimensions or thresholds, so as to obtain the equivalent values ​​corresponding to multiple candidate beams at the current time. The equivalent values ​​corresponding to multiple candidate beams are compared in the same way, and the beam with the largest equivalent value among multiple candidate beams is determined as the target transmission beam.

[0053] Optionally, the processing performed on the above measurements to obtain corresponding equivalent values ​​can be varied, including but not limited to normalization. Taking three beams as an example, the conversion method is specifically illustrated as follows: the received powers of the three beams are 0.5W, 0.2W, and 0.1W, respectively. Normalization converts these to corresponding equivalent values ​​of 1, 0.4, and 0.2, with beam 1 taken as the target transmission beam. The bit error rates of the three beams are respectively... , and Take the reciprocal as , and Then normalize to equivalent values ​​of 1, 0.1, and 0.5, and take beam 1 as the target transmission beam. The channel quality indicators of the three beams are 10, 6, and 4 respectively (no unit, only indicating the channel quality). The maximum value is set to 1, and the others are set to zero, which is converted to equivalent values ​​of 1, 0, and 0. Take beam 1 as the target transmission beam.

[0054] In an optional embodiment, after determining the target transmission beam with the largest equivalent value among the plurality of candidate beams, the method further includes: obtaining a preset relative displacement tracking model; and training the relative displacement tracking model based on the equivalent values ​​corresponding to the plurality of candidate beams at the current time to obtain a trained relative displacement tracking model.

[0055] It is understandable that the relative displacement tracking model is dominant, so all data needs to be fed back. The step of feeding back the equivalent values ​​corresponding to multiple candidate beams does not require any preconditions and is used to ensure the accuracy of decision-making through continuous training.

[0056] In one optional embodiment, training the relative displacement tracking model based on the equivalent values ​​corresponding to the plurality of candidate beams at the current time to obtain the trained relative displacement tracking model includes: determining a preset first sample pool for training the relative displacement tracking model; obtaining a new first sample based on the equivalent values ​​corresponding to the plurality of candidate beams at the current time and the relative displacements corresponding to the historical times; updating the first sample pool using the new first sample to obtain an updated first sample pool; selecting a first number of training samples from the updated first sample pool; and training the relative displacement tracking model based on the first number of training samples to obtain the trained relative displacement tracking model.

[0057] It is understandable that, since the equivalent value obtained at each historical moment is unconditionally fed back to the relative displacement tracking model, the aforementioned first sample pool includes data from all historical moments. When the relative displacement tracking model receives the equivalent values ​​corresponding to multiple candidate beams at the current moment, it uses the equivalent values ​​corresponding to the multiple candidate beams at the current moment and the relative displacements corresponding to the aforementioned historical moments to form a new first sample. The data in the first sample pool is updated using the new first sample, resulting in an updated first sample pool. The samples included in the first sample pool are all obtained using the same method as generating the new first sample. A first number of training samples are selected from the updated first sample pool. Based on the first number of training samples, the relative displacement tracking model is trained to obtain the trained relative displacement tracking model. Due to the fundamental characteristic of model training—that the training effect of the same model is better when the sample is rich—by continuously updating the first sample pool, the first sample pool can be continuously enriched to achieve better beam tracking processing.

[0058] Alternatively, there are several ways to select the first number of training samples, such as random selection or selection by setting preset selection rules.

[0059] In an optional embodiment, the method further includes: obtaining a preset spatial location tracking model and a second decision weight corresponding to the spatial location tracking model at the current time; if the second decision weight is greater than a preset weight threshold, training the spatial location tracking model based on the equivalent values ​​corresponding to the plurality of candidate beams at the current time, resulting in a trained spatial location tracking model.

[0060] It is understandable that the spatial position tracking model complements the relative displacement tracking model, achieving better beam tracking performance only at certain specific locations in space. Therefore, the data fed back to the spatial position tracking model needs to be carefully selected. The condition that needs to be met is that if the second decision weight is greater than a preset weight threshold, the equivalent value at that moment is considered beneficial for training the spatial position tracking model to achieve better processing capabilities. Therefore, in addition to feeding back the equivalent values ​​corresponding to multiple candidate beams to the relative displacement tracking model for training, the aforementioned equivalent values ​​should also be fed back to the spatial position tracking model for training. Through this process, selectively training the spatial position tracking model helps to further enhance the processing capabilities of either the spatial position tracking model or the displacement tracking model in the corresponding processing angles.

[0061] In one optional embodiment, the spatial position tracking model is trained based on the equivalent values ​​corresponding to the plurality of candidate beams at the current time. The trained spatial position tracking model includes: determining a preset second sample pool for training the spatial position tracking model; obtaining a new second sample based on the equivalent values ​​corresponding to the plurality of candidate beams at the current time and the spatial position corresponding to the previous time; updating the second sample pool using the new second sample to obtain an updated second sample pool; selecting a second number of training samples from the updated second sample pool; and training the spatial position tracking model based on the second number of training samples to obtain the trained spatial position tracking model.

[0062] It is understandable that, since the equivalent values ​​obtained at each historical moment are conditionally fed back to the spatial location tracking model, the aforementioned second sample pool only includes data from a portion of historical moments. When the second decision weight is greater than a preset weight threshold, the spatial location tracking model receives the equivalent values ​​corresponding to multiple candidate beams fed back at the current moment. Using the equivalent values ​​corresponding to the multiple candidate beams at the current moment, and the spatial location corresponding to the previous moment, a new second sample is generated. This new second sample is used to update the data in the second sample pool, resulting in an updated second sample pool. The samples included in the second sample pool are all obtained using the same method as generating the new second sample. Second training samples are selected from the updated second sample pool. Based on the second training samples, the spatial location tracking model is trained, resulting in a trained spatial location tracking model. By continuously updating and enriching the second sample pool, better beam tracking processing can be achieved, improving the ability to identify spatial locations.

[0063] Alternatively, there are several ways to select the second number of training samples, such as random selection or selection by setting preset selection rules.

[0064] Through the above steps S102 to S108, it is possible to identify the beam change pattern in an obstructed environment, thereby improving communication stability and achieving the technical effect of improving beam tracking accuracy. This solves the technical problem that the beam tracking accuracy of related technologies is not ideal in obstructed environments.

[0065] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 2 This is a schematic diagram of an optional beam tracking device according to an embodiment of the present invention, which mainly includes the following steps:

[0066] Step S1: The communication terminal inputs the beam relative displacement information and beam spatial position information from several past moments into the relative displacement tracking model and the spatial position tracking model, respectively. The models output the relative displacement beam search range (i.e., the first beam search range) and the spatial position beam search range (i.e., the second beam search range), respectively.

[0067] Step S1 also provides a specific implementation method for obtaining the relative displacement beam search range and the spatial position beam search range, which is described in detail below.

[0068] Record the current moment as The time period is defined as the N historical times preceding the current time. At any given moment, the relative displacement of the beam in the horizontal and vertical directions constitutes the relative displacement vector.

[0069]

[0070] in, and They represent The relative displacement of the beam in the horizontal and vertical directions at any given time.

[0071] The relative displacement vector is input into the beam relative displacement tracking model, and the output value of the model is all the data transmitted by the base station to the terminal. The search value of each beam (i.e., the first search value) is used to sort the above values ​​in descending order, and the values ​​greater than a certain threshold are selected. Several beams form the relative displacement beam search range.

[0072] exist At that moment, The absolute coordinates of the beam in the horizontal and vertical directions at any given time. and Input beam spatial location tracking model, the model output value is all the beams transmitted by the base station to the terminal The search value of each beam (i.e., the second search value) is used to sort the above values ​​in descending order, and the values ​​greater than a certain threshold are selected. Several beams form the spatial location beam search range.

[0073] Step S2: Input the relative displacement beam search range and the spatial position beam search range into the decision fusion model. The decision fusion model fuses the relative displacement beam search range and the spatial position beam search range according to the decision weights of the relative displacement tracking model and the spatial position tracking model, and outputs the fused beam search range (i.e., the candidate beam search range).

[0074] Step S2 also provides a specific implementation method for obtaining the search range of the fused beam, which is described in detail below.

[0075] The decision fusion model internally stores all The decision weights for the relative displacement tracking model and the spatial position tracking model corresponding to each beam. If The data transmission beam at any given moment is The first of the beams The nth beam, then obtain the nth beam The first decision weight corresponding to the relative displacement tracking model of each beam is: , and the The second decision weight of the spatial position tracking model for each beam .

[0076] The first decision weights corresponding to the M beams are denoted as follows: and the second decision weight .in, The sum of the first and second decision weights for the same beam is 1.

[0077] The decision fusion model is based on the decision weights of the relative displacement tracking model and the spatial position tracking model. and From the relative displacement beam search range Selected from each beam in descending order of search value One beam, Select the number of beams for the first beam. From the spatial location beam search range... Selected from each beam in descending order of search value One beam, The number of beams selected for the second beam forms the fused beam search range, where and . The specific value can be obtained through the following formula:

[0078]

[0079] The specific value can be obtained through the following formula:

[0080]

[0081] in, It is a preset constant or a value obtained by multiplying c1, i, c2, i, K1, K2 by a certain coefficient. and These are the symbols for rounding down and rounding up.

[0082] In step S3, the terminal measures the beams within the fusion beam search range, selects the data transmission beam based on the measurement results, and feeds back the measurement results to the relative displacement tracking model, the spatial position tracking model, and the decision fusion model. The above models update their internal parameters based on the measurement results.

[0083] Step S3 also provides a specific implementation method for updating the decision weights of the relative displacement tracking model and the spatial position tracking model, which is described in detail below.

[0084] The beams within the fusion search range are measured, and the beam with the best measurement result is determined as the data transmission beam;

[0085] The beam measurement results within the fusion beam search range Convert to equivalent measurement results This ensures that the following condition is met: if the measurement result of the m-th beam is better than the measurement result of the n-th beam, then... .

[0086] Determine whether the data transmission beam originates from the relative displacement beam search range or the spatial position beam search range. If it originates from the relative displacement beam search range, do not update the decision weights of the relative displacement tracking model and the spatial position tracking model. and If it originates from the spatial location beam search range, and assumes The data transmission beam at time 1 is the first If there are multiple beams, then the decision weights for the relative displacement tracking model and the spatial position tracking model are... and The updates are performed according to the following rules: , , .in For discount rate, , , where a is a preset constant.

[0087] All equivalent measurement results of the beam within the fusion beam search range Feedback is sent to the relative displacement tracking module, which then sends the relative displacement vector... With equivalent measurement results The constituent samples are stored in sample pool 1, and a batch of samples is randomly drawn from sample pool 1 to train the relative displacement tracking module.

[0088] Relative displacement information actually includes the terminal's motion information. By continuously learning the correspondence between relative displacement information and equivalent measurement values, the relative displacement tracking module can determine, in a statistical sense, which beams have high search value (equivalent measurement values ​​are usually high) and which beams have low search value (equivalent measurement values ​​are usually low) for a certain relative displacement sequence (a certain motion law). Therefore, the relative displacement tracking module mainly provides suggested search beam ranges by identifying the terminal's motion law.

[0089] Assumption The data transmission beam at time t is the i-th beam. If the decision weights of the spatial position tracking model corresponding to the above data transmission beams are... If the value exceeds a certain threshold, all equivalent measurement results of the beams within the beam search range will be fused. The feedback is sent to the spatial position tracking model, which then sets the spatial position coordinates of the beam at time T0-1. , and equivalent measurement results The constituent samples are stored in sample pool 2, and a batch of samples is randomly drawn from sample pool 2 to train the spatial location tracking model.

[0090] Spatial location information effectively indicates the terminal's spatial location. By continuously learning the correspondence between spatial location information and equivalent measurements, the spatial location tracking module can determine, statistically speaking, which beam the terminal would typically hop to in the next moment when it is located within the coverage area of ​​a certain beam. Therefore, the spatial location tracking module primarily identifies the terminal's spatial location to suggest the range of hopping beams to search. Especially in scenarios where hopping is necessary due to potential obstruction, the spatial location tracking module can learn from long-term accumulated samples that certain beams correspond to unusual locations requiring a significant hop in the next moment to maintain communication continuity. This allows for a rapid hop to a reflection path to maintain communication in the event of obstruction.

[0091] After training the relative displacement tracking module and the spatial position tracking module, the decision fusion model compares the statistical superiority of the search ranges provided by the relative displacement tracking module and the spatial position tracking module at different beam positions. Through long-term accumulation, it can be determined which positions usually experience large beam jumps (where the spatial position tracking module usually provides better results) and which positions usually experience continuous beam changes (where the relative displacement tracking module usually provides better results). Therefore, the beam search range provided by the spatial position tracking module is mainly used at positions where large beam jumps usually occur, and the beam search range provided by the relative displacement module is mainly used at positions where beam changes are usually continuous.

[0092] Figure 3a and Figure 3b This is a schematic diagram showing the results of an optional beam tracking method provided by an embodiment of the present invention. The simulation results using beam tracking are as follows. Figure 3a and Figure 3b As shown, Figure 3a and Figure 3b The results are from two tracking simulations. In one simulation, the beam tracking period was 1 second, the user terminal's speed was 1 m / s, the base station was suspended at a height of 3 m, and the user moved randomly on a plane at a height of 0 m. An obstruction existed in the environment. When the line-of-sight path between the base station and the user was blocked, a timely switch to the reflection path was required to maintain communication continuity. When the line-of-sight path reappeared, a timely switch back from the reflection path was necessary to ensure optimal transmission rate. Figure 3a and Figure 3b The arrows indicate where the beam is obstructed or where a jump is needed after obstruction. The comparison between the expected ideal result and the beam tracking result from this embodiment of the invention is shown. The vertical axis beam index indicates the correspondence between beam number and beam position. For example, from -90° (degrees) to 90°, one beam is set every 10°. Therefore, number 0 represents the beam at -90°, number 1 represents the beam at -80°, and so on, resulting in a simulated line graph. Simulation results show that in this communication scenario, regardless of whether there is an obstruction jump or continuous beam change, the method provided by this embodiment of the invention can maintain stable beam tracking. However, other comparison algorithms do not have the ability to jump; when the line-of-sight path is obstructed, the beam is lost, and communication is interrupted.

[0093] The above optional implementation methods achieve at least the following effects: by utilizing beam relative displacement information and spatial position information, the beam change pattern and the location where the beam is blocked can be effectively identified, thereby maintaining the stability of the communication link in complex environments where the terminal moves rapidly and there are obstructions, having the ability to be applicable to complex communication environments, and improving the accuracy of beam tracking.

[0094] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0095] This embodiment also provides a beam tracking device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0096] According to embodiments of the present invention, an embodiment of an apparatus for implementing a beam tracking method is also provided. Figure 4 This is a schematic diagram of a beam tracking device according to an embodiment of the present invention, such as... Figure 4 As shown, the above-mentioned beam tracking device includes an acquisition module 402, a first determination module 404, a measurement module 406, and a second determination module 408. The device will be described below.

[0097] The acquisition module 402 is used to acquire the relative displacements of the beams transmitted by the base station to the terminal at multiple historical moments before the current moment, and the spatial position corresponding to the previous moment of the current moment, wherein the relative displacement is the displacement of the beam at a historical moment relative to the beam at the previous moment of the corresponding historical moment, and the spatial position is the transmission position of the beam transmitted by the base station.

[0098] The first determining module 404, connected to the obtaining module 402, is used to determine the candidate beam search range for the current moment based on the relative displacements corresponding to the beams at the multiple historical moments and the spatial position corresponding to the previous moment of the current moment.

[0099] The measurement module 406, connected to the first determination module 404, is used to measure the multiple candidate beams based on preset measurement indicators when the candidate beam search range includes multiple candidate beams, and obtain the measurement values ​​corresponding to the multiple candidate beams respectively.

[0100] The second determining module 408, connected to the measurement module 406, is used to determine the target transmission beam in the candidate beam search range based on the actual measurement values ​​corresponding to the multiple candidate beams.

[0101] In a beam tracking device provided by this embodiment of the invention, an acquisition module 402 is used to acquire the relative displacements of beams transmitted by a base station to a terminal at multiple historical moments prior to the current moment, and the spatial position corresponding to the previous moment of the current moment. The relative displacement is the displacement of the beam at a historical moment relative to the beam at the previous historical moment, and the spatial position is the transmission position of the beam transmitted by the base station. A first determination module 404, connected to the acquisition module 402, is used to determine the candidate beam search range at the current moment based on the relative displacements of the beams at the multiple historical moments and the spatial position corresponding to the previous moment of the current moment. A measurement module 406, connected to the first determination module 404, is used to measure the multiple candidate beams based on preset measurement indicators when the candidate beam search range includes multiple candidate beams, obtaining the measurement values ​​corresponding to the multiple candidate beams. A second determination module 408, connected to the measurement module 406, is used to determine the target transmission beam in the candidate beam search range based on the actual measurement values ​​corresponding to the multiple candidate beams. This technology achieves the goal of identifying beam change patterns in obstructed environments, thereby improving communication stability and enhancing beam tracking accuracy. It also solves the technical problem of unsatisfactory beam tracking accuracy in obstructed environments.

[0102] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0103] It should be noted that the acquisition module 402, the first determination module 404, the measurement module 406, and the second determination module 408 mentioned above correspond to steps S102 to S108 in the embodiments. The instances and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a computer terminal.

[0104] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0105] The aforementioned beam tracking device may also include a processor and a memory. The acquisition module 402, the first determination module 404, the measurement module 406, the second determination module 408, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0106] The processor contains a core that retrieves the corresponding program unit from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0107] This invention provides a non-volatile storage medium storing a program that, when executed by a processor, implements a beam tracking method.

[0108] This invention provides an electronic device, including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: obtaining the relative displacements of beams transmitted by a base station to a terminal at multiple historical moments prior to the current moment, and the spatial position corresponding to the previous moment of the current moment, wherein the relative displacement is the displacement of the beam at a historical moment relative to the beam at the previous historical moment, and the spatial position is the transmission position of the beam transmitted by the base station; determining a candidate beam search range for the current moment based on the relative displacements of the beams at the multiple historical moments and the spatial position corresponding to the previous moment of the current moment; if the candidate beam search range includes multiple candidate beams, measuring the multiple candidate beams based on preset measurement indicators to obtain measurement values ​​corresponding to the multiple candidate beams; and determining the target transmission beam within the candidate beam search range based on the measurement values ​​corresponding to the multiple candidate beams. The device in this document can be a server, PC, etc.

[0109] This invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program with the following method steps: obtaining the relative displacements corresponding to beams transmitted by a base station to a terminal at multiple historical moments prior to the current moment, and the spatial position corresponding to the previous moment of the current moment, wherein the relative displacement is the displacement of the beam at a historical moment relative to the beam at the previous moment, and the spatial position is the transmission position of the beam transmitted by the base station; determining the candidate beam search range at the current moment based on the relative displacements corresponding to the beams at the multiple historical moments and the spatial position corresponding to the previous moment of the current moment; when the candidate beam search range includes multiple candidate beams, measuring the multiple candidate beams based on preset measurement indicators to obtain the measurement values ​​corresponding to the multiple candidate beams respectively; and determining the target transmission beam in the candidate beam search range based on the measurement values ​​corresponding to the multiple candidate beams respectively.

[0110] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0115] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0116] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0117] It should also be noted that 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 process, method, article, or apparatus. Unless otherwise specified, 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.

[0118] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A beam selection method, characterized in that, The method comprises: obtaining relative displacements of beams corresponding to the base station and the terminal at a plurality of historical time points before a current time point and a spatial position corresponding to a time point before the current time point, wherein the relative displacement is a displacement of a beam at a historical time point relative to a beam at a time point before the historical time point, and the spatial position is a transmission position of the beam of the base station; determining a candidate beam search range at the current time point based on the relative displacements of the beams corresponding to the plurality of historical time points and the spatial position corresponding to the time point before the current time point; in a case where the candidate beam search range comprises a plurality of candidate beams, measuring the plurality of candidate beams based on a preset measurement index to obtain measurement values corresponding to the plurality of candidate beams respectively; determining a target transmission beam in the candidate beam search range based on the measurement values corresponding to the plurality of candidate beams respectively; wherein the determining of the candidate beam search range at the current time point based on the relative displacements of the beams corresponding to the plurality of historical time points and the spatial position corresponding to the time point before the current time point comprises: obtaining a preset relative displacement tracking model and a preset spatial position tracking model; inputting the relative displacements corresponding to the plurality of historical time points into the relative displacement tracking model for processing to obtain a first beam search range; inputting the spatial position corresponding to the time point before the current time point into the spatial position tracking model for processing to obtain a second beam search range; and determining the candidate beam search range based on the first beam search range and the second beam search range.

2. The method of claim 1, wherein, The inputting of the relative displacements corresponding to the plurality of historical time points into the relative displacement tracking model for processing to obtain the first beam search range comprises: in a case where the beams transmitted by the base station to the terminal are of a preset number, processing the relative displacements corresponding to the preset number of beams at each of the plurality of historical time points by using the relative displacement tracking model to obtain first search values corresponding to the preset number of beams at the current time point, wherein the first search values corresponding to the preset number of beams are used to represent the influence of the displacement of the preset number of beams at the current time point relative to the time point before the current time point on the signal transmission effect; obtaining the first beam search range based on the first search values corresponding to the preset number of beams.

3. The method of claim 2, wherein, The obtaining of the first beam search range based on the first search values corresponding to the preset number of beams comprises: sorting the first search values corresponding to the preset number of beams in a predetermined first sorting manner to obtain a first sorting result; determining a first number of beams with first search values greater than a preset first value threshold in the first sorting result; obtaining the first beam search range based on the first number of beams.

4. The method of claim 1, wherein, The inputting of the spatial position corresponding to the time point before the current time point into the spatial position tracking model for processing to obtain the second beam search range comprises: In a case where a preset number of beams transmitted by the base station to the terminal is a preset number, based on spatial positions corresponding to the preset number of beams in a last time of the current time, the spatial position tracking model is used for processing to obtain second search values corresponding to the preset number of beams in the current time, wherein the second search values corresponding to the preset number of beams are used to represent influences of the spatial positions corresponding to the preset number of beams in the current time on signal transmission effects; The second beam search range is obtained based on the second search values corresponding to the preset number of beams.

5. The method of claim 4, wherein, The second beam search range is obtained based on the second search values corresponding to the preset number of beams, comprising: The second search values corresponding to the preset number of beams are sorted according to a predetermined second sorting manner to obtain a second sorting result; A second number of beams with second search values greater than a preset second value threshold are determined in the second sorting result; The second beam search range is obtained based on the second number of beams.

6. The method according to any one of claims 1 to 5, characterized in that, The candidate beam search range is determined based on the first beam search range and the second beam search range, comprising: A first decision weight corresponding to the relative displacement tracking model and a second decision weight corresponding to the spatial position tracking model are determined; A first beam selection number in the first beam search range is determined based on the first decision weight; A second beam selection number in the second beam search range is determined based on the second decision weight; The first beam selection number of beams are selected in the first beam search range; The second beam selection number of beams are selected in the second beam search range; The candidate beam search range is determined based on the first beam selection number of beams and the second beam selection number of beams.

7. The method of claim 6, wherein, The first decision weight corresponding to the relative displacement tracking model and the second decision weight corresponding to the spatial position tracking model are determined, comprising: A first historical weight corresponding to the relative displacement tracking model in a last time of the current time and a second historical weight corresponding to the spatial position tracking model in the last time of the current time are obtained; A last transmission beam of the base station to the terminal in the last time of the current time, and a first beam search range and a second beam search range corresponding to the last time of the current time are determined; The first decision weight and the second decision weight are determined based on the last transmission beam, the first historical weight, the second historical weight, and the first beam search range and the second beam search range corresponding to the last time of the current time.

8. The method of claim 7, wherein, The first decision weight and the second decision weight are determined based on the last transmission beam, the first historical weight, the second historical weight, and the first beam search range and the second beam search range corresponding to the last time of the current time, comprising: In a case where the last transmission beam is from a first beam search range corresponding to a last time point of the current time point, the first historical weight is taken as the first decision weight, and the second historical weight is taken as the second decision weight.

9. The method of claim 7, wherein, The determining the first decision weight and the second decision weight based on the last transmission beam, the first historical weight, the second historical weight, and the first beam search range and the second beam search range corresponding to a last time point of the current time point comprises: In a case where the last transmission beam is from the second beam search range corresponding to the last time point of the current time point, the first historical weight is updated to obtain an updated first historical weight; The second historical weight is updated to obtain an updated second historical weight; The updated first historical weight is taken as the first decision weight; The updated second historical weight is taken as the second decision weight.

10. The method of claim 1, wherein, The measuring the multiple candidate beams included in the candidate beam search range based on the preset measurement index, and determining a target transmission beam in the candidate beam search range comprises: The measurement values corresponding to the multiple candidate beams respectively are converted to obtain equivalent values corresponding to the multiple candidate beams respectively at the current time point; The candidate beam with the largest equivalent value in the multiple candidate beams is determined as the target transmission beam.

11. The method of claim 10, wherein, After the candidate beam with the largest equivalent value in the multiple candidate beams is determined as the target transmission beam, the method further comprises: obtaining a preset relative displacement tracking model; training the relative displacement tracking model based on the equivalent values corresponding to the multiple candidate beams respectively at the current time point to obtain a trained relative displacement tracking model.

12. The method of claim 11, wherein, The training the relative displacement tracking model based on the equivalent values corresponding to the multiple candidate beams respectively at the current time point to obtain a trained relative displacement tracking model comprises: determining a preset first sample pool for training the relative displacement tracking model; obtaining a new first sample based on the equivalent values corresponding to the multiple candidate beams respectively at the current time point and the relative displacements corresponding to the historical time points respectively; updating the first sample pool by using the new first sample to obtain an updated first sample pool; selecting a first number of training samples from the updated first sample pool; training the relative displacement tracking model based on the first number of training samples to obtain the trained relative displacement tracking model.

13. The method of claim 11, wherein, The method further comprises: obtaining a preset spatial position tracking model and a second decision weight corresponding to the current time point of the spatial position tracking model; in a case where the second decision weight is greater than a preset weight threshold, training the spatial position tracking model based on the equivalent values corresponding to the multiple candidate beams respectively at the current time point to obtain a trained spatial position tracking model.

14. The method of claim 13, wherein, The training the spatial position tracking model based on the equivalent values corresponding to the multiple candidate beams respectively at the current time point to obtain a trained spatial position tracking model comprises: determining a preset second sample pool for training the spatial position tracking model; obtaining a new second sample based on the respective equivalent values of the plurality of candidate beams at the current moment and the spatial position corresponding to a previous moment of the current moment; updating the second sample pool by using the new second sample to obtain an updated second sample pool; selecting a second number of training samples from the updated second sample pool; training the spatial position tracking model based on the second number of training samples to obtain the trained spatial position tracking model.

15. An electronic device, comprising: comprise: one or more processors and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the beam selection method of any one of claims 1 to 14.

Images