Beam management method and device

Abstract

Disclosed are a beam management method and apparatus, applied to a network device, comprising: receiving first feedback information reported by a user equipment, the first feedback information comprising measured values of signal parameters of a first beam set in N historical time windows, the signal parameters comprise physical layer reference signal receiving power L1-RSRP, reference signal receiving quality RSRQ and signal to interference plus noise ratio SINR, and N is an integer greater than or equal to 1; performing beam prediction based on the first feedback information to obtain a beam prediction result, the beam prediction result comprising a second beam set and / or second beam information, the second beam set being a subset of a third beam set, and the third beam set being a set of candidate beams used by the network device for transmitting data; the second beam information comprises a predicted value of a signal parameter of each beam in the second beam set. By implementing the embodiments of the present application, the accuracy of beam prediction can be improved, and the signaling overhead and time delay of beam prediction can be reduced.

Description

Technical Field

[0001] This application relates to the field of wireless communications, and in particular, to a beam management method and apparatus. Background Art

[0002] In 5G and future communication networks, a base station can transmit dozens or even hundreds of narrow beams to cover users in different directions to achieve multi-user, high-rate, and low-latency communication. Among them, the narrow beam transmitted by the base station is a beam pattern in which the electromagnetic wave energy radiated by the antenna is highly concentrated in a specific direction. Its beam width (i.e., the angular range covered by the main lobe) is relatively narrow, usually between a few degrees and dozens of degrees, with stronger directivity and higher energy concentration. Therefore, its antenna gain is relatively high, which can compensate for the path loss of high-frequency signals, reduce interference in other directions, and is suitable for multi-user spatial multiplexing scenarios. In the communication between the base station and the user equipment, the base station can manage the narrow beam, realize coverage optimization through beam sweeping and beam tracking, dynamically adapt to environmental changes, flexibly respond to user movement, and also improve capacity, that is, achieve multi-user parallel transmission.

[0003] However, in the existing technical solutions, the methods for measuring and predicting beams used by the base station in beam sweeping and beam monitoring have high latency, large signaling overhead, and insufficient measurement and prediction accuracy, resulting in problems such as data transmission delay and packet loss in the wireless communication between the base station and the user equipment, and there may also be deviations in resource allocation, that is, allocating limited resources to non-optimal beams, reducing the efficiency and performance of the communication system. Summary of the Invention

[0004] Embodiments of this application provide a beam management method and apparatus, which can improve the accuracy and flexibility of beam prediction.

[0005] In a first aspect, an embodiment of this application provides a beam management method, which is applied to a network device and includes: receiving first feedback information reported by a user equipment, where the first feedback information includes measurement values of signal parameters of a first beam set in N historical time windows, the signal parameters include physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; performing beam prediction based on the first feedback information to obtain a beam prediction result, where the beam prediction result includes a second beam set and / or second beam information, the second beam set is a subset of a third beam set, and the third beam set is a set of candidate beams used by the network device to transmit data; the second beam information includes predicted values of the signal parameters of each beam in the second beam set.

[0006] An embodiment of the present application provides a beam management method applied to a network device, which can improve the accuracy of beam prediction of the network device and reduce the signaling overhead and latency of beam prediction. Specifically, the network device obtains historical data (i.e., the first feedback information) of the beams (i.e., the beams in the first beam set) sent to the user equipment in the historical time by receiving the first feedback information sent by the user equipment, and performs beam prediction based on the first feedback information to obtain a beam (i.e., the second beam set) or beam information (i.e., the second prediction information) that is more suitable for transmitting to the user equipment at a future moment. Among them, the first feedback information includes measured values corresponding to the physical layer reference signal received power (L1-RSRP), reference signal received quality (RSRQ), and signal-to-interference-plus-noise ratio (SINR), which can provide the network device with more comprehensive historical data of the beams in the first beam set, so that the network device can improve the prediction accuracy when performing beam prediction based on the first feedback information; in addition, a more accurate prediction result can reduce the number of times the network device transmits candidate beams to determine the optimal beam (that is, narrow the range of candidate beams), as well as reduce the number of times of receiving and analyzing the feedback information and the amount of data included in the feedback information. Therefore, the latency and signaling overhead of the network device for determining the optimal beam for transmitting data can be reduced, and the real-time performance and efficiency of wireless communication can be improved.

[0007] In a possible implementation manner, the first feedback information includes measured values of the signal parameters of each beam in the first beam set in each of the N historical time windows, where one or more measured values correspond to one signal parameter of each beam in one historical time window. In the embodiment of the present application, the first feedback information can reflect the signal quality of the beams in the first beam set in the past multiple time windows. In other words, when the historical time window is long, the first feedback information can reflect the signal quality of the beams in the first beam set in the past long time through the measured values of the signal parameters corresponding to fewer historical time windows. When the historical time window is short, the first feedback information can better reflect the change of the signal quality of the beams in the first beam set in the past short time through the measured values of the signal parameters corresponding to more historical time windows. In this way, the first feedback information can increase the amount of data during beam prediction through the number and length of the historical time windows, and can improve the reliability of beam prediction.

[0008] In a possible implementation, performing beam prediction based on the first feedback information to obtain a beam prediction result includes: inputting the first feedback information into a beam prediction model to output a beam prediction result. In the embodiments of the present application, beam prediction can be performed through the beam prediction model, enabling the network device to automatically extract features from the first feedback information without manual intervention. Moreover, beam prediction through the model can process large-scale data, improving the accuracy and rate of beam prediction and also enhancing the generalization ability of beam prediction.

[0009] In a possible implementation, inputting the first feedback information into a beam prediction model to output a beam prediction result includes: determining the channel condition of the user equipment based on the first feedback information; preprocessing the first feedback information based on the channel condition to obtain preprocessed first feedback information, where the types of parameters included in the signal parameters in the preprocessed first feedback information are less than or equal to the types of parameters included in the signal parameters in the first feedback information before preprocessing; and inputting the preprocessed first feedback information into the beam prediction model to output a beam prediction result. In the embodiments of the present application, although the first feedback information received by the network device includes measurement values corresponding to three signal parameters, when performing beam prediction under the channel conditions corresponding to different user equipments, the three signal parameters are not all necessary. Therefore, the network device can first determine the user equipment channel condition based on the first feedback information, and then select one or more of the three signal parameters of the first feedback information according to the channel condition. This can ensure that the first feedback information on which beam prediction depends can provide sufficient signal quality information, and can eliminate some data that has little effect on beam prediction according to different channel conditions to reduce the calculation amount and improve the prediction efficiency.

[0010] In a possible implementation, preprocessing the first feedback information includes: selecting one or more parameters from L1-RSRP, RSRQ, and SINR based on the channel condition; normalizing the measurement values corresponding to the selected one or more parameters in the first feedback information according to the parameter types to map the measurement values corresponding to different types of parameters to different value ranges. In the embodiments of the present application, different types of signal parameters have different value ranges, and the absolute values of the parameters are often large. Performing normalization processing can make the parameter measurement values of different types of signal parameters at the same dimension level, reducing the calculation complexity and improving the inference speed when performing beam prediction based on the first feedback information. In addition, normalizing the measurement values of signal parameters to different value ranges according to different types can strengthen the influence of a certain (or certain) signal parameter on beam prediction and improve the accuracy of beam prediction.

[0011] In a possible implementation, the method further includes: receiving reference information, where the reference information includes one or more of beam selection rules, parameter evaluation thresholds; the step of inputting the preprocessed first feedback information into a beam prediction model to output a beam prediction result includes: inputting the preprocessed first feedback information and the reference information into the beam prediction model to output a beam prediction result. In the embodiments of the present application, the network device may also receive reference information for beam prediction to assist beam prediction, so that the obtained beam prediction result better meets the requirements of different tasks, and improves the flexibility and robustness of beam prediction.

[0012] In a possible implementation, the second beam set includes K beams, where K is an integer greater than 1, and the K beams are K beams in the third beam set that meet a preset condition. In the embodiments of the present application, by presetting the preset condition, the beams included in the predicted result better meet the requirements in different situations, and the robustness of beam prediction is increased.

[0013] In a possible implementation, the method further includes: determining a fourth beam set based on the beam prediction result, where the fourth beam set is a beam set used by the network device to transmit to the user equipment for determining the optimal beam, the fourth beam set includes one or more beams in the second beam set, or the fourth beam set includes one or more beams in the second beam set and the third beam set, and the optimal beam is a beam in the fourth beam set; transmitting the beams in the fourth beam set to the user equipment; receiving the identifier of the optimal beam reported by the user equipment; and transmitting the optimal beam to the user equipment. In the embodiments of the present application, after obtaining the beam prediction result, the network device can make a further selection based on the beam prediction result in combination with the actual situation of the network device or the environment to determine the set of alternative beams (i.e., the fourth beam set) that can be used to transmit data and will ultimately be transmitted to the user equipment, which can avoid a decline in communication quality caused by directly transmitting the beam corresponding to the beam prediction result when the beam prediction is inaccurate, and at the same time make the beam transmitted by the network device more in line with the needs of the user equipment, reducing the signaling overhead and latency generated for determining the optimal beam.

[0014] In a possible implementation, the beam prediction model is a gated recurrent unit (GRU) model. In the embodiments of the present application, the model used for beam prediction is a GRU model. Compared with other recurrent neural network models in the prior art, the GRU model can capture the temporal variations of the beam more fully, enabling it to make more accurate predictions based on historical data. In addition, the GRU model has a simpler structure, can handle a larger amount of data, and has a simpler calculation process, so that less memory is occupied and less calculation time is used during beam prediction, improving the real-time performance of beam prediction.

[0015] In a second aspect, embodiments of the present application provide a beam management method applied to a user equipment, including: receiving each beam in a first beam set transmitted by a network device, and measuring each beam in the first beam set to obtain first feedback information, where the first feedback information includes measured values of signal parameters of the first beam set within N historical time windows, the signal parameters including physical layer reference signal received power (L1-RSRP), reference signal received quality (RSRQ), and signal-to-interference-plus-noise ratio (SINR), and N is an integer greater than or equal to 1; and sending the first feedback information to the network device.

[0016] In a possible implementation, the method further includes: receiving each beam in a fourth beam set transmitted by the network device, and measuring each beam in the fourth beam set to obtain second feedback information, where the fourth beam set is a beam set sent by the network device to the user equipment for determining an optimal beam, and the second feedback information includes measured values of the signal parameters of each beam in the fourth beam set; determining the optimal beam in the fourth beam set based on the second feedback information; and sending an identifier of the optimal beam to the network device.

[0017] Third aspect, an embodiment of the present application provides a beam management device, which is applied to a network device. The device includes: a receiving module, configured to receive first feedback information reported by a user equipment, where the first feedback information includes measurement values of signal parameters of a first beam set within N historical time windows, and the signal parameters include physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; a prediction module, configured to perform beam prediction based on the first feedback information to obtain a beam prediction result, where the beam prediction result includes a second beam set and / or second beam information, the second beam set is a subset of a third beam set, and the third beam set is a set of candidate beams used by the network device to transmit data; the second beam information includes predicted values of the signal parameters of each beam in the second beam set; a scanning module, configured to determine a fourth beam set based on the beam prediction result, and scan the beams in the fourth beam set for the user equipment, where the fourth beam set is a beam set used by the network device to transmit to the user equipment to determine an optimal beam, and the fourth beam set includes one or more beams in the second beam set, or the fourth beam set includes one or more beams in the second beam set and the third beam set.

[0018] In a possible implementation manner, the receiving module is further configured to: receive an identifier of an optimal beam reported by the user equipment, where the optimal beam is a beam in the fourth beam set.

[0019] Fourth aspect, an embodiment of the present application provides a beam management device, which is applied to a user equipment. The device includes: a measurement module, configured to measure each beam in a first beam set to obtain first feedback information, where the first feedback information includes measurement values of signal parameters of the first beam set within N historical time windows, and the signal parameters include physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; a feedback module, configured to send the first feedback information to a network device; a communication module, configured to receive an optimal beam transmitted by the network device, and establish a communication link based on the optimal beam.

[0020] In a possible implementation manner, the measurement module is further configured to: measure each beam in a fourth beam set to obtain second feedback information, where the fourth beam set is a beam set used by the network device to transmit to the user equipment to determine the optimal beam, and the second feedback information includes measurement values of the signal parameters of each beam in the fourth beam set.

[0021] In a possible implementation, the feedback module is further configured to: send the second feedback information to the network device.

[0022] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to execute the method according to the first aspect or any implementation manner of the first aspect.

[0023] In a sixth aspect, an embodiment of the present invention provides a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to execute the method according to the second aspect or any implementation manner of the second aspect.

[0024] In a seventh aspect, an embodiment of the present invention provides a computer program product including computer program code that, when run on a computer, causes the computer to execute the method according to the first aspect or any implementation manner of the first aspect.

[0025] In an eighth aspect, an embodiment of the present invention provides a computer program product including computer program code that, when run on a computer, causes the computer to execute the method according to the second aspect or any implementation manner of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the following will describe the drawings required to be used in the embodiments of the present application or the background art.

[0027] Figure 1 FIG. 1 is a schematic diagram of a wireless communication system 100 provided by an embodiment of the present application.

[0028] Figure 2A FIG. 2 is a schematic diagram of a communication link between a network device and a user equipment provided by an embodiment of the present application.

[0029] Figure 2B FIG. 3 is a schematic diagram of beam scanning of a network device provided by an embodiment of the present application.

[0030] Figure 2C FIG. 4 is another schematic diagram of beam scanning of a network device provided by an embodiment of the present application.

[0031] Figure 3A FIG. 5 is a schematic diagram of a beam management method flow provided by an embodiment of the present application.

[0032] Figure 3B FIG. 6 is a schematic diagram of a data prediction processing flow for the first feedback information provided by an embodiment of the present application.

[0033] Figure 3C It is a schematic flowchart of a beam management method on the base station side provided by an embodiment of the present application.

[0034] Figure 4A It is a network structure diagram of a GRU beam prediction model provided by an embodiment of the present application.

[0035] Figure 4B It is a schematic diagram of the input and output of a GRU network provided by an embodiment of the present application.

[0036] Figure 5A It is a schematic diagram of a beam prediction device 50 provided by an embodiment of the present application.

[0037] Figure 5B It is a schematic diagram of another beam prediction device 60 provided by an embodiment of the present application.

[0038] Figure 6 It is a schematic diagram of the structure of a user equipment provided by an embodiment of the present application.

[0039] Figure 7 It is a schematic diagram of the structure of a network device provided by an embodiment of the present application. Detailed implementation manners

[0040] Next, the embodiments of the present application will be described in conjunction with the accompanying drawings in the embodiments of the present application. The terms "first", "second", "third", and "fourth", etc. in the specification and claims of the present application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices. Referring to "embodiment" in this article means that a specific feature, structure, or characteristic described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0041] As used in this specification, the terms "component", "module", "system", etc. are used to represent computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be components. One or more components can reside in a process and / or an execution thread, and a component can be located on one computer and / or distributed between two or more computers. In addition, these components can execute from various computer-readable media storing various data structures. A component can communicate, for example, through local and / or remote processes according to signals having one or more data packets (e.g., data from two components interacting with another component in a local system, a distributed system, and / or a network, such as data interacting with other systems through signals over the Internet).

[0042] First, in combination with Figure 1 describe the wireless communication system to which the beam management method provided in the embodiments of the present application is applicable.

[0043] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD), 5th generation (5G) mobile communication systems or NR communication systems, and / or networks operating according to other systems and radio technologies (including future systems and radio technologies not explicitly mentioned herein).

[0044] Figure 1 is a schematic diagram of a wireless communication system 100 provided by the embodiments of the present application. As Figure 1 shown, the wireless communication system 100 can include one or more network devices. For example, Figure 1 the network device 101 shown. The wireless communication system 100 can also include one or more user devices. For example, Figure 1 the mobile terminal 102, vehicle-mounted terminal 103, fixed terminal 104, etc. shown.

[0045] The network device 101 in the embodiments of this application may be a device used to communicate with a user equipment. The network device 101 may be a base station, an evolved node B (eNB), a home base station, an access point (AP) in a wireless fidelity (WIFI) system, a wireless relay node, a wireless backhaul node, a transmission point (TP), or a transmission and reception point (TRP), etc. It may also be a gNB in a New Radio (NR) system. Alternatively, it may also be a component or a part of a device that constitutes a base station, such as a central unit (CU), a distributed unit (DU), or a baseband unit (BBU), etc. Among them, the specific technologies and specific device forms adopted by the network device in the embodiments of this application are not limited. In this application, the network device 101 may refer to the network device 101 itself, or a chip applied to the network device 101 to complete the wireless communication processing function.

[0046] In the embodiments of the present application, the mobile terminal 102 in the wireless communication system 100 may also be referred to as a terminal, a mobile station (MS), a mobile terminal (MT), etc. Specifically, the mobile terminal 102 may be a mobile phone, a tablet computer (Pad), a mobile computing device with wireless transceiver functions, a wireless terminal applied to scenarios such as virtual reality (VR) and augmented reality (AR), and other mobile terminals capable of supporting wireless communication; the vehicle-mounted terminal 103 is a terminal device installed on a vehicle and used to enable the vehicle to interact with the outside world (such as other vehicles, base stations, traffic infrastructure, etc.), and may be a vehicle-mounted navigation terminal, a vehicle-mounted navigation terminal, a self-driving terminal, and a wireless terminal applied to scenarios such as transportation safety; the fixed terminal 104 refers to a device or terminal that is placed at a fixed position and does not have the characteristic of moving freely, and is mainly connected to the wireless communication system through a wired or fixed wireless access point to achieve functions such as data transmission and communication, for example, a wireless terminal applied to scenarios such as industrial control, remote medical, smart grid, smart city, and smart home. In the embodiments of the present application, the foregoing user equipment and the chips applicable to the foregoing user equipment are collectively referred to as user equipment. Among them, the embodiments of the present application do not limit the specific technologies and specific device forms adopted by the user equipment.

[0047] In some possible embodiments, the network device 101 and user devices (including the mobile terminal 102, vehicle-mounted terminal 103, and fixed terminal 104) can be dispersed throughout a geographical area to form a wireless communication system 100, and can include devices in different forms or with different capabilities. Wireless communication can be carried out between the network device 101 and user devices (including the mobile terminal 102, vehicle-mounted terminal 103, and fixed terminal 104) via one or more network device-user device communication links 105. For example, the network device 101 can support coverage of a certain area, within which the network device 101 and user devices (including the mobile terminal 102, vehicle-mounted terminal 103, and fixed terminal 104) can establish one or more network device-user device communication links 105. Among them, the coverage area can be a geographical area, within which the network device in combination with the user device can support signal communication of one or more radio access technologies (such as radio frequency access links). In some implementations of the wireless communication system 100, direct communication links are also supported between user devices (D2D). For example, the vehicle-mounted terminal-mobile terminal communication link 106 can be a communication link between a vehicle (such as the vehicle-mounted terminal 103) and terminal devices (such as the mobile terminal 102 and fixed terminal 104). The vehicle-mounted terminal-mobile terminal communication link 106 can support one or more communication methods (such as short-range wireless communication links such as Bluetooth, near-field communication NFC, cellular network communication links, dedicated short-range communication DSRC, and vehicle-to-everything V2X). For another example, communication links are also supported between terminal devices (such as the mobile terminal 102 and fixed terminal 104), such as the mobile terminal-fixed terminal communication link 107. In addition, communication links can also be established between the mobile terminals 102, between the vehicle-mounted terminals 103, and between the fixed terminals 104 ( Figure 1 not shown in the figure), such as sidelink communication channels. In some aspects, vehicles can communicate using vehicle-to-everything (V2X) communication, vehicle-to-vehicle (V2V) communication, or some combination of the above methods.

[0048] It should be noted that Figure 1 it is only an exemplary diagram provided to illustrate the wireless communication system applicable to the embodiments of the present application. Other network devices can also be included in this wireless communication system. For example, core network devices, wireless relay devices, and wireless backhaul devices can also be included ( Figure 1 not shown in the figure). In addition, the embodiments of the present application do not limit the number of network devices and user devices included in this wireless communication system.

[0049] Based on the above wireless communication system, the communication link and beam management between the network device and the user device will be further described below in combination with Figure 2A 、 Figure 2B and Figure 2C .Figure 2A This is a schematic diagram of the communication link between a network device and a user equipment provided by an embodiment of the present application. As Figure 2A shown, communication can be carried out between the network device 101 and the user equipment 202 via a downlink communication link 203 and an uplink communication link 204. Among them, the downlink communication link 203 and the uplink communication link 204 can be Figure 1 an example of the network device-user equipment communication link 105 in Figure 1 The user equipment 202 is an example of a user equipment, and can include

[0050] the mobile terminal 102, the vehicle-mounted terminal 103, and the fixed terminal 104 in Figure 2B , Figure 2B This is a schematic diagram of the beam scanning of the network device provided by an embodiment of the present application. As Figure 2BAs shown, the network device first performs wide-beam scanning using a wide-beam set (Set B) 211. Usually, Set B 211 contains multiple wide beams (for example Figure 2B the two wider fan-shaped regions shown in Set B 211 in Figure 2B can represent two specific wide beams). It should be noted that the number of wide beams contained in Set B 211 is not fixed, and its specific number is related to the size of the area covered by the network device 101 and the width of the beams transmitted by the network device 101. Figure 2B Set B 211 in Figure 2B is only an exemplary illustration for explaining the wireless communication between the network device 101 and the user equipment 202, and does not constitute a specific limitation.

[0051] Specifically, the wide beams in Set B 211 have a wide coverage range and can send signals in a relatively large area, but their gain is relatively low, which is suitable for quickly discovering the user equipment 202. The wide beams in Set B 211 can sequentially send reference signals (such as CSI-RS) in space at a certain angular interval (such as every 30 degrees) to cover the entire service area and try to discover potential user equipment 202. After receiving the wide beams in Set B 211, the user equipment 202 can measure the reference signal strength of the wide beams therein and report it to the network device 101; based on the measurement results reported by the user equipment 202, the network device 101 can determine the approximate location of the user equipment 202. Further, reference can be made to Figure 2C , Figure 2C which is another schematic diagram of beam scanning of the network device provided by an embodiment of the present application. The network device 101 can switch to a narrow-beam set (Set A) 221 for refined scanning. Set A 221 can include multiple narrow beams (for example Figure 2C the 5 narrower fan-shaped regions shown in Set A 221 in Figure 2C can represent 5 specific narrow beams). The widths of these narrow beams are usually small, but their gain is high, which can more accurately point to the user equipment 202 and improve the quality of wireless communication. It should be noted that similar to Set B 211, the number of narrow beams in Set A 221 is also not fixed, and its specific number is also related to the size of the area covered by the network device 101 and the width of the beams transmitted by the network device 101. Figure 2CThe medium narrow beam set (Set A) 221 is only an exemplary illustration for explaining the wireless communication between the network device 101 and the user equipment 202, and does not constitute a specific limitation. Generally, the number of beams in Set A 221 is greater than the number of beams in Set B 211. Further, the user equipment 202 can measure the reference signal strength of the beams in Set A 221 and report it to the network device 101. The network device 101 can further adjust the beams based on the measurement results reported by the user equipment 202 until the optimal beam is determined, and perform wireless communication with the user equipment 202 through the optimal beam. Among them, the optimal beam refers to the beam that can maximize the signal quality or minimize the interference among the candidate beams used by the network device 101 to transmit data to the user equipment 202.

[0052] Based on the process of establishing a downlink for wireless communication between the network device 101 and the user equipment 202 as described above, it can be understood that when the network device 101 scans using a narrow beam set, since the width of the beam becomes smaller compared to the wide beam, more intensive beam direction tests are required, and its computational complexity and latency are relatively high, and the scanning overhead is also relatively high. Moreover, frequent beam scanning and feedback will increase the signaling overhead, which will further increase the communication latency. In addition, when the user equipment 202 is in a high-speed moving scenario, the ultra-high moving speed (or obstacle occlusion) of the user equipment 202 will cause the channel conditions to change rapidly over time. Based on the above problems, in the existing technical solutions, beam time-domain downlink prediction is usually performed on the network device side, that is, based on the historical information of the beam (such as the measurement information based on the wide beam) to predict the optimal beam (such as the narrow beam set or a certain beam in the narrow beam set) for the user equipment within the next time period, so as to minimize the beam scanning overhead and the corresponding signaling overhead, and reduce the latency in the wireless communication process. In addition, in response to scenarios of high-speed movement or obstacle occlusion, the beam time-domain downlink prediction can also quickly adapt to the channel changes, enabling the wireless communication system to complete beam switching in a short time and reducing the situation of communication interruption or signal quality degradation.

[0053] In the existing technical solutions, an artificial intelligence (AI) or machine learning (ML) model can be deployed on the base station side for time-domain downlink prediction. However, when making predictions using the existing technical solutions, since the reference historical measurement information is too single, the true state of the wireless channel cannot be fully reflected, resulting in the prediction results of the model often deviating from the actual situation. That is, the non-optimal beam is incorrectly selected, leading to a decline in communication quality and problems such as data transmission delay and packet loss. Further, inaccurate prediction results may also cause deviations in resource allocation by the base station, allocating limited resources to non-optimal beams, reducing the efficiency and performance of the entire communication system. In addition, the model structure used in the existing technical solutions is too complex (such as the long short-term memory (LSTM) model), making the time cost required to process a large amount of input data too high and the generation of prediction results having an obvious delay, making it difficult to meet the response requirements of ultra-reliable low-latency communication (URLLC).

[0054] To solve the problems existing in the above-mentioned existing technical solutions, the embodiments of the present application provide a beam management method. This method can accurately reflect the beam information and channel state within a historical time, and perform beam prediction through a model with a simpler structure to obtain a more accurate time-domain downlink beam prediction result, reducing latency and signaling overhead.

[0055] The main process of the beam management method provided by the embodiments of the present application is described below. This method is applied to the network device 101 and mainly includes: Receiving first feedback information. Specifically, the network device 101 can receive the first feedback information reported by the user equipment 202. The first feedback information includes the measured values corresponding to three parameters, namely, the physical layer reference signal received power (L1-RSRP), reference signal received quality (RSRQ), and signal-to-interference plus noise ratio (SINR), within N historical time windows, where N is an integer greater than or equal to 1. Among them, the historical time window is a period of time relative to the current moment.

[0056] In a possible implementation, the specific time lengths of the N historical time windows can be set by the network device 101, and the time lengths of the set N historical time windows are sent to the user equipment 202 before the user equipment 202 sends the first feedback information to the network device. The user equipment 202 can measure the beams in the first beam set based on the specific lengths of the N historical time windows to obtain the first feedback information. Among them, the network device 101, as the core control node of a wireless communication system (such as the wireless communication system 100), can determine the specific lengths of the historical time windows according to the overall situation of the wireless communication system (such as network load, service type distribution, etc.) and wireless environment characteristics (such as signal interference level, propagation loss, etc.). For example, in an area with relatively large interference, the network device 101 may set shorter historical time windows to obtain signal change information (such as the first feedback information) more frequently. In this way, when performing beam prediction based on the first feedback information, the timeliness and accuracy of beam prediction can be improved; for another example, in an area where the signal is relatively stable, the network device 101 can set longer historical time windows (and can reduce the number of historical time windows at the same time) to reduce the frequency of obtaining signal change information, which can reduce unnecessary signaling overhead and delay. Optionally, the time lengths of the N historical time windows can be different.

[0057] Specifically, the first feedback information may include three parameters: L1-RSRP, RSRQ, and SINR. The definitions of the three parameters are as follows: 1. L1-RSRP: It refers to the linear average power of the reference signal received on a specific resource element, with the unit of decibel milliwatt (dBm). The specific resource element refers to the resource element used to carry the reference signal (RS). In the implementation of this application, the resource element used to carry the reference signal can be a beam (including the beams in the first beam set, the second beam set, and the third beam set). The calculation formula of L1-RSRP is:

[0058] Among them, is the number of measured resource elements, is the received signal of the th resource element. In an aspect of the embodiments of this application, L1-RSRP can be used to measure the strength of the reference signal sent by the network device 101 received by the user equipment 202. The higher the value of L1-RSRP, the stronger the signal received by the user equipment 202, indicating that the user equipment 202 is closer to the network device 101 or the loss on the signal propagation path is smaller, and the network coverage is better; 2. RSRQ: It is the ratio of RSRP to the Received Signal Strength Indicator (RSSI), which can comprehensively reflect the signal strength and interference level. The unit is decibel (dB), and its calculation formula is:

[0059] where is also the number of measured resource elements, is the total received power of all signals (including serving cell, neighboring cells, interference, and noise) within the same resource block (i.e., multiple user equipments share or compete for the same physical resource units at the same time and within the same frequency range), which can measure the received signal strength in wireless communication; compared with L1-RSRP, RSRQ can not only reflect the signal strength, but also comprehensively reflect the signal strength and interference situation. That is to say, if the signal strength received by user equipment 202 is high, that is, the value of RSRP is high, but the number and strength of surrounding interference signals are large, that is, the value of RSSI responds high, then the ratio RSRQ of RSRP to RSSI will be low, which indicates that due to the existence of interference signals, the actual channel communication quality is not particularly ideal; 3. SINR: It is the ratio of the power of the received useful signal to the sum of the powers of the interference signal and the noise signal, that is, the ratio of RSRP to the interference plus noise power ) The unit is usually decibel (dB). SINR can directly reflect the degree of influence of interference and noise received by the signal during transmission, that is, it can directly characterize the channel quality. Its calculation formula is:

[0060] where is the co-channel interference power of neighboring cells, that is, when other cells (neighboring cells) adjacent to the current serving cell in the wireless network use the same frequency as the current serving cell for signal transmission, the interference power generated by these neighboring cell signals on the received signals of user equipments in the current serving cell, is the power of the noise signal; the higher the value of SINR, the higher the strength of the useful signal relative to interference and noise, the better the communication quality, the lower the bit error rate of data transmission, and the higher data transmission rate can be supported; on the contrary, if the value of SINR is lower, the communication quality is worse, and problems such as data transmission errors are more likely to occur.

[0061] In a possible implementation manner, the first feedback information can be measured by the user equipment 202 and fed back to the network equipment 101, and the first feedback information includes the above three parameters at the same time. In this way, when the network equipment 101 makes a prediction based on the first feedback information, not only the single L1-RSRP is used as parameter data, but L1-RSRP, RSRQ, and SINR are all used as reference data for beam prediction.

[0062] Furthermore, beam prediction is performed based on the first feedback information to obtain a beam prediction result. Specifically, the network equipment 101 can perform beam prediction based on the first feedback information to obtain a beam prediction result. The beam prediction result includes one or more of a second beam set or second beam information. The second beam set is a subset of a third beam set, and the third beam set is a set of candidate beams used by the network equipment to transmit data; the second beam information is prediction information of beams in the second beam set, and the second beam information includes predicted values corresponding to the three parameters of L1-RSRP, RSRQ, and SINR of the beams in the second beam set.

[0063] In some possible implementation manners, the network equipment 101 can maintain multiple dynamic beam sets, which may include a beam set for determining a potential user equipment 202 or for determining the radio channel environment of the user equipment 202 (for example Figure 2B the wide beam set Set B 211 shown). The width of the beams in this kind of beam set is relatively large, but the signal directivity and gain are poor, and it is difficult to meet the response requirements of reliable low-latency communication. However, the beam can quickly obtain spatial coverage information, determine the approximate location of the user equipment 202, and the channel environment. In addition, the network equipment 101 can also maintain a (one or more) dynamic set of candidate beams for transmitting data, that is, the third beam set. The beam width in the third beam set is relatively small, but the directivity and signal gain are strong, and it can better meet the communication requirements of a wireless communication system (such as the wireless communication system 100). It is a candidate beam that can establish a communication link with the user equipment 202 and transmit data (that is, one or more of them may ultimately establish a communication link with the user equipment 202 and transmit data). In a possible implementation manner, the third beam set can be Figure 2C the narrow beam set Set A 221 shown.

[0064] However, since the width of the beams in the third beam set is usually small, a relatively large number of beams are required to cover a certain spatial area. However, the user equipment 202 ultimately only needs one beam to establish a communication link. Therefore, not all the beams in the third beam set are usable by the user equipment 202 or have good signal quality. Some beams in the third beam set are significantly inapplicable to the user equipment 202 due to their directions and the channel environment of the user equipment 202. Therefore, before using narrow beam scanning, it is necessary to determine, through beam prediction, one or more beams that are more suitable and have better communication quality for the user equipment 202 in the third beam set, that is, the second beam set. Optionally, the result of beam prediction may include the second beam set, and the second beam set is a subset of the third beam set. That is to say, the second beam set includes one or more beams in the third beam set. In a possible implementation manner, the beams included in the second beam set refer to the identifiers (IDs) of one or more beams in the third beam set, rather than the actual beams.

[0065] In a possible implementation manner, the beam prediction result may further include second beam information. The second beam information is the prediction information of the beams in the second beam set, that is, the predicted values of the three parameters of L1-RSRP, RSRQ, and SINR of the beams in the second beam set at a future moment. It can represent the beams in the second beam set predicted from the third beam set and reflect the channel quality of the beams in the second beam set. Optionally, the beam prediction result may include the second beam set or the second beam information or both the second beam set and the second beam information.

[0066] Specifically, after the network device 101 receives the first feedback information, if it does not perform beam prediction and directly scans the beams in the third beam set, it needs to receive the parameter measurement values for the beams in the third beam set again, and further evaluate the parameter measurement values. It may even need to perform multiple scans and evaluations until the optimal beam is determined, and then use the optimal beam to transmit data. In this existing technical solution, due to the large number of beams in the third beam set, the signaling overhead and latency for scanning and evaluation are both large, and the response requirements of ultra-reliable low-latency communication (URLLC) cannot be met. Therefore, beam prediction is required. The method provided in the implementation of this application can predict the beams in the third beam set that are more likely to establish a communication link and transmit data, or their corresponding prediction information, based on the measurement information for the first beam set, which can reduce the number of times the network device transmits candidate beams to determine the optimal beam (that is, narrow the range of candidate beams), as well as reduce the number of times of receiving and analyzing feedback information and the amount of data contained in the feedback information. Therefore, it can reduce the latency and signaling overhead for the network device to determine the optimal beam for sending data, and improve the real-time performance and efficiency of wireless communication. In addition, the first feedback information includes the measured values corresponding to the physical layer reference signal received power (L1-RSRP), reference signal received quality (RSRQ), and signal-to-interference-plus-noise ratio (SINR), which can provide the network device with more comprehensive historical data of the beams in the first beam set, enabling the network device to improve the accuracy of prediction when performing beam prediction based on the first feedback information.

[0067] In some possible implementation manners, the beam management method provided in the embodiments of this application can perform beam prediction through a beam prediction model. The following Figure 3A describes in more detail the beam management method provided in the embodiments of this application. Figure 3A is a schematic flowchart of a beam management method provided in the embodiments of this application. As Figure 3A shown, the beam management method may include: Step S301: Transmit the beams in the first beam set.

[0068] Specifically, the network device 101 transmits the beams in the first beam set to the user equipment 202 for measurement by the user equipment 202. The first beam set is a beam set maintained by the network device 101 for scanning the user equipment 202. The beams in the first beam set have a larger beam width and can be used to quickly determine the approximate location and channel environment of the user equipment 202. In one possible implementation manner, the first beam set may be Figure 2B the wide beam set Set B 211 shown.

[0069] Step S302: Measure the first beam set to obtain the first feedback information.

[0070] Specifically, the user equipment 202 receives the beams in the first beam set transmitted by the network equipment 101 and measures them. In a possible implementation manner, before transmitting the first beam set to the user equipment 202, the network equipment 101 may set the specific time lengths of N historical time windows based on the overall situation of the wireless communication system. For specific details, reference may be made to the relevant descriptions in the main process of the above beam management method, which will not be elaborated here. Further, the network equipment 101 may send the lengths of the set N historical time windows to the user equipment 202 to guide the user equipment 202 to measure the beams in the first beam set. Optionally, the network equipment 101 may send the lengths of the set N historical time windows to the user equipment 202 through the beams in the first beam set, or through other beams.

[0071] In a possible implementation manner, the user equipment 202 measures the beams in the first beam set according to the lengths of the N historical time windows set by the network equipment 101, so as to obtain the measured values of the signal parameters L1-RSRP, RSRQ, and SINR corresponding to each beam in the first beam set within the N historical time windows.

[0072] Step S303: Report the first feedback information.

[0073] Specifically, the user equipment 202 may send the measured first feedback information to the network equipment 101. In a possible implementation manner, before sending the first feedback information to the network equipment 101, the user equipment 202 may also perform preliminary preprocessing on the first feedback information. For specific details, reference may be made to the relevant descriptions in step S404 below.

[0074] Step S304: Perform preprocessing on the first feedback information.

[0075] Specifically, although using three parameters, namely L1-RSRP, RSRQ, and SINR, for beam prediction can solve the problem of single historical reference data and improve the prediction accuracy, there are significant differences in the sensitivity of historical parameters in different communication scenarios. For example, in a high-interference environment, as a core indicator for measuring signal coverage strength, RSRP can directly reflect the connection stability of the beam between the user equipment 202 and the network device 101. In a dynamic scenario, RSRQ and SINR can more reflect the changes in interference and instantaneous channel quality and are more suitable for measuring the beam state in a dynamic scenario. Therefore, the network device 101 can perform data preprocessing on the first feedback information by dynamically selecting one or more parameters in the first feedback information and then performing beam prediction, which can make the historical reference data used for beam prediction more adaptable to the communication environment where the user equipment 202 is located and make the beam prediction more accurate. In addition, the first feedback data received by the network device 101 includes multiple parameter measurement values of multiple beams in multiple historical time windows, with a large amount of data and complexity. The network device 101 can also perform data preprocessing on the first feedback information by splicing it into one or more sequences for facilitating input into the beam prediction model for beam prediction.

[0076] In a possible implementation manner, the embodiment of the present application provides a possible solution for data preprocessing of the first feedback information, which can be referred to Figure 3B , Figure 3B is a schematic flowchart of data prediction processing for the first feedback information provided by the embodiment of the present application. As Figure 3B shown, the data preprocessing of the first feedback information by the network device 101 may include: Step S401: Determine the channel condition based on the first feedback information.

[0077] Specifically, after receiving the first feedback information, the network device 101 can determine the channel condition of the user equipment 202 that sends the first feedback information based on the specific parameter measurement values in the first feedback information. The first feedback information includes the measurement values of L1-RSRP, RSRQ, and SINR of the beams in the first beam set. The network device 101 can judge the scenario where the user equipment 202 is located, that is, the channel condition, based on the specific measurement values of L1-RSRP, RSRQ, and SINR. The channel condition refers to the state description of the impact on signal transmission quality after the comprehensive action of the physical characteristics of the signal transmission path (such as the beam) and environmental factors in wireless communication.

[0078] In a possible implementation manner, refer to Table 1. Table 1 is a table of the value ranges of L1-RSRP, RSRQ, SINR, and RSSI provided by the embodiments of the present application. Among them, the value range of L1-RSRP is generally between -140 dBm and -44 dBm, and the typical value range is between -140 dBm and -80 dBm. In the first feedback information, when the measured value corresponding to L1-RSRP is -85 dBm or above, it indicates that the signal strength of the beam in the first beam set received by the user equipment 202 is good and is suitable for high-speed data transmission. At this time, the communication quality between the user equipment 202 and the network device 101 is relatively high (for example, there is basically no obstruction), and a large amount of data can be stably transmitted; when the measured value corresponding to L1-RSRP is between -85 dBm and -95 dBm, it indicates that the signal strength of the beam in the first beam set received by the user equipment 202 is good, which can meet the data transmission requirements of most user equipment 202, and the communication experience is relatively smooth; when the measured value corresponding to L1-RSRP is between -95 dBm and -105 dBm, it indicates that the signal strength of the beam in the first beam set received by the user equipment 202 is average, and there is a certain obstruction between the user equipment 202 and the network device 101 (for example, when the user equipment 202 is in a relatively deep position indoors or in a densely built-up area), which is suitable for low-speed data transmission, and the communication quality may decrease due to a reduction in the data transmission speed during the wireless communication process; when the measured value corresponding to L1-RSRP is below -105 dBm, it indicates that the signal strength of the beam in the first beam set received by the user equipment 202 is very poor, and there is a serious obstruction between the user equipment 202 and the network device 101 (for example, the user equipment 202 is in a closed space such as a basement or an elevator, or is far from the base station), which may cause a significant decrease in the data transmission speed or even a connection interruption; The value range of RSRQ is usually between -19.5 dB and -3 dB, and the typical value range is between -19 dB and -3 dB. In the first feedback information, when the measured value corresponding to RSRQ is -10 dB or above, it indicates that the signal quality of the beam in the first beam set received by the user equipment 202 is excellent, and the reference signal power is very large relative to the interference and noise power. The user equipment 202 may be in an area with good signal coverage and less interference, the signal transmission is stable, the bit error rate is extremely low, and it can support high-speed and high-quality data transmission with low latency; when the measured value corresponding to RSRQ is between -10 dB and -15 dB, it indicates that the signal quality of the beam in the first beam set received by the user equipment 202 is good, and the ratio of the reference signal power to the interference and noise power is at a relatively high level. There may be certain interference around the user equipment 202, but the interference intensity is small and does not seriously affect the signal quality. The data transmission rate is relatively high, and the network delay increases slightly compared with when the measured value corresponding to RSRQ is -10 dB or above; when the measured value corresponding to RSRQ is between -15 dB and -18 dB, it indicates that the signal quality of the beam in the first beam set received by the user equipment 202 is average, and the ratio of the reference signal power to the interference and noise power is at a medium level. The user equipment 202 may be in an area with obvious interference (such as the center of a business district or a large office building), the data transmission rate decreases, and there will be data transmission delay and quality degradation; when the measured value corresponding to RSRQ is below -18 dB, it indicates that the signal quality of the beam in the first beam set received by the user equipment 202 is poor, and the ratio of the reference signal power to the interference and noise power is very low. The user equipment 202 may be in an area with severe interference (such as a large event site, a factory workshop, etc.), the communication link is unstable, and the data transmission is often interrupted; The value range of SINR is usually between -20 dB and 30 dB, and the typical value range is between -3 dB and 20 dB. In the first feedback information, when the measured value corresponding to SINR is 15 dB or above, it indicates that the useful signal strength of the beams in the first beam set received by the user equipment 202 is much greater than the interference and noise strength, the signal quality is very good, the user equipment 202 may be in an area with good signal coverage and minimal interference, and the data transmission rate is extremely high; when the measured value corresponding to SINR is between 10 dB and 15 dB, it indicates that the useful signal strength of the beams in the first beam set received by the user equipment 202 is significantly greater than the interference and noise strength, the signal quality is good, there may be a small amount of interference around the user equipment 202, but the interference strength is small and is not sufficient to have a significant impact on the signal quality, the data transmission rate is high, and the network latency is low; when the measured value corresponding to SINR is between 5 dB and 10 dB, it indicates that the useful signal strength of the beams in the first beam set received by the user equipment 202 is slightly greater than the interference and noise strength, the signal quality is average, the user equipment 202 may be in an area with relatively more interference (such as a residential area or a small commercial area), and the data transmission quality and rate decrease; when the measured value corresponding to SINR is between 0 dB and 5 dB, it indicates that the useful signal strength of the beams in the first beam set received by the user equipment 202 is similar to the interference and noise strength, the signal quality is poor, the user equipment 202 may be in an area with severe interference (such as the site of a large-scale performance), and the data transmission is unstable and the rate is low; when the measured value corresponding to SINR is below 0 dB, it indicates that the interference and noise strength of the beams in the first beam set received by the user equipment 202 is greater than the useful signal strength, and the signal can hardly be received normally. The user equipment 202 may be in an area where the signal is severely interfered or the coverage is extremely poor (such as a basement, an elevator shaft and other enclosed spaces or near a strong interference source), and the user equipment 202 can hardly establish a communication link for data transmission.

[0079] The value range of RSSI is usually between -110 dBm and -30 dBm, and the typical value range is between -100 dBm and -60 dBm. In the first feedback information, when the measured value corresponding to RSSI is between -50 dBm and -30 dBm, it indicates that the signal of the beam in the first beam set received by the U user equipment 202 is very strong, the data transmission is very stable, the data transmission rate is high, and the delay is low; when the measured value corresponding to RSSI is between -70 dBm and -50 dBm, it indicates that the signal of the beam in the first beam set received by the user equipment 202 is good, the wireless link is relatively stable, and the user equipment 202 may be in an area with good coverage of the network device 101; when the measured value corresponding to RSSI is between -101 dBm and -70 dBm, it indicates that the signal of the beam in the first beam set received by the user equipment 202 is poor, the data transmission rate decreases, and transmission interruption may occur.

[0080] In a possible implementation manner, the first feedback information is measured and fed back by the user equipment 202 within N historical time windows. Therefore, the network device 101 can respectively determine the channel conditions of the user equipment 202 within the N historical time windows based on the first feedback information.

[0081] Table 1 L1-RSRP, RSRQ, SINR, and RSSI value range table

[0082] Step S402: Based on the channel conditions, select the types of parameters in the first feedback information.

[0083] In a possible implementation manner, based on the determined channel conditions of the user equipment 202, the network device 101 can select one or more signal parameters from the first feedback information (that is, select one or more from the three signal parameters of L1-RSRP, RSRQ, and SINR). It should be noted that the network device 101 selects one or more types of parameters from the first feedback information specifically by retaining (or eliminating) the specific parameter measurement values corresponding to one or more types of parameters (within the N historical time windows), so that the first feedback information that is more suitable for the communication environment of the user equipment 202 can be used as the reference data for beam prediction during beam prediction.

[0084] Specifically, when the network device 101 determines that the channel condition of the user equipment 202 is a high-interference scenario, such as in a dense urban area or a multi-user competition scenario, the RSRQ can reflect the degree of interference on the signal quality of the beams in the first beam set received by the user equipment 202, and the SINR can reflect the quantization signal-to-noise ratio of the beams in the first beam set received by the user equipment 202. The combination of the two can better dynamically capture the impact of interference fluctuations on the channel. In addition, in a high-interference scenario, the intensity of the interference signal may be higher than that of the useful signal. Since it is difficult to completely separate the useful signal and the interference signal in actual measurements, the measured L1-RSRP is very likely to contain the power component of the interference signal, which will cause the measured L1-RSRP not to accurately reflect the true intensity of the useful signal, but instead increase the overhead of measurement and calculation. Therefore, optionally, the network device 101 can select the parameters RSRQ and SINR from the three signal parameters (L1-RSRP, RSRQ, SINR) of the first feedback information, that is, retain the specific parameter measurement values corresponding to RSRQ and SINR (within N historical time windows) in the first feedback information, or eliminate the specific parameter measurement values corresponding to L1-RSRP (within N historical time windows) in the first feedback information; When the network device 101 determines that the channel condition of the user equipment 202 is a weak signal scenario, such as when the user equipment 202 is at the edge of the coverage area of the network device 101 or indoors, the L1-RSRP can provide information on the beam signal strength and is a key parameter for beam coverage evaluation, while the SINR can provide information on the beam signal quality and can assist in evaluating the signal stability and avoiding misjudgment due to instantaneous noise. The combination of the two can more comprehensively evaluate the wireless communication environment. In addition, when the user equipment 202 is in a weak signal environment, the RSRQ (Reference Signal Receiving Quality) is not very meaningful and may also increase the calculation amount and calculation complexity when performing beam prediction based on the first feedback information. Therefore, optionally, the network device 101 can select the parameters L1-RSRP and SINR from the three parameters (L1-RSRP, RSRQ, SINR) of the first feedback information, that is, retain the specific parameter measurement values corresponding to L1-RSRP and SINR (within N historical time windows) in the first feedback information, or eliminate the specific parameter measurement values corresponding to RSRQ (within N historical time windows) in the first feedback information; When the network device 101 determines that the channel condition of the user equipment 202 is a simplified deployment scenario, that is, the user equipment 202 is in a network coverage environment that is miniaturized, flexible, or lightweight. In one possible aspect, it means that the network device 101 that transmits the first beam set to the user equipment 202 is restricted by resources or has a low-complexity requirement, and thus simplifies the deployment method, network architecture, or operation and maintenance. In this scenario, the scale of the wireless communication system where the user equipment 202 is located is small, the number of devices is relatively small, the interference sources are relatively simple, and the coverage range of the wireless communication system where it is located is also small. The signal propagation path is relatively simple, and L1-RSRP can better reflect the signal strength and coverage. There is no need to measure RSRQ and SINR to evaluate the channel quality. In addition, in the simplified deployment scenario, usually the user equipment 202 does not have too high requirements for the channel quality, and the requirements for real-time performance and reliability are also relatively low. Therefore, only L1-RSRP can better measure the signal quality to ensure that the beam predicted based on this reference information can better meet the requirements of the user equipment 202. Therefore, optionally, the network device 101 can select the parameter L1-RSRP from the three parameters (L1-RSRP, RSRQ, SINR) of the first feedback information, that is, retain the specific parameter measurement values corresponding to L1-RSRP (within N historical time windows) in the first feedback information, or exclude the specific parameter measurement values corresponding to RSRQ and SINR (within N historical time windows) in the first feedback information.

[0085] In some possible implementation manners, the network device 101 can directly use the first feedback information, that is, without screening or selection. In this case, the first feedback information can more comprehensively and accurately reflect the quality of the beams in the first beam set received by the user equipment 202, and can improve the accuracy of beam prediction.

[0086] Step S403: Perform normalization processing on the first feedback information.

[0087] In one possible implementation manner, the first feedback information after parameter selection may include the parameter measurement values corresponding to one or more of the three parameters L1-RSRP, RSRQ, and SINR. As can be seen from Table 1, the value ranges of the three parameters are different. Before using the first feedback information as reference information for beam prediction, it is necessary to perform normalization processing on the parameter measurement values corresponding to different types of parameters in the first feedback information, so as to solve the scale difference problem of different types of data and improve the performance and stability of prediction.

[0088] Optionally, interval scaling can be used to normalize the parameter measurement values of different types of parameters in the first feedback information. Among them, L1-RSRP is used to evaluate the strength of the signal received by the user equipment 202 and is a basic indicator for measuring the quality of the wireless signal, playing a very crucial role in measuring the signal strength. Therefore, when scaling the first feedback information, a differential scaling method can be adopted to ensure the core role of L1-RSRP when performing beam prediction based on the first feedback information.

[0089] Specifically, when no parameter selection is performed on the first feedback information, that is, when the specific parameter measurement values corresponding to the three parameters in the first feedback information are retained, interval scaling can be performed on the specific parameter measurement value corresponding to L1-RSRP. For example, the parameter measurement values corresponding to L1-RSRP within N historical time windows are mapped to the interval [0, 1.2]. For the specific parameter measurement values corresponding to RSRQ and SINR, deviation normalization (Min-Max Normalization) can be performed to the interval [0, 1], that is, the parameter measurement values corresponding to RSRQ and SINR within N historical time windows are mapped to [0, 1]. In this way, L1-RSRP in the first feedback information after normalization has a larger data range, which is equivalent to configuring a higher weight for L1-RSRP in the first feedback information after normalization, highlighting its core position in signal measurement.

[0090] Optionally, when the first feedback information after parameter selection processing (that is, the first feedback information after step S402) only includes the parameter measurement values corresponding to RSRQ and SINR, the specific parameter measurement values corresponding to the two can be deviation-normalized (Min-Max Normalization) to the interval [0, 1], that is, the parameter measurement values corresponding to RSRQ and SINR within N historical time windows are mapped to [0, 1]; Optionally, when the first feedback information after parameter selection processing (that is, the first feedback information after step S402) only includes the parameter measurement values corresponding to L1-RSRP and SINR, interval scaling can be performed on the specific parameter measurement value corresponding to L1-RSRP. For example, the parameter measurement values corresponding to L1-RSRP within N historical time windows are mapped to the interval [0, 1.2], and deviation normalization is performed on the specific parameter measurement value corresponding to SINR, that is, the parameter measurement values corresponding to SINR within N historical time windows are mapped to [0, 1]; Optionally, when the first feedback information after parameter selection processing (i.e., the first feedback information after step S402) only includes the parameter measurement values corresponding to L1-RSRP, the specific parameter measurement values corresponding to L1-RSRP can still be scaled within an interval. For example, the parameter measurement values corresponding to L1-RSRP within N historical time windows are mapped to the interval [0, 1.2]. This can ensure the consistency of normalization processing for multi-parameter scenarios and the dimensional compatibility of reference data in beam prediction. Moreover, compared with only relying on the original value of L1-RSRP in the prior art, mapping the parameter measurement values corresponding to L1-RSRP to the interval [0, 1.2] can amplify the dynamic range of L1-RSRP, enabling it to occupy a higher weight value in beam prediction.

[0091] Step S404: Perform splicing processing on the first feedback information.

[0092] Specifically, the first feedback information includes the measurement values of signal parameters corresponding to each beam in the first beam set within N historical time windows (one or more), where N is an integer greater than or equal to 1, and for each beam, one signal parameter corresponds to one or more measurement values within one historical time window. Therefore, the data volume of the first feedback information is large and there is a certain time relationship between the data. It is necessary to perform certain splicing processing on it to form a time series as the input of the beam prediction model, so that the beam prediction model can predict the beam with the best signal quality for the user equipment 202 at a future moment based on the input with time-order characteristics.

[0093] In a possible implementation manner, first, the parameter measurement values of one or more signal parameters within N historical time windows in the first feedback information can be respectively formed into sequences according to the types of signal parameters. Taking the first feedback information that still contains three signal parameters after parameter selection as an example, the method of splicing the first feedback information is described below. The sequences of signal parameters within N historical time windows after splicing can be: ; ; .

[0094] Among them, can be the total number of beams received by the user equipment 202 that measures and sends the first feedback information, or, in a possible implementation manner, 1 to can represent the identifiers of each beam in the first beam set. Specifically, the user equipment 202 can include k specific user equipments, where k is an integer greater than or equal to 1. Therefore, the sequence The sequence of L1-RSRP measurement values of each beam in the first beam set can be measured for the k-th specific user equipment in the user equipment 202 within the i-th historical time window, where the sequence Any element in it represents the measurement value of L1-RSRP for a certain beam in the first beam set by the k-th specific user equipment in the user equipment 202 within the i-th historical time window. For example, the sequence The element in means: the measurement value of L1-RSRP for the second beam (or the beam with identifier "2") in the first beam set by the k-th specific user equipment in the user equipment 202 within the i-th historical time window; Optionally, the sequence can be the sequence of RSRQ measurement values of each beam in the first beam set measured by the k-th specific user equipment in the user equipment 202 within the i-th historical time window in any historical time window, where any element in the sequence represents the measurement value of RSRQ for a certain beam in the first beam set by the k-th specific user equipment in the user equipment 202 within the i-th historical time window. For example, the element in the sequence in means: the measurement value of RSRQ for the second beam (or the beam with identifier "2") in the first beam set by the k-th specific user equipment in the user equipment 202 within the i-th historical time window; Optionally, the sequence can be the sequence of SINR measurement values of each beam in the first beam set measured by the k-th specific user equipment in the user equipment 202 within the i-th historical time window in any historical time window, where any element in the sequence represents the measurement value of SINR for a certain beam in the first beam set by the k-th specific user equipment in the user equipment 202 within the i-th historical time window. For example, the element in the sequence in means: the measurement value of SINR for the second beam (or the beam with identifier "2") in the first beam set by the k-th specific user equipment in the user equipment 202 within the i-th historical time window.

[0095] Further, the sequences of the three signal parameters of the user equipment 202 within N historical time windows are concatenated in a preset order to obtain a comprehensive signal measurement vector corresponding to each historical time window of the user equipment 202. Optionally, the preset order may be "L1 - RSRP sequence - RSRQ sequence - SINR sequence". In a possible implementation manner, if the user equipment 202 includes k specific user equipments, for any one specific user equipment, the sequences of the three signal parameters corresponding to any one historical time window may be concatenated together to obtain the comprehensive signal measurement vector of this user equipment in any one historical time window. For example:

[0096] wherein, is the comprehensive measurement vector of the k-th specific user equipment in the user equipment 202 within the first historical time window, and the "1" in "sig1" may indicate that the current comprehensive measurement vector is the comprehensive measurement vector corresponding to the first historical time window among the N historical time windows.

[0097] In a possible implementation manner, if after step S402: Based on the channel condition, the types of parameters in the first feedback information are selected, and the first feedback information includes only the parameter measurement values corresponding to RSRQ and SINR, or L1 - RSRP and SINR retained, when concatenating, it can still be concatenated in the above preset order. For example, for the first feedback information that only retains the parameter measurement values corresponding to the signal parameters RSRQ and SINR, if the user equipment 202 includes k specific user equipments, for any one specific user equipment, the sequences of RSRQ and SINR within any one historical time window may be concatenated together to obtain the comprehensive signal measurement vector of this user equipment in any one historical time window:

[0098] For another example, for the first feedback information that only retains the parameter measurement values corresponding to the signal parameters L1 - RSRP and SINR, if the user equipment 202 includes k specific user equipments, for any one specific user equipment, the sequences of L1 - RSRP and SINR within any one historical time window may be concatenated together to obtain the comprehensive signal measurement vector of this user equipment in any one historical time window:

[0099] The first feedback information is concatenated in the order of the L1 - RSRP sequence - the RSRQ sequence - the SINR sequence. That is, the signal parameter L1 - RSRP is placed at the head of the concatenated sequence. The linear average power of the reference signal received by the user equipment 202 on a specific resource element can be directly reflected by L1 - RSRP, and the other two signal parameters provide supplementary information on the signal quality. It should be noted that the above concatenation order is a possible implementation provided by the embodiments of the present application, and does not constitute a specific limitation on the embodiments of the present application. In other possible implementations, the preset concatenation order can be other schemes.

[0100] Furthermore, the comprehensive signal measurement vectors corresponding to the user equipment 202 in N historical time windows are formed into a comprehensive signal measurement sequence in the chronological order of the historical time windows to obtain the comprehensive signal measurement sequence. For example, for the kth specific user equipment in the user equipment 202, the comprehensive signal measurement sequence can be obtained as follows:

[0101] Among them, respectively represent the comprehensive signal measurement sequence of the 1st historical time window, the comprehensive signal measurement sequence of the 2nd historical time window, the comprehensive signal measurement sequence of the 3rd historical time window, and so on up to the comprehensive signal measurement sequence of the Nth historical time window of the kth specific user equipment in N historical time windows.

[0102] If the first feedback information only retains the signal parameter L1 - RSRP, then only the parameter measurement values of L1 - RSRP within N historical time windows in the first feedback information need to be formed into a sequence to obtain the sequence:

[0103] And the L1 - RSRP sequences corresponding to the user equipment 202 in N historical time windows are formed into a comprehensive signal measurement sequence in the chronological order of the historical time windows.

[0104] Based on the above pre - processing of the first feedback information, the finally obtained pre - processed first feedback information can be in the form of a sequence. That is, the pre - processed first feedback information can be the comprehensive measurement sequence of the user equipment 202. It should be noted that the user equipment 202 can include one or more specific devices or chips. That is, the user equipment 202 can be a general term for user equipment in any wireless communication system, or can refer to a specific user equipment.

[0105] Optionally, the concatenation processing of the first feedback processing can also be performed by the user equipment 202. That is, after the user equipment measures the beams in the first beam set to obtain the first feedback information, it can first concatenate the first feedback information to obtain the first feedback information in the form of a comprehensive measurement sequence, and then send the first feedback information to the network device 101. The specific process can refer to the above process of concatenating the first feedback information including three signal parameters. Further, the network device 101 can analyze the channel conditions and select the type of signal parameters based on the concatenated first feedback information to obtain the preprocessed first feedback information.

[0106] Step S305: Perform beam prediction based on the preprocessed first feedback information.

[0107] Specifically, the network device 101 can perform beam prediction through a beam prediction model, where the preprocessed first feedback information can be used as the input of the beam prediction model.

[0108] In a possible implementation manner, the network device 101 can also receive reference information for beam prediction, so as to be input into the beam prediction model as auxiliary information for beam prediction. The reference information is a parameter related to beam prediction, such as a beam selection rule, a quality evaluation threshold, etc. These reference information can be preset relevant information and can guide the beam prediction process of the model.

[0109] In a possible implementation, the network device 101 also needs to input the third beam set into the beam prediction model, so that the beam prediction model can predict the second beam set and / or the second prediction information from the third beam set, that is, obtain the beam prediction result. Among them, the network device 101 can maintain the third beam set, and the third beam set can be a dynamic beam set maintained by the network device 101. Moreover, the width of the beams in the third beam set is smaller than that of the beams in the first beam set. The beams in the third beam set are a set of candidate beams for future data transmission to the user equipment 202, that is, the beams actually establishing a communication link with the user equipment in the wireless communication system. They have stronger directivity, higher gain in the target direction, and the number of beams in the third beam set is usually greater than that in the first beam set. In a possible implementation, the first beam set can be a wide beam set (Set B), and the third beam set can be a narrow beam set (Set A). The second beam set is a set of beams that meet the preset conditions and are predicted by the beam prediction model from the third beam set in combination with the reference information and the first feedback information. The second prediction information is the measured value of the signal parameters corresponding to the beams that meet the preset conditions and are predicted by the beam prediction model from the third beam set in combination with the reference information and the first feedback information. Optionally, the types of signal parameters included in the second prediction information can depend on the types of signal parameters included in the first feedback information input into the beam prediction model. That is, if the first feedback information input into the beam prediction model only includes one or more signal parameters among L1-RSRP, RSRQ, and SINR, the second prediction information also correspondingly includes the same types of signal parameters. For example, after step S304: preprocessing the first feedback information, if the first feedback information only includes the parameter measurement values corresponding to the signal parameters RSRQ and SINR and is input into the beam prediction model, then the second prediction values predicted by the beam prediction model also only include the RSRQ and SINR measurement values of the beams that meet the preset conditions and are predicted from the third beam set. Among them, the preset conditions can be different according to different beam prediction models used. Specifically, reference can be made to the relevant description of the preset conditions in the following Figure 4B corresponding description. In addition, optionally, the first beam set, the second beam set, and the third beam set can be sets of corresponding beam identifiers, rather than sets of actual beams.

[0110] In a possible implementation, the beam prediction model can be a gated recurrent unit (GRU) model. The GRU model is a special recurrent neural network (RNN) and can be used to process sequence data (such as time series, natural language, etc.). Specifically, reference can be made to Figure 4A , Figure 4A which is a network structure diagram of a GRU beam prediction model provided by an embodiment of this application. AsFigure 4A As shown, the GRU beam prediction model may include an input layer (Input Layer), which is the interface for the GRU beam prediction model to interact with external data and is responsible for receiving the input at each time step of the sequence data. For example, it can receive the first feedback information and reference information as input data. The GRU beam prediction model may also include a GRU layer. The GRU layer is the core of the GRU beam prediction model and consists of multiple GRU units. It is used to process the sequence data and capture the long-term dependencies therein. For example, it performs a non-linear transformation on the input data in combination with historical data and passes it to the next layer. The GRU layer belongs to a type of hidden layer (HiddenLayer). Further, the GRU beam prediction model may also include fully connected layers (Fully connected layers). The fully connected layer is also one of the core components of the GRU beam prediction model and is also a type of hidden layer. It is used to perform linear transformation and non-linear activation on the input data and historical data. Still further, the GRU beam prediction model may also include an output layer (OutputLayer) for generating the beam prediction result of the model. The beam prediction result may include a second beam set or second prediction information or a combination of both, and the design of the output layer depends on the specific task type. For example, if the beam prediction result that the GRU beam prediction model finally needs to output only includes the second beam set, the output layer can use the softmax function. This activation function can convert the original value of the output layer into a probability value. That is, the output layer can output the selection probability of each beam in the third beam set. The selection probability described here can be the suitability of the corresponding beam for transmitting data to the user equipment 202 in the future time window. The beam prediction model can determine K beams that meet the preset conditions as the second beam set based on the selection probability of each beam in the third beam set. The preset conditions here can be: the top K beams with the highest selection probability in the third beam set, or it can be: K beams in the third beam set with a selection probability greater than the threshold (if there are more than K beams with a selection probability greater than the threshold, K beams can be randomly sampled from the beams with a selection probability greater than the threshold); if the beam prediction result that the GRU beam prediction model finally needs to output only includes the second prediction information, the output layer can use a linear activation function to directly output the second prediction information.

[0111] Specifically, compared with the traditional recurrent neural network (RNN) model, the GRU model can capture the changes of wireless signals in the time dimension through the gated recurrent mechanism. Refer to Figure 4B , Figure 4B is an input-output schematic diagram of a GRU network provided by an embodiment of the present application. The GRU beam prediction model can be composed of the current input and the hidden state of the previous time step Constitute the input of the current time step. Here, the time step refers to a discrete time point in the sequence data, corresponding to an element in the sequence data. For example, the preprocessed first feedback information includes a comprehensive measurement sequence, and an element in this comprehensive measurement sequence can correspond to a time step; the hidden state refers to the internal state of the GRU beam prediction model at each time step, which is used to store the historical information of the sequence and is the core for capturing the long-term relationships in the sequence (for example, it can capture the time-domain relationships within the first feedback information). The GRU beam prediction model combines and to obtain the output of the current time step and the hidden state corresponding to the next time step .

[0112] In addition, compared with traditional recurrent neural network (RNN) models, such as long short-term memory (LSTM) networks, the GRU model simplifies the model structure through reset gates and update gates (LSTM includes input gates, forget gates, and output gates), reducing the number of parameters and thus the computational amount, and its inference speed is faster and the efficiency is higher.

[0113] Step S306: Determine the fourth beam set based on the beam prediction result.

[0114] Specifically, after obtaining the beam prediction result through the beam prediction model, the network device 101 can determine the fourth beam set based on the beam prediction result. The fourth beam set is the set of beams that the network device 101 finally actually transmits to the user device 202. That is to say, the network device 101 can obtain the beam prediction result through the beam prediction model, but the beam prediction result is predicted by the beam model and may not actually be completely suitable for transmitting to the user device 202 and establishing a communication link. Therefore, the network device can, based on this beam prediction result and combined with the actual communication state of the wireless communication system, determine the set of beams that are finally actually transmitted to the user device 202, that is, the fourth beam set. Optionally, the fourth beam set can be a subset of the second beam set, or can include one or more beams in the second beam set and one or more beams in the third beam set.

[0115] Step S307: Transmit the beams in the fourth beam set.

[0116] Furthermore, the network device 101 can transmit the beams in the fourth beam set to the user device 202.

[0117] Step S308: Measure the fourth beam set to obtain the second feedback information.

[0118] Specifically, after the user equipment 202 receives the beams in the fourth beam set transmitted by the network equipment 101, it can measure the beams in the fourth beam set to obtain the second feedback information. The second feedback information is the parameter measurement values corresponding to the signal parameters L1-RSRP, RSRQ, and SINR of each beam in the fourth beam set measured by the user equipment 202. Optionally, the second feedback information can be the parameter measurement values within the current time window, or the parameter measurement values within one or more time windows, which is used to reflect the signal quality of the beams in the fourth beam set.

[0119] Step S309: Determine the optimal beam based on the second feedback information.

[0120] Specifically, the user equipment 202 can determine the optimal beam in the fourth beam set based on the second feedback information. That is, through the measurement values of the signal parameters of each beam in the fourth beam set, the beam with the best signal quality and most suitable for supporting the establishment of a communication link between the network equipment 101 and the user equipment 202 is determined.

[0121] In addition, optionally, determining the optimal beam in the fourth beam set based on the second feedback information can be performed not only by the user equipment 202, but also by the network equipment 101. For example, after the user equipment 202 obtains the second feedback information through measurement, it can send the second feedback information to the network equipment 101, and the network equipment 101 determines the optimal beam in the fourth beam set by analyzing the second feedback information.

[0122] Step S310: Report the identifier of the optimal beam.

[0123] Specifically, after the user equipment 202 determines the optimal beam, it can send the identifier of the optimal beam to the network equipment to notify the network equipment 101 to establish a communication link with itself (i.e., the user equipment 202) through the beam corresponding to the identifier.

[0124] Step S311: Transmit the optimal beam.

[0125] Specifically, after the network equipment 101 receives the identifier of the optimal beam sent by the user equipment 202, it can transmit the beam corresponding to the identifier to the user equipment 202, that is, the optimal beam, and establish a communication link with the user equipment 202 through the optimal beam to transmit data to the user equipment 202.

[0126] It should be noted that the accompanying drawings involved in the above description are only exemplary drawings for illustrating the embodiments and do not constitute a specific limitation on the present application.

[0127] In a possible implementation, the network device 101 may be a base station. The method may be applied to the base station, and data is transmitted between the base station and the user. The user equipment here may be Figure 2A the user equipment 202 shown in the figure, which can be referred to Figure 3C , Figure 3C is a schematic flowchart of a beam management method on the base station side provided by an embodiment of the present application. The method may include: 1. The base station scans the transmission beams in Set B.

[0128] Specifically, the base station may first scan the transmission beams in Set B to the user equipment. The transmission beams are the beams transmitted by the base station to the user equipment. Set B may be a wide beam set, for example, it may be Figure 2B the wide beam set (Set B) 211 shown in the figure. Further, the user equipment may measure the L1-RSRP, RSRQ, and SINR of each beam in Set B to obtain corresponding measurement values. Among them, the corresponding measurement values may be the first feedback information.

[0129] 2. Report the L1-RSRP, RSRQ, and SINR measurement values of Set B.

[0130] Specifically, the user equipment reports the L1-RSRP, RSRQ, and SINR measurement values of Set B to the base station. Optionally, the measurement values may be the first feedback information corresponding to Set B. After receiving the L1-RSRP, RSRQ, and SINR measurement values of Set B, the base station may perform Top-K beam prediction. Among them, the Top-K beams are the top K beams predicted by the beam prediction model deployed in the base station and most suitable for transmitting data to the user equipment.

[0131] Optionally, the beam prediction model deployed by the base station may be a GRU model, and this model may be obtained through training of the GRU model; during the beam prediction process, the GRU beam prediction model may use the Top-K sampling algorithm. Top-K sampling is a sampling method for generating samples in a probability distribution. That is to say, optionally, the GRU beam prediction model may output the suitability (in the form of probability) of multiple beams for transmitting data to the user equipment, and then the base station performs Top-K sampling on it to obtain the K beams most suitable for transmitting data to the user equipment. Using Top-K sampling can be more inclined to select beams with higher probabilities and improve the quality of beam selection. Among them, optionally, the K beams may form Set A.

[0132] 3. Scan the top K beams.

[0133] Specifically, the K beams scanned and predicted by the base station for the user equipment are the beams in the scanning Set A. In a possible implementation, the user equipment can measure the L1-RSRP, RSRQ, and SINR of the K beams to obtain corresponding measurement values, and determine the optimal beam among the K beams (Set A) based on the measurement values. The optimal beam is the beam with the best signal and the least interference for transmitting data to the user equipment.

[0134] 4. Report the identifier of the optimal beam in Set A.

[0135] Specifically, the user equipment reports the identifier of the optimal beam to the base station.

[0136] 5. Use the optimal beam in Set A for transmission.

[0137] Specifically, after receiving the identifier of the optimal beam reported by the user equipment, the base station can transmit the beam corresponding to the identifier (i.e., the optimal beam) to the user equipment and perform data transmission through the optimal beam. Further, the user equipment receives the scanning of the optimal beam and, optionally, receives the data sent by the base station through the optimal beam.

[0138] The present application embodiment also provides a beam management method, which is applied to a user equipment and includes: Receiving each beam in the first beam set transmitted by the network device, and measuring each beam in the first beam set to obtain first feedback information, where the first feedback information includes measurement values of signal parameters of the first beam set within N historical time windows, and the signal parameters include physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; Sending the first feedback information to the network device.

[0139] In a possible implementation manner, the method further includes: Receiving each beam in the fourth beam set transmitted by the network device, and measuring each beam in the fourth beam set to obtain second feedback information, where the fourth beam set is the beam set used by the network device to determine the optimal beam for the user equipment, and the second feedback information includes measurement values of the signal parameters of each beam in the fourth beam set; Determining the optimal beam in the fourth beam set based on the second feedback information; Sending the identifier of the optimal beam to the network device.

[0140] It should be noted that for the specific process of the beam management method described in the embodiments of the present application, reference can be made to the above Figures 1 - 4BThe relevant descriptions in the application embodiments described above will not be elaborated here.

[0141] The present application embodiment also provides a beam prediction device 50, which is applied to a network device. Refer to Figure 5A , Figure 5A FIG. is a schematic diagram of a beam prediction device 50 provided by the present application embodiment. As Figure 5A shown, the beam prediction device 50 includes: A receiving module 501, configured to receive first feedback information reported by a user equipment, where the first feedback information includes measurement values of signal parameters of a first beam set within N historical time windows, the signal parameters including physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; A prediction module 502, configured to perform beam prediction based on the first feedback information to obtain a beam prediction result, where the beam prediction result includes a second beam set and / or second beam information, the second beam set is a subset of a third beam set, and the third beam set is a set of candidate beams used by the network device to transmit data; the second beam information includes predicted values of the signal parameters of each beam in the second beam set; A scanning module 503, configured to determine a fourth beam set based on the beam prediction result and scan the beams in the fourth beam set for the user equipment, where the fourth beam set is a beam set used by the network device to transmit to the user equipment to determine an optimal beam, and the fourth beam set includes one or more beams in the second beam set, or the fourth beam set includes one or more beams in the second beam set and the third beam set.

[0142] In a possible implementation manner, the receiving module 501 is further configured to: receive an identifier of an optimal beam reported by the user equipment, where the optimal beam is a beam in the fourth beam set.

[0143] The present application embodiment also provides a beam prediction device 60, which is applied to a user equipment. Refer to Figure 5B , Figure 5B FIG. is a schematic diagram of another beam prediction device 60 provided by the present application embodiment. As Figure 5B shown, the beam prediction device 60 includes: A measurement module 601 is configured to measure each beam in a first beam set to obtain first feedback information, where the first feedback information includes measurement values of signal parameters of the first beam set within N historical time windows, the signal parameters including physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; A feedback module 602 is configured to send the first feedback information to a network device; A communication module 603 is configured to receive the optimal beam transmitted by the network device and establish a communication link based on the optimal beam.

[0144] In a possible implementation, the measurement module 601 is further configured to: measure each beam in a fourth beam set to obtain second feedback information, where the fourth beam set is a beam set sent by the network device to the user equipment for determining the optimal beam, and the second feedback information includes measurement values of the signal parameters of each beam in the fourth beam set.

[0145] In a possible implementation, the feedback module 602 is further configured to: send the second feedback information to the network device.

[0146] Please refer to Figure 6 , Figure 6 which is a schematic structural diagram of a user equipment provided by an embodiment of the present application. The user equipment may include a processor 710, an internal memory 720, an antenna 1, an antenna 2, a wireless communication module 730, and a wireless communication module 740, etc.

[0147] It can be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the UE. In other embodiments, the UE may include more or fewer components than those illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0148] The processor 710 may include one or more processing units. For example, the processor 710 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0149] It can be understood that the interface connection relationships among the modules illustrated in this embodiment are only illustrative and do not constitute a structural limitation on the UE. In other embodiments of the present application, the UE may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0150] The internal memory 720 may be used to store computer-executable program codes, and the executable program codes include instructions. The processor 710 executes various functional applications and data processing of the UE by running the instructions stored in the internal memory 720. The internal memory 720 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function, etc. The data storage area may store data created during the use of the UE (such as channel state information), etc. In addition, the internal memory 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc. The processor 710 executes various functions and data processing of the UE by running the instructions stored in the internal memory 720 and / or the instructions stored in the memory provided in the processor.

[0151] The wireless communication function of the UE may be implemented by antenna 1, antenna 2, wireless communication module 730, wireless communication module 740, a modem processor, and a baseband processor, etc.

[0152] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the UE can be used to cover a single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization rate of the antennas. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0153] The wireless communication module 730 may provide solutions for wireless communications including 2G / 3G / 4G / 9G, etc. applied to the UE. The wireless communication module 730 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The wireless communication module 730 may receive electromagnetic waves through antenna 1, filter and amplify the received electromagnetic waves, and then transmit them to the modulation and demodulation processor for demodulation. The wireless communication module 730 may also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves through antenna 1 and radiate it out. In some embodiments, at least some functional modules of the wireless communication module 730 may be disposed in the processor 710. In some embodiments, at least some functional modules of the wireless communication module 730 and at least some modules of the processor 710 may be disposed in the same device.

[0154] The wireless communication module 740 may provide solutions for wireless communications including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc. applied to the user equipment. The wireless communication module 740 may be one or more devices integrating at least one communication processing module. The wireless communication module 740 receives electromagnetic waves through antenna 2, performs frequency modulation and filtering on the electromagnetic wave signals, and sends the processed signals to the processor 710. The wireless communication module 740 may also receive the signals to be sent from the processor 710, perform frequency modulation and amplification on them, and convert them into electromagnetic waves through antenna 2 and radiate them out.

[0155] In addition, an operating system runs on the above components. For example, iOS operating system, Android operating system, Windows operating system, etc. Application programs can be installed and run on the operating system. Those skilled in the art can clearly understand that for the sake of convenience and conciseness of description, the explanations and beneficial effects of the relevant content in any of the above UEs can refer to the corresponding method embodiments provided above, and will not be elaborated here.

[0156] Next, the structure of a network device 1000 provided by an embodiment of the present application will be introduced. Figure 7 It is a schematic structural diagram of a network device provided by an embodiment of the present application.

[0157] As shown Figure 7 in the figure, the network device may include: one or more network device processors 1001, a memory 1002, a communication interface 1003, a receiver 1005, a transmitter 1006, a coupler 1007, an antenna module 1008, and a network device interface 1009. These components may be connected through a bus 1004 or other means. Figure 7 Taking the connection through the bus as an example. Among them: The communication interface 1003 can be used for the network device to communicate with other communication devices, such as user equipment. Specifically, the user equipment can be a cellular phone. Specifically, the communication interface 1003 can be a 5G communication interface or a communication interface of a future new air interface. Not limited to wireless communication interfaces, the network device can also be configured with a wired communication interface 1003, such as a local access network (LAN) interface. The transmitter 1006 can be used to perform transmission processing on the signals output by the network device processor 1001. The receiver 1005 can be used to perform reception processing on the mobile communication signals received by the antenna module 1008.

[0158] In some embodiments of the present application, the transmitter 1006 and the receiver 1005 can be regarded as a wireless modem. In the network device, the number of the transmitter 1006 and the receiver 1005 can both be one or more. The antenna module 1008 can be used to convert the electromagnetic energy in the transmission line into electromagnetic waves in space, or convert the electromagnetic waves in space into electromagnetic energy in the transmission line. The coupler 1007 is used to divide the mobile communication signals received by the antenna module 1008 into multiple paths and distribute them to multiple receivers 1005.

[0159] The memory 1002 is coupled to the network device processor 1001 and is used to store various software programs and / or multiple sets of instructions. Specifically, it may include at least one of the following types: read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or it can also be an Electrically erasable programmable read-only memory (EEPROM). In some scenarios, the memory can also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0160] The network device processor 1001 can be used to read and execute computer-readable instructions. It can include but is not limited to at least one of the following: central processing unit (CPU), microprocessor, digital signal processor (DSP), microcontroller unit (MCU), or various computing devices that run software such as artificial intelligence processors. Each computing device can include one or more cores for executing software instructions to perform operations or processing. The processor can be a single semiconductor chip or can be integrated with other circuits into a semiconductor chip. For example, it can form a system on a chip (SoC) with other circuits (such as codec circuits, hardware acceleration circuits, or various bus and interface circuits), or it can also be integrated as an internal processor of an ASIC in the ASIC. The ASIC integrated with the processor can be separately packaged or can also be packaged together with other circuits. In addition to the cores for executing software instructions to perform operations or processing, the processor can further include necessary hardware accelerators, such as field programmable gate array (FPGA), programmable logic device (PLD), or logic circuits for implementing dedicated logical operations. Specifically, the network device processor 1001 can be used to call the program stored in the memory 1002, such as the implementation program of the uplink resource configuration method provided by one or more embodiments of the present application on the network device side, and execute the instructions included in the program.

[0161] It should be noted thatFigure 7 The network device shown is merely one implementation manner of the embodiments of the present application. In practical applications, the network device may further include more or fewer components, which are not limited herein.

[0162] It should be understood that each step in the above method embodiments can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The method steps disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware processor, or executed and completed by the combination of the hardware and software modules in the processor.

[0163] The present application also provides a terminal device, which may include: a memory and a processor. Among them, the memory can be used to store computer programs; the processor can be used to call the computer programs in the memory so that the terminal device executes the method executed on the terminal device side in any one of the above embodiments.

[0164] The present application also provides a terminal device, which may include: a memory and a processor. Among them, the memory can be used to store computer programs; the processor can be used to call the computer programs in the memory so that the terminal device executes the method executed on the terminal device side in any one of the above embodiments.

[0165] The present application also provides a chip system, and the chip system includes at least one processor for implementing the functions involved on the terminal device side in any one of the above embodiments.

[0166] In a possible design, the chip system further includes a memory, and the memory is used to store program instructions and data, and the memory is located inside or outside the processor.

[0167] The chip system may be composed of chips, or may include chips and other discrete devices.

[0168] Optionally, the processor in the chip system may be one or more. The processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented by software, the processor can be a general-purpose processor, which is implemented by reading the software code stored in the memory.

[0169] Optionally, the memory in the chip system may also be one or more. The memory can be integrated with the processor or separately arranged from the processor, and the embodiments of the present application do not limit this. Exemplarily, the memory can be a non-transitory processor, such as a read-only memory ROM, which can be integrated with the processor on the same chip or separately arranged on different chips. The embodiments of the present application do not specifically limit the type of the memory and the setting manner of the memory and the processor.

[0170] Exemplarily, the chip system may be a field programmable gate array (FPGA), may be an application specific integrated circuit (ASIC), may also be a system on chip (SoC), may also be a central processor unit (CPU), may also be a network processor (NP), may also be a digital signal processor (DSP), may also be a micro controller unit (MCU), may also be a programmable logic device (PLD) or other integrated chips.

[0171] The present application also provides a computer program product, which includes: a computer program (which may also be referred to as code, or instruction). When the computer program is run, it causes a computer to execute the method performed on the terminal device side in any one of the above embodiments.

[0172] The present application also provides a computer-readable storage medium, which stores a computer program (which may also be referred to as code, or instruction). When the computer program is run, it causes a computer to execute the method performed on the terminal device side in any one of the above embodiments.

[0173] The various embodiments of the present application can be combined arbitrarily to achieve different technical effects.

[0174] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (such as coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state disk (SSD)), etc.

[0175] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by relevant hardware instructed by a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as ROM or random access memory RAM, magnetic disks, or optical discs.

[0176] In summary, the above are only embodiments of the technical solutions of this application and are not used to limit the protection scope of this application. Any modifications, equivalent replacements, improvements, etc. made based on the disclosure of this application shall be included within the protection scope of this application.

Claims

1. A beam management method, characterized in that, Applied to a network device, including: Receiving first feedback information reported by a user device, where the first feedback information includes measurement values of signal parameters of a first beam set within N historical time windows, the signal parameters including physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; Performing beam prediction based on the first feedback information to obtain a beam prediction result, where the beam prediction result includes a second beam set and / or second beam information, the second beam set is a subset of a third beam set, and the third beam set is a set of candidate beams used by the network device for data transmission; the second beam information includes predicted values of the signal parameters of each beam in the second beam set.

2. The method according to claim 1, wherein The first feedback information includes measurement values of the signal parameters of each beam in the first beam set within each of the N historical time windows, where for one signal parameter of each beam, there is one or more measurement values corresponding to one historical time window.

3. The method according to claim 1, wherein The performing beam prediction based on the first feedback information to obtain a beam prediction result includes: Inputting the first feedback information into a beam prediction model to output a beam prediction result.

4. The method according to claim 3, wherein The inputting the first feedback information into a beam prediction model to output a beam prediction result includes: Determining the channel condition of the user device based on the first feedback information; Based on the channel condition, preprocessing the first feedback information to obtain preprocessed first feedback information, where the types of parameters included in the signal parameters in the preprocessed first feedback information are less than or equal to the types of parameters included in the signal parameters in the first feedback information before preprocessing; Inputting the preprocessed first feedback information into the beam prediction model to output a beam prediction result.

5. The method according to claim 4, characterized in that, The preprocessing the first feedback information includes: Selecting one or more parameters from L1-RSRP, RSRQ, and SINR based on the channel condition; Normalizing the measurement values corresponding to the selected one or more parameters in the first feedback information according to the types of parameters to map the measurement values corresponding to different types of parameters to different value ranges.

6. The method according to claim 4, characterized in that The method further includes: Receiving reference information, where the reference information includes one or more of a beam selection rule and a parameter evaluation threshold; The inputting the preprocessed first feedback information into a beam prediction model to output a beam prediction result includes: Inputting the preprocessed first feedback information and the reference information into the beam prediction model to output a beam prediction result.

7. The method according to claim 1, characterized in that, The second beam set includes K beams, where K is an integer greater than 1, and the K beams are K beams in the third beam set that meet a preset condition.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Based on the beam prediction result, determine a fourth beam set, where the fourth beam set is a beam set transmitted by the network device to the user equipment for determining an optimal beam, the fourth beam set includes one or more beams in the second beam set, or the fourth beam set includes one or more beams in the second beam set and the third beam set, and the optimal beam is a beam in the fourth beam set; Transmit the beams in the fourth beam set to the user equipment; Receive the identifier of the optimal beam reported by the user equipment; Transmit the optimal beam to the user equipment.

9. The method according to any one of claims 3 to 7, characterized in that The beam prediction model is a gated recurrent unit (GRU) model.

10. A beam management method, characterized in that, When applied to a user equipment, it includes: Receive each beam in the first beam set transmitted by the network device, and measure each beam in the first beam set to obtain first feedback information, where the first feedback information includes measurement values of signal parameters of the first beam set within N historical time windows, and the signal parameters include physical layer reference signal received power (L1-RSRP), reference signal received quality (RSRQ), and signal-to-interference-plus-noise ratio (SINR), and N is an integer greater than or equal to 1; Send the first feedback information to the network device.

11. The method according to claim 10, wherein The method further includes: Receive each beam in the fourth beam set transmitted by the network device, and measure each beam in the fourth beam set to obtain second feedback information, where the fourth beam set is a beam set transmitted by the network device to the user equipment for determining an optimal beam, and the second feedback information includes measurement values of the signal parameters of each beam in the fourth beam set; Determine the optimal beam in the fourth beam set based on the second feedback information; Send the identifier of the optimal beam to the network device.

12. A beam management device, characterized in that, When applied to a network device, the apparatus includes: A receiving module, configured to receive first feedback information reported by a user equipment, where the first feedback information includes measurement values of signal parameters of a first beam set within N historical time windows, and the signal parameters include physical layer reference signal received power (L1-RSRP), reference signal received quality (RSRQ), and signal-to-interference-plus-noise ratio (SINR), and N is an integer greater than or equal to 1; A prediction module, configured to perform beam prediction based on the first feedback information to obtain a beam prediction result, where the beam prediction result includes a second beam set and / or second beam information, the second beam set is a subset of a third beam set, and the third beam set is a set of candidate beams used by the network device for data transmission; the second beam information includes prediction values of the signal parameters of each beam in the second beam set; A scanning module, configured to determine a fourth beam set based on the beam prediction result, and scan the beams in the fourth beam set for the user equipment, where the fourth beam set is a beam set transmitted by the network device to the user equipment for determining an optimal beam, and the fourth beam set includes one or more beams in the second beam set, or the fourth beam set includes one or more beams in the second beam set and the third beam set.

13. The device according to claim 12, wherein The receiving module is further configured to: receive an identifier of the optimal beam reported by the user equipment, where the optimal beam is a beam in the fourth beam set.

14. A beam management device, characterized in that, Applied to a user equipment, the apparatus includes: A measuring module, configured to measure each beam in a first beam set to obtain first feedback information, where the first feedback information includes measured values of signal parameters of the first beam set within N historical time windows, the signal parameters including physical layer reference signal received power L1-RSRP, reference signal received quality RSRQ, and signal-to-interference-plus-noise ratio SINR, and N is an integer greater than or equal to 1; A feedback module, configured to send the first feedback information to a network device; A communication module, configured to receive the optimal beam transmitted by the network device and establish a communication link based on the optimal beam.

15. The device according to claim 14, characterized in that, The measuring module is further configured to: Measure each beam in a fourth beam set to obtain second feedback information, where the fourth beam set is a beam set transmitted by the network device to the user equipment for determining the optimal beam, and the second feedback information includes measured values of the signal parameters of each beam in the fourth beam set.

16. The device according to claim 15, wherein The feedback module is further configured to: send the second feedback information to the network device.

17. A computer-readable storage medium, characterized in that, Instructions are stored in the computer-readable storage medium, and when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 9.

18. A computer-readable storage medium, characterized in that, Instructions are stored in the computer-readable storage medium, and when executed on a computer, cause the computer to execute the method according to any one of claims 10 and 11.

19. A computer program product, characterized in that, The computer program product includes computer program code, and when the computer program code runs on a computer, causes the computer to execute the method according to any one of claims 1 to 9.

20. A computer program product, characterized in that, The computer program product includes computer program code, and when the computer program code runs on a computer, causes the computer to execute the method according to any one of claims 10 and 11.

Images