Beam processing methods and electronic equipment

Abstract

This application provides a beam processing method and electronic device, relating to the field of communication technology. The method includes: a terminal device receiving first information sent by a network device, the first information indicating abnormal beams that were not blocked during the training phase of a first model but were blocked during the inference phase of the first model; the first model is used for beam prediction. After removing abnormal beams included in a first reference signal set, the terminal device performs measurements based on the first reference signal set to obtain first signal quality information. Then, the terminal device processes the first signal quality information based on the first model to obtain second signal quality information for a second reference signal set. This avoids using the measurement results of blocked beams as model input, thereby optimizing the selection of the best beam and improving the accuracy of beam prediction.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to beam processing methods and electronic devices. Background Technology

[0002] With the development of artificial intelligence (AI) technology, AI technology is now widely used in beam management scenarios, such as beam prediction based on AI.

[0003] The beam prediction process mainly involves the network device sending a set of reference signals to the terminal device. The terminal device then measures this set of reference signals to obtain the signal quality measurement value for each individual reference signal. This measurement value is then used as input to an AI model to predict the signal quality of another set of reference signals.

[0004] However, AI model training is usually done offline. Therefore, if the obstacle environment changes during inference compared to the training process, it will affect the model's inference results. Summary of the Invention

[0005] This application provides a beam processing method and an electronic device, which are applied in the field of communication technology.

[0006] Firstly, embodiments of this application propose a beam processing method applied to a terminal device. The method includes:

[0007] The system receives first information sent by a network device. The first information is used to indicate an abnormal beam that is not occluded during the training phase of the first model but is occluded during the inference phase of the first model. The first model is used to perform beam prediction.

[0008] After removing anomalous beams from the first reference signal set, measurements are performed based on the first reference signal set to obtain the first signal quality information;

[0009] The first signal quality information is processed based on the first model to obtain the second signal quality information of the second reference signal set.

[0010] In this implementation, the network device can send first information to the terminal device to indicate abnormal beams. The terminal device can then remove abnormal beams from the first reference signal set and measure the first reference signal set to avoid using the measurement results of blocked beams as model input. This allows for optimization of the selection of the best beam and improvement of the accuracy of beam prediction.

[0011] In one possible implementation, the method also includes:

[0012] After removing anomalous beams from the second reference signal set, the target beam is determined based on the second signal quality information of the second reference signal set.

[0013] Send information to network devices to indicate the target beam.

[0014] In this way, the terminal device can eliminate abnormal beams in the second reference signal set, and then sort the predicted values ​​of the signal quality in the second reference signal set to avoid selecting blocked beams as target beams, thereby optimizing the selection of the best beam and improving the accuracy of beam prediction.

[0015] In one possible implementation, the target beam is the beam corresponding to the top K reference signals in the second signal quality information after removing abnormal beams, where K is an integer greater than or equal to 1.

[0016] By eliminating abnormal beams and selecting the top K beams as target beams, the rationality of the target beam selection can be improved.

[0017] In one possible implementation, the number of reference signals included in the second set of reference signals is greater than the number of reference signals included in the first set of reference signals.

[0018] This allows for beam prediction based on a small number of reference signals, enabling measurement results to be obtained from a larger number of reference signals.

[0019] In one possible implementation, the anomalous beams are determined based on a first beam set and a second beam set, the first beam set including beams that were not occluded during the training phase and the second beam set including beams that were occluded during the inference phase.

[0020] By determining the first beam set and the second beam set, abnormal beams can be accurately and effectively identified.

[0021] In one possible implementation, the attenuation parameter of the unobstructed beam on at least one path between the terminal device and the network device is less than or equal to a preset threshold. The at least one path includes a direct path, a transmission path, and a reflection path. The attenuation parameter indicates the degree of power attenuation of the beam after passing through the path. The attenuation parameter can be, for example, the beam power attenuation rate described in the embodiments section.

[0022] By using attenuation parameters to determine whether a beam is blocked, the accuracy of identifying abnormal beams can be improved.

[0023] In one possible implementation, the attenuation parameter is determined based on environmental information and beam information;

[0024] Environmental information includes at least one of the following: the location of the terminal device, the location of the network device, the location of obstacles in the environment, and the material of the obstacles. Beam information includes at least one of the following: the beam center direction and the beam propagation distance.

[0025] By using environmental and beam information, the degree of power attenuation of the beam after it passes through the beam can be accurately measured.

[0026] In one possible implementation, the environmental information is determined based on environmental images obtained from the environment in which the network devices and terminal devices are located.

[0027] Secondly, embodiments of this application propose a beam processing method applied to network devices. The method includes:

[0028] Send first information to the terminal device. The first information is used to indicate an abnormal beam that was not occluded during the training phase of the first model but was occluded during the inference phase of the first model. The first model is used to perform beam prediction.

[0029] In one possible implementation, the method also includes:

[0030] The target beam sent by the receiving terminal device does not include abnormal beams.

[0031] In one possible implementation, the target beam is the beam corresponding to the top K reference signals in the second signal quality information after removing abnormal beams, where K is an integer greater than or equal to 1.

[0032] The second signal quality information is the result of the first model processing the first signal quality information. The second signal quality information corresponds to the second reference signal set, and the first signal quality information corresponds to the first reference signal set.

[0033] In one possible implementation, the number of reference signals included in the second set of reference signals is greater than the number of reference signals included in the first set of reference signals.

[0034] In one possible implementation, the anomalous beams are determined based on a first beam set and a second beam set, the first beam set including beams that were not occluded during the training phase and the second beam set including beams that were occluded during the inference phase.

[0035] In one possible implementation, the attenuation parameter of the unobstructed beam on at least one path between the terminal device and the network device is less than or equal to a preset threshold, and the at least one path includes: a direct path, a transmission path, and a reflection path; the attenuation parameter is used to indicate the degree of power attenuation of the beam after passing through the path.

[0036] In one possible implementation, the attenuation parameter is determined based on environmental information and beam information;

[0037] Environmental information includes at least one of the following: the location of the terminal device, the location of the network device, the location of obstacles in the environment, and the material of the obstacles. Beam information includes at least one of the following: the beam center direction and the beam propagation distance.

[0038] In one possible implementation, the environmental information is determined based on environmental images obtained from the environment in which the network devices and terminal devices are located.

[0039] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, the memory for storing code instructions, and the processor for running the code instructions to perform the methods described in the first aspect or any possible implementation of the first aspect.

[0040] The electronic devices can be, for example, terminal devices or network devices.

[0041] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions that, when executed on a computer, cause the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0042] Fifthly, embodiments of this application provide a computer program product including a computer program, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0043] Sixthly, this application provides a chip or chip system including at least one processor and a communication interface. The communication interface and the at least one processor are interconnected via a circuit. The at least one processor is used to run computer programs or instructions to perform the methods described in the first aspect or any possible implementation of the first aspect. The communication interface in the chip can be an input / output interface, pins, or circuits, etc.

[0044] In one possible implementation, the chip or chip system described above in this application further includes at least one memory storing instructions. The memory can be an internal storage unit of the chip, such as a register or cache, or it can be a storage unit of the chip itself (e.g., read-only memory, random access memory, etc.).

[0045] It should be understood that the second to sixth aspects of this application correspond to the technical solutions of the first aspect of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be repeated here. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the architecture of the communication system provided in the embodiments of this application;

[0047] Figure 2 A schematic diagram illustrating the implementation of beam prediction provided in an embodiment of this application;

[0048] Figure 3 A schematic diagram of the signal quality ranking of the reference signal provided in the embodiments of this application. Figure 1 ;

[0049] Figure 4 Signaling interaction diagram of the beam processing method provided in the embodiments of this application;

[0050] Figure 5 This application provides a schematic diagram of the implementation of abnormal beam rejection in its embodiments. Figure 1 ;

[0051] Figure 6 This is a schematic diagram illustrating the relationship between the reference signal sets provided in the embodiments of this application;

[0052] Figure 7 This application provides a schematic diagram of the implementation of abnormal beam rejection in its embodiments. Figure 2 ;

[0053] Figure 8 A schematic diagram of the transmission path provided in the embodiments of this application;

[0054] Figure 9 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application;

[0055] Figure 10 This is a schematic diagram of the network device provided in an embodiment of this application. Detailed Implementation

[0056] To facilitate understanding of the embodiments of this application, the following points will be explained first:

[0057] In this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information for the purpose of instructing A, it can be understood that the instruction information carries A, directly instructs A, or indirectly instructs A.

[0058] In this application, " / " can indicate that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" can be used to describe three relationships between the related objects. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0059] In this application, "at least one" means one or more, and "more than one" means two or more, such as three, four, or more. Similar expressions (such as at least one, at least one, etc.) are used in the same way. "At least one of the following," "one or more of the following," or similar expressions refer to any combination of these items, which may include only a single item or a combination of multiple items. For example, at least one of a, b, or c can mean: a, or b, or c; a and b; or a and c; or b and c; or a, b, and c. Where a, b, and c can be single or multiple.

[0060] In this application, for the convenience of describing the technical solutions of the embodiments of this application, the terms "first" and "second" may be used to distinguish them. The terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0061] In this application, the words "exemplary," "example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "example," or "for example" should not be construed as being more preferred or advantageous than other embodiments or designs. The use of the words "exemplary," "example," or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0062] In this application, "sending information / data" only indicates the direction of information / data transmission, including direct transmission via the device's communication interface (such as an air interface, or simply air interface). "Sending" can also be understood as the "output" of a module interface. "Sending" can also include indirect transmission by the processing unit through the communication interface, meaning that after the processing unit outputs information / data through the module interface, it is transmitted to the device's communication interface and then sent out. "Receiving information / data" only indicates the direction of information / data transmission, including direct reception via the communication interface. "Receiving" can also be understood as the "input" of a module interface. "Receiving information / data" can also include indirect reception by the processing unit through the communication interface, meaning that after the communication interface receives information / data, it is transmitted to the processing unit's module interface and then input to the processing unit. "Sending information / data to… (such as a terminal)" can be understood as the destination of the information being the terminal. It can include sending information / data directly or indirectly to the terminal. "Receiving information / data from… (such as a terminal)" can be understood as the source of the information being the terminal, and can include receiving information / data directly or indirectly from the terminal. Information / data may undergo necessary processing, such as format changes, between the source and destination, but the destination can understand the valid information / data from the source. Similar statements in this application can be understood in a similar way, and will not be repeated here.

[0063] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, 5th Generation (5G) communication systems, satellite communication systems, Wireless Fidelity (WiFi) systems, and the solutions provided in this application can also be applied to future communication systems or other communication systems. This application does not limit these applications.

[0064] Figure 1 This is a schematic diagram of the architecture of the communication system provided in an embodiment of this application. Figure 1 A schematic diagram of a possible, non-limiting system architecture is shown. (e.g.) Figure 1 As shown, the communication system 100 includes a radio access network (RAN) 10 and a core network (CN) 20. Optionally, the communication system 100 also includes an Internet 30. RAN 10 includes at least one RAN node (e.g., Figure 1 110a and 110b in the above) and at least one terminal (such as Figure 1 RAN10 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1(Not shown in the image). The terminal connects to the RAN node wirelessly. The RAN node connects to the core network 20 wirelessly or via a wired connection. The core network equipment in the core network 20 and the RAN node in the RAN 10 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0065] RAN 10 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems. RAN 10 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (Wi-Fi) system. RAN 10 can also be a communication system that integrates two or more of the above systems.

[0066] RAN nodes, sometimes also called access network devices, RAN entities, or access nodes, are part of a communication system used to help terminals achieve wireless access. Multiple RAN nodes in communication system 100 can be of the same type or different types. In some scenarios, the roles of RAN nodes and terminals are relative, for example... Figure 1 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 10 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN nodes and terminals are sometimes referred to as communication devices, for example... Figure 1 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0067] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a 6G mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. Figure 1The RAN nodes can be 110a), micro base stations or indoor stations (110b in Figure 1), relay nodes or donor nodes, or wireless controllers in CRAN scenarios. Optionally, RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be roadside units (RSUs).

[0068] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0069] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0070] Terminals can also be called edge devices, user equipment (UE), mobile stations, mobile terminals, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, etc.

[0071] In the embodiments of this application, the terminal and network device can be hardware devices, or software functions running on dedicated hardware, or software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal and network device.

[0072] To better understand the technical solution of this application, the technical background involved in this application will be explained below.

[0073] Beam management (BM) is a technique for dynamically optimizing beam directionality in wireless communication systems to improve link quality and spectral efficiency. Its core lies in aligning the beams of the transmitter and receiver spatially through processes such as beam scanning, measurement, selection, and adjustment, thereby overcoming the effects of path loss, interference, and user mobility in the wireless channel.

[0074] With the development of artificial intelligence (AI) technology, AI is now widely used in beam management scenarios. For example, beam prediction can be performed based on AI. The beam prediction process mainly involves:

[0075] The network device sends a set of reference signals (e.g., SetB) to the terminal device. The terminal device then measures SetB to obtain the signal quality measurement value corresponding to each reference signal in SetB. The signal quality measurement value can be, for example, Layer 1 Reference Signal Received Power (L1-RSRP).

[0076] Then, the measured signal quality of SetB is used as input or part of the input to the AI ​​model, which is then used to predict the signal quality of another reference signal set (e.g., SetA). The AI ​​model can be deployed in a terminal device or a network device. This embodiment describes the implementation of the AI ​​model deployed in a terminal device. It can be understood that the implementation of the AI ​​model deployed in a network device is similar, with only adaptive adjustments to the relevant steps.

[0077] The purpose of beam prediction is to use a trained model to predict the more expensive SetA using a less expensive SetB. At the same time, it can also rely on life cycle management (LCM) to set key performance indicators (KPIs) to monitor the performance of the AI ​​model. If the performance of the AI ​​model is not good, model switching can be performed.

[0078] For SetB, it can be a set of Channel State Information Reference Signals (CSI-RS), or a set of Synchronization Signals and Physical Broadcast Channel Blocks (SSBs). For SetA, it is usually a set of CSI-RS.

[0079] It can also be understood that SetB is a smaller set than SetA. For example, SetB may contain CSI-RS#[2,4,6,8], while SetA contains CSI-RS#[1,2,3,4,5,6,7,8], where the numbers after the # (such as #1, #2) represent different RS resource indices. Each index typically corresponds to a different beam direction, which means that each reference signal corresponds to one beam.

[0080] CSI-RS#[2,4,6,8] represents Set B containing 4 reference signals, each corresponding to a beam pointing in a different direction. Similarly, CSI-RS#[1,2,3,4,5,6,7,8] represents Set A containing 8 reference signals, each corresponding to a beam pointing in a different direction. In practice, the specific reference signals included in Set A and Set B can be configured according to actual needs; this embodiment does not impose any restrictions on this.

[0081] After measuring SetB, the terminal device can obtain the RSRP corresponding to the four reference signals with indices 2, 4, 6, and 8. These RSRPs can then be used as input to the AI ​​model, allowing the model to output the predicted RSRP values ​​for the eight reference signals in SetA. Alternatively, the AI ​​model can output the probability that each reference signal in SetA is the one with the largest measured RSRP value, i.e., the prediction probability.

[0082] Clearly, without using an AI model, network devices need to send the entire SetA to terminal devices, which then need to perform measurements on the entire SetA, leading to increased resource overhead for beam management.

[0083] AI has two use cases in beam management, namely BM-Case1 and BM-Case2:

[0084] BM-Case 1: Based on the measurement results of reference signal set SetB, perform downlink beam prediction in the spatial domain for reference signal set SetA. In other words, predict the optimal beam pointing of SetA in the spatial domain using instantaneous measurement information of SetB. For example, this can be combined with... Figure 2 To understand, Figure 2 This is a schematic diagram illustrating the implementation of beam prediction provided in an embodiment of this application.

[0085] like Figure 2 As shown, the network device can send a Set B reference resource to the terminal device. The terminal device then measures the reference resource and generates a CSI report. Finally, the terminal device feeds back the CSI report to the network device. The CSI report may include the best beam predicted by the terminal device.

[0086] BM-Case 2: Based on historical measurements of SetB, perform downlink beam prediction for SetA over a time dimension. More specifically, measurements can be taken of SetB over the past M transmission times. These historical measurements of SetB are used as input to or part of the input to an AI model for prediction. The AI ​​model can then output the predicted beam patterns within SetA for the next N time moments. In other words, by utilizing the temporal variation patterns of SetB measurements, the future state of the beams in SetA is predicted.

[0087] From another perspective, BM-Case1 is a single-slot beam prediction, while BM-Case2 is a multi-slot beam prediction. Therefore, under certain conditions, BM-Case1 can be regarded as a special case of BM-Case2 in the prediction process.

[0088] In scenarios where AI models are deployed in terminal devices, after model inference is performed on the terminal device side, the signal quality measurement values ​​corresponding to each reference signal in SetA can be obtained. Then, the signal quality measurement values ​​corresponding to each reference signal in SetA can be sorted, and the beams corresponding to the Top-K reference signals can be selected and reported to the network device. The beams corresponding to the Top-K reference signals can be understood as the optimal transmission beams.

[0089] For example, it can be combined Figure 3 To understand, Figure 3 A schematic diagram of the signal quality ranking of the reference signal provided in the embodiments of this application. Figure 1 .

[0090] As shown in Figure 3, for example, the measured signal quality values ​​of each reference signal in SetA are sorted from highest to lowest. The sorted result is reference signal 5, reference signal 3, reference signal 1, reference signal 4, reference signal 7, reference signal 2, reference signal 6, and reference signal 8. Then, for example, the top 3 (i.e., Top-3) reference signals can be selected, and the beam of these 3 reference signals can be determined as the optimal transmission beam. Figure 3 In the example, the beam 5 corresponding to reference signal 5, the beam 3 corresponding to reference signal 3, and the beam 1 corresponding to reference signal 1 can be determined as the optimal transmission beams.

[0091] In beam management scenarios, current AI-based beam prediction solutions mostly rely on signal quality (such as RSRP) measurements to predict the optimal transmission beam. For terminal devices, after determining the Top-K beams based on the AI ​​model, the information of the Top-K beams is usually directly reported to the network device without incorporating other information to optimize beam selection.

[0092] However, in the framework of AI model-assisted beam management, the training of AI models is usually carried out offline. Therefore, if the obstacle environment changes during inference compared to the obstacle environment during training, it will affect the model's inference results.

[0093] For example, if the surrounding environment of the terminal device changes during the inference process, the predicted optimal beam may actually be blocked. However, the pre-trained model cannot adapt to such environmental changes, which will lead to inaccurate prediction results.

[0094] To address this issue, this application proposes the following technical concept: beam occlusion can be determined both during model training and inference. Based on these results, abnormal beams that were not occluded during training but are occluded during inference can be identified. These abnormal beams can then be removed from both the model's input and output data to optimize the accuracy and effectiveness of beam prediction.

[0095] The beam processing method provided in this application will be described below with reference to specific embodiments. Figure 4 This is a signaling interaction diagram of the beam processing method provided in the embodiments of this application. Figure 5 This application provides a schematic diagram of the implementation of abnormal beam rejection in its embodiments. Figure 1 , Figure 6 This is a schematic diagram illustrating the relationship between the reference signal sets provided in the embodiments of this application. Figure 7 This application provides a schematic diagram of the implementation of abnormal beam rejection in its embodiments. Figure 2 .

[0096] like Figure 4 As shown, the method includes:

[0097] S401. The network device sends first information to the terminal device. The first information is used to indicate an abnormal beam that was not blocked during the training phase of the first model but was blocked during the inference phase of the first model. The first model is used to perform beam prediction.

[0098] In this embodiment, a first model for beam prediction can be deployed in a terminal device. Furthermore, a network device can identify beams that are not occluded during the training phase of the first model but are occluded during the inference phase; in this embodiment, these beams are defined as anomalous beams.

[0099] If the network device determines that an abnormal beam exists, it can send a first message to the terminal device to indicate the abnormal beam.

[0100] In this context, network equipment can be understood as a base station, or it can also be understood as core network equipment; this embodiment does not limit this.

[0101] S402. After removing abnormal beams included in the first reference signal set, the terminal device performs measurements based on the first reference signal set to obtain the first signal quality information.

[0102] After the terminal device receives the first information, it can remove abnormal beams from the input data of the first model to avoid the information of abnormal beams being input into the first model, thereby interfering with the reasoning process of the first model.

[0103] As can be understood from the above embodiments, in a beam prediction scenario, the terminal device can measure a set of reference signals containing a small number of reference signals, and then use the measurement results of this set of reference signals as input to the model. In this embodiment, the set of reference signals containing a small number of reference signals is referred to as the first set of reference signals.

[0104] Furthermore, since some beams may not be obstructed during the training phase but are obstructed during the inference phase, measuring these abnormal beams could lead to inaccurate predictions from the first model. Therefore, after removing abnormal beams from the first reference signal set, measurements can be performed based on the first reference signal set to obtain the first signal quality information. The first signal quality information includes the measured signal quality values ​​of each reference signal in the first reference signal set after removing abnormal beams.

[0105] Can be combined Figure 5 To understand the current situation, such as Figure 5 As shown, the first reference signal set 501 includes reference signal 2, reference signal 4, reference signal 6, and reference signal 8. Assuming the first information indicates that reference signal 4 and reference signal 6 are abnormal beams, the terminal device can remove reference signal 4 and reference signal 6 from the first reference signal set 501, thereby obtaining the first reference signal set 502 after removing the abnormal beams.

[0106] Subsequently, the terminal device measures reference signal 2 and reference signal 8 included in the first reference signal set 502 to obtain first signal quality information. The first signal quality information includes the measured value of the signal quality of reference signal 2 (for example, measurement value a in the figure) and the measured value of the signal quality of reference signal 8 (for example, measurement value b in the figure). The first signal quality information, i.e., measured values ​​a and b, can then be input into the first model as model input.

[0107] This avoids inputting the signal quality measurements of abnormal beams that have already been blocked during the inference stage into the beam, thereby improving the prediction accuracy of the first model.

[0108] S403. The terminal device processes the first signal quality information based on the first model to obtain the second signal quality information of the second reference signal set.

[0109] Subsequently, the terminal device can input the measured first signal quality information into the first model, so that the first model outputs an inference result. The inference result can then indicate the second signal quality information of the second reference signal set, which contains the predicted signal quality values ​​of each reference signal in the second reference signal set.

[0110] It can be understood that the number of reference signals included in the second reference signal set is greater than the number of reference signals included in the first reference signal set. For example, the first reference signal set can be itself of the second reference signal set.

[0111] In one implementation, the second reference signal set can be SetA, and the first reference signal set can be SetB. Alternatively, the second reference signal set can be SetA, the first reference signal set can be SetC, and the first reference signal set after removing anomalous beams can include SetB. The latter case will be illustrated below with specific examples; the former case is similarly understood and will not be elaborated upon further.

[0112] like Figure 6 As shown, SetC can contain elements of SetB as well as anomalous beams (and may also include other beams, not fully shown in the figure). After removing the anomalous beams from SetC, a reference signal set containing SetB can be obtained, meaning SetB can be a subset of SetA. The terminal device can then measure the reference signal set containing SetB to avoid erroneous input to the model.

[0113] and reference Figure 6 It can also be understood that SetA can contain SetC, that is, SetC can be a subset of SetA.

[0114] This combination Figure 6 This describes one possible scenario. In actual implementation, the relationship between the first and second reference signal sets, as well as the reference signals contained in the first and second reference signal sets, can be set according to actual needs. The key is to ensure that the number of reference signals in the second reference signal set is greater than the number of reference signals in the first reference signal set to achieve beam prediction.

[0115] In one implementation, before measuring the reference signals in the first set of reference signals, the terminal device may first report its inference capabilities to the network device. These inference capabilities may include, for example, the number of reference signals contained in the first and second sets of reference signals. Subsequently, the network device can configure the reference signals based on the inference capabilities reported by the terminal device. For instance, it can configure the reference signals included in the first and second sets of reference signals based on the number of reference signals reported by the terminal device.

[0116] S404. After removing abnormal beams included in the second reference signal set, the terminal device determines the target beam based on the second signal quality information of the second reference signal set.

[0117] Reference Figure 6 The example can also be understood that the second set of reference signals may also include anomalous beams. Therefore, anomalous beams included in the second set of reference signals can be eliminated before selecting the target beam to avoid identifying anomalous beams as the best beam.

[0118] In one implementation, after removing the anomalous beams included in the second reference signal set, the signal quality of each reference signal included in the second reference signal set can be sorted, and then the beams corresponding to the top K reference signals in the sorting can be selected as the target beams.

[0119] For example, you can refer to Figure 7 To illustrate, as shown in Figure 3, for example, the second reference signal set includes eight reference signals, namely reference signal 1 to reference signal 8. And suppose that reference signal 1, reference signal 4, and reference signal 6 are anomalous beams. Then, after removing these three anomalous beams, we obtain the second reference signal set, which includes reference signals 2, 3, 5, 7, and 8, after removing the anomalous beams.

[0120] Next, the predicted signal quality values ​​for each reference signal in the second set of reference signals (after removing anomalous beams) can be sorted from highest to lowest. The sorted predicted signal quality values ​​are: Reference Signal 5, Reference Signal 3, Reference Signal 7, Reference Signal 2, and Reference Signal 8. Then, for example, the top 3 (Top-3) reference signals can be selected, and the beams of these 3 reference signals can be determined as the optimal transmission beams. Figure 7 In the example, the beam 5 corresponding to reference signal 5, the beam 3 corresponding to reference signal 3, and the beam 7 corresponding to reference signal 7 can be determined as the optimal transmission beams.

[0121] In this way, after eliminating abnormal beams, the best beam can be selected according to the second signal quality information, which is the target beam in this embodiment, so as to avoid selecting the blocked beam as the best beam.

[0122] S405. The terminal device sends information to the network device to indicate the target beam.

[0123] After the terminal device performs beam prediction and determines the target beam, it can send information indicating the target beam to the network device to inform the network device of the best beam predicted by the terminal device.

[0124] In one implementation, after receiving information from the terminal device indicating the target beam, the network device can perform secondary verification, for example. The network device can send a reference signal corresponding to the target beam to the terminal device, which can then measure the reference signal sent by the network device and send the measurement results back to the network device. The network device can then verify whether the target beam is the optimal beam based on the measurement results.

[0125] In this embodiment, the network device can send first information indicating abnormal beams to the terminal device. The terminal device can then remove abnormal beams from a first set of reference signals before measuring the first set of reference signals to avoid using the measurement results of blocked beams as model input. Furthermore, the terminal device can also remove abnormal beams from a second set of reference signals and then sort the predicted signal quality values ​​in the second set of reference signals to avoid selecting blocked beams as target beams. This optimizes the selection of the best beam and improves the accuracy of beam prediction.

[0126] Based on the above introduction, for example, the first information can be carried through downlink control information (DCI). The implementation of carrying the first information through DCI will be explained below with reference to Table 1.

[0127] Table 1

[0128]

[0129] The TCI Present in DCI field is used to activate the TCI mode. When the value of this field is 0, it indicates that the single TCI mode is activated. When the value of this field is 1, it indicates that the multiple TCI modes are activated.

[0130] The Multi-TCI Indicator field is used to further indicate the type of TCI mode used when multi-TCI mode is activated.

[0131] When this field is set to 00, it indicates one of the four TCI-State modes (this mode can be the default mode). When this field is set to 01, it indicates the beam cluster mode, that is, the four TCI-States are used as a group (beam cluster), for example, when the beam cluster needs to be pre-configured by RRC signaling. When this field is set to 10, it indicates the AI-TCI mode, that is, the scheduling will use an AI model to dynamically predict the beam.

[0132] The TCI-State List field is used to indicate a dynamic list of TCI states, where each TCI state occupies 3 to 7 bits.

[0133] The Resource Mapping field is used to indicate resource mapping rules, corresponding to frequency division multiplexing, space division multiplexing, time division multiplexing, etc.

[0134] The UE-Capability-confirmation field is used to confirm the UE's capabilities. When the value of this field is 1, it instructs the network device to confirm the UE's capabilities. When the value of this field is 0, it instructs the function to ignore this field.

[0135] The "TCI Present in DCI" field indicates whether TCI is enabled. For example, a value of 1 indicates that TCI is enabled, while a value of 0 indicates that the function indicator is ignored.

[0136] The TCI-State ID field is used to indicate the ID of the transmit beam and the ID of the receive beam currently being used in the scheduling.

[0137] The Error beam ID field is used to indicate abnormal beams. For example, 00000 indicates that beam 1 is an abnormal beam, 00001 indicates that beam 2 is an abnormal beam, and so on.

[0138] The above describes one signaling implementation for carrying the first information. In actual implementation, the signaling used to carry the first information can be set according to actual needs, and this application embodiment does not impose any restrictions on this.

[0139] Furthermore, it's important to understand that an excessive number of abnormal beams can negatively impact the normal operation of the primary model. For example, it may result in insufficient input data for inference, and the inference results may lack sufficient data to select a target beam.

[0140] The technical solution of this application may also include, for example, executing the technical solution described in the above embodiments only when the number of abnormal beams is less than or equal to a first quantity threshold, so that the first model can work normally.

[0141] If the number of abnormal beams exceeds the first threshold, the system can enter the model performance monitoring stage or retrain the first model. That is, beam prediction is not performed based on the first model first, in order to improve the accuracy of beam prediction by the first model.

[0142] Referring to the above embodiments, in one implementation, the first reference signal set can be SetC, and the first reference signal set after removing abnormal beams can include SetB. For example, the difference between the number of elements in SetC and the number of elements in SetB can be used as a first quantity threshold. Alternatively, the first quantity threshold can be set according to actual needs, which is not discussed in this embodiment.

[0143] The following section will describe how network devices determine abnormal beams using specific embodiments. This section may include the following three parts.

[0144] Content 1: Building 3D spatial models of network devices.

[0145] In one implementation, the network device can acquire an environmental image of the environment in which the network device and terminal devices are located. This means the environmental image can include the network device, the terminal devices, and their surrounding environment. It is understood that obstacles may exist in the environment in which the network device and terminal devices are located.

[0146] If the multimedia data collected by the network device can be in image format, then environmental images can be directly obtained. Alternatively, the multimedia data collected by the network device can also be in video format, in which case image frames can be extracted from the video to obtain environmental images.

[0147] Subsequently, network devices can process environmental images through semantic segmentation and image depth estimation to obtain a 3D spatial model of the environment in which the network devices and terminal devices are located.

[0148] In this 3D spatial model, the location of the network device can be represented as The location of the terminal device can be represented as The horizontal angle of arrival of the beam can be expressed as And the candidate beam set can be denoted as Based on depth estimation and the intrinsic parameter matrix of the camera used to acquire environmental images, the transformation from 2D image coordinates to 3D spatial coordinates can be completed. For example, in this 3D spatial model, a 3D coordinate system can be established with the location of the network device as the origin.

[0149] Content 2: Network devices determine whether the beam is blocked based on a 3D spatial model.

[0150] In wireless communication systems, signals can propagate through various paths, including direct, reflected, transmitted, and diffracted paths, forming complex multipath channels. In other words, the propagation path of a signal includes a direct path, a transmitted path, and a reflected path.

[0151] A direct path refers to a straight-line propagation path between the receiver and transmitter without any physical obstructions. On a direct path, signal energy is strongest, attenuation is minimal, and propagation delay is shortest. It is typically the most ideal propagation path. The receiver can be, for example, a terminal device, and the transmitter can be, for example, a terminal device, or vice versa.

[0152] A reflection path refers to the path formed when a wave beam encounters a surface of an obstacle much larger than its wavelength (such as a building wall, glass curtain wall, or ground), resulting in specular reflection. Along the transmission path, signal energy is lost, the phase changes, the propagation distance is longer, and the corresponding time delay is also greater.

[0153] The transmission path refers to the path along which a beam continues to propagate after penetrating an obstacle (such as a glass window, wooden wall, or leaves). Along the transmission path, the signal undergoes significant attenuation, the degree of which is closely related to the material and thickness of the obstacle, as well as the signal frequency (the higher the frequency, the greater the attenuation).

[0154] For example, you can refer to Figure 8 To understand, Figure 8 This is a schematic diagram of the transmission path provided in an embodiment of this application.

[0155] like Figure 8 As shown, for example, the network device can be a base station, and the terminal device can be a UE. The base station can act as a transmitter (TX) to send beams to the UE, which acts as a receiver (RX). Each beam can correspond to its own direction. For example, the diagram illustrates four beams, namely b1, b2, b3, and b4.

[0156] As can be understood from the illustrations, obstacles can exist in the environment where the base station and UE are located. For example, beam b1 can reach the UE through an obstacle that can act as a projector, that is, it reaches the receiver through a projection path. Beam b2 can reach the UE without passing through an obstacle, that is, it reaches the receiver through a direct path. Beam b3, for example, may be blocked by an obstacle and cannot reach the UE; that is, beam b3 is the blocked beam. Beam b4 can reach the UE through the reflective surface of an obstacle, that is, it reaches the receiver through a reflection path.

[0157] The decision logic for these three paths will be explained below:

[0158] (1) Direct path determination

[0159] Assuming the environment contains There are several obstacles, and assuming the transmitter is located in the 3D coordinate system described above. The receiver location is The direction of the beam center is Therefore, the beam propagation path can be expressed as the following formula:

[0160] Formula 1

[0161] Wherein, parameter d represents the propagation distance of the beam.

[0162] And, for example, a geometric occlusion indicator function for the i-th obstacle can be defined:

[0163] Formula 2

[0164] As explained above, defining the beam propagation path in a 3D coordinate system, and using the 3D spatial model obtained through modeling, allows us to determine the position of obstacles in the 3D coordinate system. Based on this, for example, we can use ray tracing to determine whether the beam intersects with the i-th obstacle. Alternatively, we can determine whether the beam intersects with the i-th obstacle by checking if there is a focal point between a line and a point.

[0165] So, if there is This indicates that the beam travels along a line-of-sight (LoS) path, which is the direct path described above. In other words, the beam can transmit through a direct path without intersecting with obstacles in the environment.

[0166] And, if there is This indicates that the beam travels along a non-line-of-sight (NLoS) path. A non-line-of-sight path refers to a propagation scenario where there is no physically unobstructed straight-line path between the transmitter and receiver. The signal must reach the receiver through mechanisms such as reflection, diffraction, scattering, or transmission.

[0167] exist Under the condition that the beam does not pass through any object, the beam power attenuation rate This can be expressed as Formula 3 below:

[0168] Formula 3

[0169] in d is the carrier wavelength, and d is the beam propagation distance. Beam power attenuation rate. This can be understood as the degree of power attenuation of a beam after it travels through a direct path. More specifically, it can characterize the difference between the power of the beam before and after traveling through a direct path. This difference can be expressed as a ratio, so the ratio of the beam's power before and after traveling through a direct path can be considered the beam power attenuation rate. .

[0170] Assuming the power attenuation rate threshold that the beam can reach the receiver is... So, if the following conditions are met... If so, the beam can reach the receiver via a direct path.

[0171] (2) Determining the transmission path

[0172] The above describes how network devices can acquire environmental images. Network devices can identify the materials of various obstacles in the environment through semantic segmentation, and then determine the materials of obstacles with transmissive capabilities based on the materials of the obstacles.

[0173] exist Under certain conditions, the beam may still reach the receiver after transmission attenuation. For example, the transmission attenuation coefficient of the i-th obstacle is defined as... Then, the beam power attenuation rate after transmission. It can be represented as:

[0174] Formula 4

[0175] In this embodiment, beam power attenuation rate This can be understood as the degree of power attenuation of the beam after it passes through the transmission path. More specifically, it can characterize the difference between the power of the beam before and after passing through the transmission path. This difference can be expressed as a ratio, so the ratio of the power of the beam before and after passing through the transmission path is the beam power attenuation rate. .

[0176] Assuming the power attenuation threshold of the beam reaching the receiver through the transmission path is... If the following formula (5) is satisfied, it means that the beam can ultimately reach the receiver through the transmission path:

[0177] Formula 5

[0178] (3) Reflection path determination:

[0179] In addition to the transmission path, the beam can also reach the receiver through the reflection path. In one implementation, the existence of a reflection path to the receiver can be determined using the "virtual image point" method.

[0180] Taking a single reflection as an example, let Rj be the reflection attenuation coefficient of the j-th reflection path. Then, the beam power attenuation rate after reflection is... It can be represented as:

[0181] Formula Six

[0182] Where d1 is the distance from the transmitter to the reflection point, and d2 is the distance from the reflection point to the receiver.

[0183] In this embodiment, beam power attenuation rate This can be understood as the degree of power attenuation of the beam after passing through the reflection path. More specifically, it can characterize the difference between the power of the beam before and after passing through the reflection path. This difference can be expressed as a ratio, so the ratio of the beam power before and after passing through the reflection path is the beam power attenuation rate. .

[0184] Assuming the power attenuation threshold of the beam reaching the receiver through the reflection path is... If the following formula (7) is satisfied, it means that the beam can eventually reach the receiver through the reflection path:

[0185] Formula 7

[0186] in, It represents the number of reflection paths.

[0187] The above describes three different methods for determining whether a beam can reach the receiver. If the beam reaches the receiver, it means the beam is not blocked; if the beam cannot reach the receiver, it means the beam is blocked. It's important to understand that the beam can reach the receiver in any way, which indicates that the beam is not blocked.

[0188] For example, if the beam can reach the receiver through at least one of the direct path, reflection path, and transmission path simultaneously, then in this case, under the condition that... In this case, it can be determined that the beam will eventually reach the receiver. In summary, the implementation described above can be used to determine whether a beam is blocked.

[0189] Content 3: Based on the determination of whether the beam is blocked, the network device identifies abnormal beams.

[0190] It's understandable that network devices need to identify anomalous beams, which means identifying unobstructed beams during the training phase and also during the inference phase. For example, the network device can denote t as the time scale for the training and inference phases of the first model.

[0191] During the training of the first model, the network device can send a set of reference signals for measurement (to obtain the input of the first model) and a set of reference signals for verification (to obtain the labeled data of the first model, i.e., the data used to calculate the model loss) to the terminal device. The network device can acquire an environmental image each time it sends a set of reference signals (either for measurement or verification), assuming N images are captured during the training phase. The set of capture times during the training phase can then be defined as... .

[0192] Furthermore, during the inference process of the first model, the network device can send a first set of reference signals to the terminal device. Then, the network device can acquire an environmental image each time it sends the first set of reference signals, assuming a total of M images are captured during the inference phase. The set of capture times during the inference phase can then be defined as... .

[0193] Furthermore, a beam blocking state function can be defined. .

[0194] Then, it can be based on various moments in the training phase (i.e. Using environmental images and beam information from various moments in the training process, a first beam set is determined. This first beam set includes beams that were not occluded during the training phase. The first beam set can be represented as: .

[0195] And, it can be based on each moment of the reasoning phase (i.e. Using environmental images and beam information from various moments in the data, a second beam set is determined. This second beam set includes beams that were occluded during the inference phase. The second beam set can be represented as: .

[0196] The implementation of determining whether a beam is blocked can be understood by referring to the explanation in section 2 above. The intersection of the first and second beam sets represents the abnormal beams—beams that were not blocked during training but were blocked during inference. The network device can then record the identifiers (IDs) of these abnormal beams and send these IDs to the terminal device.

[0197] Based on the implementation method described above, the accuracy of the identified anomalous beams can be improved, thereby providing an accurate data foundation for the subsequent optimization of beam prediction.

[0198] It should also be noted that the application scenario of the technical solution of this application can be BM-Case1 as described above, that is, single-slot beam prediction. However, the algorithm and model training and inference process involved in the solution are also applicable to BM-Case2 as described above, that is, multi-slot beam prediction. In the BM-Case2 scenario, the solution described above can be used to determine whether the beam will be blocked at different times. The process of determining a specific time among multiple times is consistent with that described in the above embodiments.

[0199] It should be noted that the module names involved in the embodiments of this application can all be defined as other names, as long as they can achieve the function of each module, and no specific restrictions are placed on the module names.

[0200] The beam processing method of the present application embodiments has been described above. The apparatus for performing the above method provided in the present application embodiments is described below. Those skilled in the art will understand that the methods and apparatus can be combined with and referenced in each other, and the related apparatus provided in the present application embodiments can perform the steps in the above beam processing method.

[0201] The uplink power control processing method provided in this application can be applied to electronic devices with communication functions. Electronic devices include terminal devices and network devices, which are described below by example.

[0202] Figure 9 This is a schematic diagram of the structure of the terminal device provided in an embodiment of this application. Please refer to... Figure 9 The terminal device 90 may include a transceiver 21, a memory 23, and a processor 22. The transceiver 21 may include a transmitter and / or a receiver. The transmitter may also be referred to as a transmitter, transmitter port, or transmitter interface, etc., and the receiver may also be referred to as a receiver, receiver port, or receiver interface, etc. Exemplarily, the transceiver 21, memory 23, and processor 22 are interconnected via a bus 24.

[0203] The memory 23 is used to store program instructions; the processor 22 is used to execute the program instructions stored in the memory, so that the terminal device 90 performs any of the uplink power control processing methods shown above. The receiver of the transceiver 21 can be used to perform the receiving function of the terminal device in the above uplink power control processing method.

[0204] In this embodiment, the terminal device can be a device that includes wireless transceiver functionality and can cooperate with network devices to provide communication services to users. Specifically, the terminal device can refer to User Equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. For example, the terminal device can be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA), handheld device with wireless communication functionality, computing device or other processing device connected to a wireless modem, in-vehicle device, wearable device, or terminal device in a 5G network or a network after 5G, etc. Here, 5G refers to the fifth generation mobile communication technology, abbreviated as 5G.

[0205] Figure 10 This is a schematic diagram of the network device provided in an embodiment of this application. Please refer to... Figure 10 The network device 101 may include a transceiver 31, a memory 33, and a processor 32. The transceiver 31 may include a transmitter and / or a receiver. The transmitter may also be referred to as a transmitter, transmitter port, or transmitter interface, etc., and the receiver may also be referred to as a receiver, receiver port, or receiver interface, etc. Exemplarily, the transceiver 31, memory 33, and processor 32 are interconnected via a bus 34.

[0206] The memory 33 is used to store program instructions; the processor 32 is used to execute the program instructions stored in the memory, so that the network device 101 performs any of the uplink power control processing methods shown above. The receiver of the transceiver 31 can be used to perform the receiving function of the network device in the above uplink power control processing method.

[0207] In the embodiments of this application, the network device can be a device used to communicate with terminal devices. For example, it can be a base station (BTS) in a Global System for Mobile Communication (GSM) or Code Division Multiple Access (CDMA) communication system, a base station (NodeB, NB) in a Wideband Code Division Multiple Access (WCDMA) system, an evolved Node B (eNB or eNodeB) in an LTE system, or the network device can be a relay station, access point, vehicle-mounted device, wearable device, network-side device in a 5G network or a network after 5G, or a network device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0208] The network devices involved in the embodiments of this application can also be referred to as network devices or Radio Access Network (RAN) devices. RAN devices are connected to terminal devices and are used to receive data from the terminal devices and send it to core network devices. RAN devices correspond to different devices in different communication systems. For example, in 2G systems, they correspond to base stations and base station controllers; in 3G systems, they correspond to base stations and Radio Network Controllers (RNCs); in 4G systems, they correspond to Evolutionary Node Bs (eNBs); and in 5G systems, they correspond to access network devices (e.g., gNBs, Centralized Units (CUs), Distributed Units (DUs)) in New Radio (NR). Furthermore, the network devices described in the embodiments of this application can also be core network devices; this embodiment does not impose any limitations on this.

[0209] This application provides a chip. The chip includes a processor, which is used to call a computer program in memory to execute the technical solutions in the above embodiments. Its implementation principle and technical effects are similar to those in the related embodiments described above, and will not be repeated here.

[0210] This application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it implements the methods described above. The methods described in the above embodiments can be implemented wholly or partially by software, hardware, firmware, or any combination thereof. If implemented in software, the functionality can be stored as one or more instructions or code on or transmitted over the computer-readable medium. The computer-readable medium can include computer storage media and communication media, and can also include any medium that can transfer a computer program from one place to another. The storage medium can be any target medium accessible by a computer.

[0211] In one possible implementation, a computer-readable medium may include RAM, ROM, compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage or other magnetic storage devices, or any other medium targeted to carry or to store the required program code in the form of instructions or data structures, and accessible by a computer. Furthermore, any connection is appropriately referred to as a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, disks and optical discs include optical discs, laser discs, optical discs, Digital Versatile Discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while optical discs optically reproduce data using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0212] This application provides a computer program product, which includes a computer program that, when run, causes a computer to perform the above-described method.

[0213] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, special-purpose computer, embedded processor, or other programmable device to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing device, generate instructions for implementing the flowchart illustrations. Figure 1One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0214] The above specific embodiments further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for beam processing, characterized in that, Applied to a terminal device, the method includes: The network device receives first information, which indicates an abnormal beam that is not occluded during the training phase of the first model but is occluded during the inference phase of the first model, and the first model is used to perform beam prediction; wherein the abnormal beam is determined by the network device by comparing the beam occlusion state during the training phase with the beam occlusion state during the inference phase. After removing anomalous beams from the first reference signal set, measurements are performed based on the first reference signal set to obtain first signal quality information; Based on the first model, the first signal quality information is processed to obtain the second signal quality information of the second reference signal set.

2. The method of claim 1, wherein, The method further includes: After removing the abnormal beams included in the second reference signal set, the target beam is determined based on the second signal quality information of the second reference signal set. Send information to the network device to indicate the target beam.

3. The method of claim 2, wherein, The target beam is the beam corresponding to the top K reference signals in the second signal quality information after removing the abnormal beams, where K is an integer greater than or equal to 1.

4. The method according to any one of claims 1 to 3, characterized in that, The number of reference signals included in the second set of reference signals is greater than the number of reference signals included in the first set of reference signals.

5. The method of claim 4, wherein, The abnormal beams are determined based on a first beam set and a second beam set, the first beam set including beams that were not occluded during the training phase, and the second beam set including beams that were occluded during the inference phase.

6. The method of claim 5, wherein, The attenuation parameter of the unobstructed beam on at least one path between the terminal device and the network device is less than or equal to a preset threshold, wherein the at least one path includes: a direct path, a transmission path, and a reflection path; the attenuation parameter is used to indicate the degree of power attenuation of the beam after passing through the path.

7. The method of claim 6, wherein, The attenuation parameter is determined based on environmental information and beam information; The environmental information includes at least one of the following: the location of the terminal device, the location of the network device, the location of obstacles in the environment, and the material of the obstacles. The beam information includes at least one of the following: the beam center direction and the beam propagation distance.

8. The method of claim 7, wherein, The environmental information is determined based on environmental images obtained from the environment in which the network device and the terminal device are located.

9. A method of beam processing, the method comprising: Applied to network devices, the method includes: The network device sends first information to the terminal device, the first information being used to indicate an abnormal beam that was not occluded during the training phase of the first model but was occluded during the inference phase of the first model, the first model being used for beam prediction; wherein the abnormal beam is determined by the network device by comparing the beam occlusion state during the training phase with the beam occlusion state during the inference phase.

10. The method of claim 9, wherein, The method further includes: The terminal device receives a target beam, which does not include the abnormal beam.

11. The method of claim 10, wherein, The target beam is the beam corresponding to the top K reference signals in the second signal quality information after removing the abnormal beams, where K is an integer greater than or equal to 1. The second signal quality information is the result of the first model processing the first signal quality information. The second signal quality information corresponds to the second reference signal set, and the first signal quality information corresponds to the first reference signal set.

12. The method of claim 11, wherein, The number of reference signals included in the second set of reference signals is greater than the number of reference signals included in the first set of reference signals.

13. The method of any one of claims 9-12, wherein, The abnormal beams are determined based on a first beam set and a second beam set, the first beam set including beams that were not occluded during the training phase, and the second beam set including beams that were occluded during the inference phase.

14. The method of claim 13, wherein, The attenuation parameter of the unobstructed beam on at least one path between the terminal device and the network device is less than or equal to a preset threshold, wherein the at least one path includes: a direct path, a transmission path, and a reflection path; the attenuation parameter is used to indicate the degree of power attenuation of the beam after passing through the path.

15. The method of claim 14, wherein, The attenuation parameter is determined based on environmental information and beam information; The environmental information includes at least one of the following: the location of the terminal device, the location of the network device, the location of obstacles in the environment, and the material of the obstacles. The beam information includes at least one of the following: the beam center direction and the beam propagation distance.

16. The method according to claim 15, characterized in that, The environmental information is determined based on environmental images obtained from the environment in which the network device and the terminal device are located.

17. An electronic device, characterized in that, The electronic device includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, and the one or more processors invoking the computer instructions to cause the electronic device to perform the method as described in any one of claims 1 to 16.

18. A chip system, characterized in that, The chip system is applied to an electronic device, the chip system including one or more processors, the one or more processors being used to invoke computer instructions to cause the electronic device to perform the method as described in any one of claims 1 to 16.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer instructions that, when executed on an electronic device, cause the electronic device to perform the method as described in any one of claims 1 to 16.

20. A computer program product, characterized in that, The computer program product includes computer program code that, when run on an electronic device, causes the electronic device to perform the method as described in any one of claims 1 to 16.

Images