Device and method for autonomous monitoring of beam prediction model

Abstract

Disclosed are a device and method for autonomous monitoring of a beam prediction model. An exemplary method comprises: comparing specific measured beam information and specific predicted beam information which are associated with a common beam; and, on the basis of the comparison, reporting an event to a network device.

Description

Devices and methods for autonomous monitoring of beam prediction models

[0001] Priority Statement

[0002] This application claims priority to Chinese Patent Application No. 202410982509.4, filed on July 22, 2024, entitled "Apparatus and Method for Autonomous Monitoring of Beam Prediction Model", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of communications, and more specifically, to devices and methods for autonomous monitoring of beam prediction models. Background Technology

[0004] The application of artificial intelligence (AI) technology is becoming increasingly widespread. In the field of communications, AI-based beam prediction models can be used to predict the optimal beam for communication between network devices and user equipment. Summary of the Invention

[0005] This disclosure provides devices and methods for autonomous monitoring of beam prediction models.

[0006] One aspect of this disclosure relates to an electronic device including at least one processing unit and at least one storage unit, the at least one storage unit including computer program code that, when executed by the at least one processing unit, causes the electronic device to perform the following operations: comparing: (1) obtaining specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beam information; (2) predicting specific predicted beam information in a set of beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams are at least one common beam shared by both the set of measured beams and the set of predicted beams; and reporting an event to a network device, at least based on the comparison.

[0007] Another aspect of this disclosure relates to an electronic device including at least one processing unit and at least one storage unit, the at least one storage unit including computer program code that, when executed by the at least one processing unit, causes the electronic device to perform the following operations: receiving an event from a user equipment (UE) based on a comparison of: (1) specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beams of the UE; (2) predicting specific predicted beam information in a set of predicted beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams being at least one common beam shared by both the set of measured beams and the set of predicted beams; and, in response to receiving the event, sending an indication to the UE, the indication being associated with model monitoring or one or more lifecycle management operations.

[0008] One aspect of this disclosure relates to a method comprising: comparing: (1) specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beam information; (2) predicting specific predicted beam information in a set of measured beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams being at least one common beam shared by both the set of measured beams and the set of predicted beams; and reporting an event to a network device, at least based on the comparison.

[0009] One aspect of this disclosure relates to a method comprising: receiving an event from a UE, the event being based on a comparison of: (1) specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beams of the UE; (2) predicting specific predicted beam information in a set of predicted beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams being at least one common beam shared by both the set of measured beams and the set of predicted beams; and, in response to receiving the event, sending an indication to the UE, the indication being associated with model monitoring or one or more lifecycle management operations.

[0010] Another aspect of this disclosure relates to a computer-readable storage medium storing one or more instructions that, when executed by one or more processing circuits of an electronic device, cause the electronic device to perform any of the methods described in this disclosure.

[0011] Another aspect of this disclosure relates to a computer program product, including a computer program that, when executed by a processor, implements any of the methods described in this disclosure.

[0012] Another aspect of this disclosure relates to an apparatus comprising components for performing any of the methods described herein. Attached Figure Description

[0013] The above and other objects and advantages of this disclosure will be further described below with reference to specific embodiments and the accompanying drawings. In the drawings, the same or corresponding technical features or components will be represented by the same or corresponding reference numerals.

[0014] Figure 1 shows a schematic diagram of a wireless communication system according to some embodiments of the present disclosure.

[0015] Figure 2 shows an exemplary block diagram of an electronic device according to some embodiments of the present disclosure.

[0016] Figure 3 shows an exemplary block diagram of an electronic device according to other embodiments of the present disclosure.

[0017] Figure 4 shows a flowchart of a method according to some embodiments of the present disclosure.

[0018] Figure 5 shows a flowchart of a method according to some other embodiments of the present disclosure.

[0019] Figure 6 illustrates a schematic diagram of a process according to some embodiments of the present disclosure.

[0020] Figure 7 is a block diagram illustrating a first example of an exemplary configuration of a gNB to which the technologies of this disclosure can be applied.

[0021] Figure 8 is a block diagram illustrating a second example of an exemplary configuration of a gNB to which the technologies of this disclosure can be applied.

[0022] Figure 9 is a block diagram illustrating an example configuration of a communication device to which the technologies of this disclosure can be applied.

[0023] Figure 10 is a block diagram illustrating an example configuration of an automotive navigation device to which the technologies of this disclosure can be applied.

[0024] While the embodiments described in this disclosure may be readily modified and alternatively implemented, specific embodiments thereof are shown by way of example in the accompanying drawings and are described in detail herein. It should be understood that the drawings and the detailed description thereof are not intended to limit the embodiments to the specific forms disclosed, but rather are intended to cover all modifications, equivalents, and alternatives that fall within the spirit and scope of the claims. Detailed Implementation

[0025] Exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings. For clarity and brevity, not all features of the embodiments are described in the specification. However, it should be understood that many implementation-specific settings must be made in carrying out the embodiments to achieve the developer's specific goals, such as complying with constraints related to the device and business, and these constraints may vary depending on the implementation. Furthermore, it should be understood that while development work can be very complex and time-consuming, such development work is merely a routine task for those skilled in the art who benefit from the present disclosure.

[0026] It should also be noted that, in order to avoid obscuring this disclosure with unnecessary details, only processing steps and / or equipment structures closely related to at least the scheme according to this disclosure are shown in the accompanying drawings, while other details that are not closely related to this disclosure are omitted.

[0027] 1. Exemplary System

[0028] Figure 1 illustrates a schematic diagram of a wireless communication system 100 according to an embodiment of the present disclosure. The wireless communication system 100 may include user equipment (UE) 120 and network devices 130. Each network device 130 may provide communication coverage for a specific geographical area and may communicate with UEs 120 located within that coverage area. It should be understood that although the wireless communication system 100 is shown as including one network device 130 and three UEs 120, in other embodiments, the wireless communication system 100 may include multiple network devices 130, and each network device may serve an additional number of UEs 120 without limitation.

[0029] According to some embodiments of this disclosure, the wireless communication system 100 may be a multi-beam communication system. In a multi-beam communication system, multiple beam pairs can be used to transmit and receive data through multiple antennas and beamforming technology equipped on the network device 130 and / or UE 120. These beam pairs can be formed in different directions. Each beam pair can serve communication between the network device 130 and the corresponding UE 120. Therefore, the multi-beam communication system can achieve more efficient resource allocation and higher data transmission rates.

[0030] In a multi-beam communication system, network device 130 and UE 120 can select suitable beam pairs (e.g., optimal transmit and receive beams) from a complete set of selectable beams through a beam management process. A typical beam-scan-based beam management process may include beam selection, beam measurement, and beam reporting. For example, network device 130 can use various transmit beams from the complete set of selectable beams to send multiple reference signals to UE 120 in turn. Correspondingly, each UE 120 can use multiple receive beams from the complete set of selectable beams to receive these multiple reference signals respectively. Each UE 120 can measure the received reference signals to obtain beam measurement results. Each UE 120 can select a subset of reference signals from the received multiple reference signals and report the selected reference signals and their beam measurement results to network device 130. Network device 130 can select a suitable beam (e.g., the beam with the best beam measurement results) from a complete set of optional beams based on information reported by each UE 120 for subsequent communication with that UE 120.

[0031] In beam management based on beam scanning, the overhead of reference signal transmission and beam scanning delay increase with the size of the complete set of selectable beams. To mitigate these issues, an AI model-based beam management process has been proposed. This AI model-based beam management process uses a trained beam prediction model that can predict one or more optimal beams in the entire complete set of selectable beams based on beam information (e.g., beam measurement results) from a subset of beams. Therefore, beam measurements can be performed only on this subset of beams, eliminating the need for beam scanning of all beams in the entire set. Using a beam prediction model has the potential to reduce the overhead of reference signal transmission and beam scanning delay.

[0032] Given that beam prediction models are pre-trained and considering the complexity and variability of communication scenarios, the reliability and accuracy of deployed beam prediction models may change in real time. Therefore, monitoring the performance of deployed beam prediction models is beneficial. Such monitoring is expected to have high accuracy, low overhead, and / or low latency. To this end, this disclosure proposes a technique for autonomous monitoring of beam prediction models, as further described below.

[0033] It should be understood that the technology disclosed herein can be applied to various communication systems. For example, these communication systems may include, but are not limited to, fifth-generation (5G) systems or New Radio (NR), Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (LTE-FDD) systems, LTE Time Division Duplex (LTE-TDD) systems, etc. The technology disclosed herein can also be applied to future communication systems, such as sixth-generation mobile communication systems, etc. The technology disclosed herein can be applied to any existing or future multi-beam communication system.

[0034] 2. Exemplary device

[0035] Figure 2 illustrates an exemplary block diagram of an electronic device 200 according to some embodiments of the present disclosure. The electronic device 200 can be implemented on the user side of a communication system. Therefore, the electronic device 200 can be referred to as a user equipment or terminal device. The electronic device 200 can be used to implement the UE 120 in Figure 1. The electronic device 200 can be used to perform one or more UE-related operations described herein. Specifically, the electronic device 200 can be implemented as the UE itself, as part of the UE, or as a control device for controlling the UE. For example, the electronic device 200 can be implemented as a chip for controlling the UE. In some embodiments herein, the electronic device 200 is implemented as the UE itself, which is merely for the convenience of description and is not intended to constitute a limitation.

[0036] According to some embodiments of this disclosure, electronic device 200 may include communication unit 210, storage unit 220, and processing circuit 230.

[0037] The communication unit 210 of the electronic device 200 can be used to receive or transmit wired or radio transmissions. The communication unit 210 can be used to establish and maintain one or more communication links. Each communication link can carry associated transmissions. These one or more communication links may include communication links between the electronic device 200 and network devices (e.g., with respect to the electronic device 300 described in FIG. 3), such as an uplink or downlink between the electronic device 200 and the network device. In some embodiments of this disclosure, the communication unit 210 can perform functions such as up-conversion, digital-to-analog conversion on transmitted signals and / or functions such as down-conversion, analog-to-digital conversion on received signals. Various techniques can be used to implement the communication unit 210. For example, the communication unit 210 can be implemented as a communication interface component such as an antenna device, radio frequency circuitry, and part of the baseband processing circuitry. In FIG. 2, the communication unit 210 is drawn with dashed lines because the communication unit 210 may alternatively be located within the processing circuitry 230 or outside the electronic device 200.

[0038] The storage unit 220 of the electronic device 200 can store information generated by the processing circuit 230, information received from other devices via the communication unit 210 or information to be sent to other devices, programs, machine code, and data used for the operation of the electronic device 200, etc. According to some embodiments of this disclosure, the storage unit 220 can store beam prediction models, measured beam sets, measured beam information sets, predicted beam sets, and so on, of the electronic device 200. The storage unit 220 can be volatile memory and / or non-volatile memory. For example, the storage unit 220 can include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. The storage unit 220 is drawn with dashed lines because it may alternatively be located within the processing circuit 230 or outside the electronic device 200.

[0039] The processing circuitry 230 of the electronic device 200 can be configured to perform one or more operations, thereby providing various functions of the electronic device 200. The processing circuitry 230 can perform corresponding operations by executing one or more executable instructions stored in the storage unit 220. The processing circuitry 230 can be used to implement one or more steps performed by the UE in various methods according to some embodiments of this disclosure.

[0040] According to some embodiments of this disclosure, the processing circuit 230 can be configured to perform the autonomous monitoring method for beam prediction models described herein.

[0041] Specifically, processing circuitry 230 can be configured to compare specific measured beam information in the measured beam information set with specific predicted beam information in the predicted beam information set. The specific measured beam information can be associated with one or more specific beams in the measured beam information set, while the specific predicted beam information can be associated with the same one or more specific beams in the predicted beam information set of the beam prediction model. The predicted beam information set is generated by the beam prediction model based at least in part on the measured beam information set. In particular, the one or more specific beams can be at least one common beam shared by both the measured beam information set and the predicted beam information set. In other words, processing circuitry 230 can be configured to compare specific measured beam information and specific predicted beam information associated with at least one common beam shared by both the measured beam information set and the predicted beam information set.

[0042] The processing circuitry 230 can then be configured to report an event to the network device, at least based on the comparison. According to some embodiments of this disclosure, the event can indicate the result of autonomous monitoring of the beam prediction model. For example, depending on the result of the comparison, the event can include an indication of prediction success or prediction failure of the beam prediction model. The network device can initiate model monitoring or one or more lifecycle management (LCM) operations in response to the event, as described further below.

[0043] According to some embodiments of this disclosure, the processing circuit 230 may include a comparison unit 231. The comparison unit 231 can perform a comparison of specific measured beam information and specific predicted beam information. For example, the comparison unit 231 can retrieve specific measured beam information from the set of measured beam information and specific predicted beam information from the set of predicted beam information of the beam prediction model from the storage unit 220. The comparison unit 231 can perform the comparison of the specific measured beam information and the specific predicted beam information according to one or more criteria. For example, the one or more criteria may be based on the received strength of a reference signal corresponding to a common beam, or on the matching of the distribution of the common beam in the set of measured beams and the set of predicted beams, or on any other suitable characteristic corresponding to the common beam. In response to the result of the comparison satisfying a specified condition, the comparison unit 231 can generate a prediction success indication or a prediction failure indication of the beam prediction model. Based on the generated indication, the electronic device 200 can report the corresponding event to the network device.

[0044] In some embodiments, the processing circuitry 230 may optionally include a model running unit (not shown). The model running unit may be configured to run a beam prediction model such that the beam prediction model generates a set of predicted beams and a corresponding set of predicted beam information based at least in part on a set of measured beam information. In other embodiments, the model running unit may be located outside the processing circuitry 230 or the electronic device 200.

[0045] In some embodiments, the processing circuitry 230 may optionally include a beam measurement unit (not shown). The beam measurement unit may be configured to perform beam measurements on a set of measurement beams configured for the network device to obtain a set of measured beam information. In other embodiments, the beam measurement unit may be located outside the processing circuitry 230 or the electronic device 200.

[0046] In some embodiments, the processing circuitry 230 may optionally include a beam reporting unit (not shown). The beam reporting unit may be configured to select one or more candidate beams for reporting to the network device. In response to a prediction success indication from the beam prediction model, the beam reporting unit may select the one or more candidate beams from the predicted beam set of the beam prediction model for reporting. In response to a prediction failure indication from the beam prediction model, the beam reporting unit may not select from the predicted beam set of the beam prediction model. Alternatively, the beam reporting unit may select one or more candidate beams that meet predetermined conditions from the measured beam set for reporting. In other embodiments, the beam reporting unit may be located external to the processing circuitry 230 or the electronic device 200.

[0047] In some embodiments, processing circuitry 230 may optionally include an LCM unit (not shown). The LCM unit may be configured to perform one or more LCM operations associated with the beam prediction model. These one or more LCM operations may include, but are not limited to, model deactivation, model activation, model switching, or model selection. The LCM unit may perform a specified LCM operation based on instructions from a network device. In other embodiments, the LCM unit may be located external to processing circuitry 230 or electronics 200.

[0048] Details of the method performed by processing circuit 230 will be further described below. It should be understood that processing circuit 230 in FIG2 is merely exemplary. Processing circuit 230 may include one or more additional units for performing the techniques of this disclosure.

[0049] Figure 3 illustrates an exemplary block diagram of an electronic device 300 according to some embodiments of the present disclosure. The electronic device 300 can be implemented on the network side of a wireless communication system. Therefore, the electronic device 300 can be referred to as a network device or a control device. In some embodiments, the electronic device 300 can be implemented as a base station (BS). For example, the electronic device 300 can be implemented as the BS itself, as part of the BS, or as a control device for controlling the BS. The electronic device 300 can be implemented as a chip for controlling the BS. In some embodiments, the electronic device 300 can be implemented as an access point (AP) in a Wi-Fi system. In some embodiments herein, the electronic device 300 is implemented as the BS itself, which is merely for the convenience of description and is not intended to constitute a limitation. In other embodiments, the electronic device 300 can be implemented as other network devices or control devices associated with the BS.

[0050] According to some embodiments of this disclosure, the electronic device 300 may include a communication unit 310, a storage unit 320, and a processing circuit 330.

[0051] The communication unit 310 of electronic device 300 can be used to receive or transmit wired or radio transmissions. The communication unit 310 can be used to establish and maintain one or more communication links. Each communication link can carry associated transmissions. For example, the one or more communication links can be communication links between electronic device 300 and UE (e.g., electronic device 200), including uplinks and / or downlinks. The communication unit 310 can perform functions such as up-conversion and digital-to-analog conversion on transmitted signals, and / or functions such as down-conversion and analog-to-digital conversion on received signals. Various technologies can be used to implement the communication unit 310. For example, the communication unit 310 can be implemented as a communication interface component such as an antenna device, radio frequency circuitry, and part of the baseband processing circuitry. In Figure 3, the communication unit 310 is drawn with a dashed line because it can alternatively be located within the processing circuitry 330 or outside the electronic device 300.

[0052] The storage unit 320 of the electronic device 300 can store information generated by the processing circuit 330, information received from other devices via the communication unit 310 or information to be sent to other devices, programs, machine code, and data used for the operation of the electronic device 300, etc. The storage unit 320 can be volatile memory and / or non-volatile memory. For example, the storage unit 320 can include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. The storage unit 320 is drawn with dashed lines because it may alternatively be located within the processing circuit 330 or outside the electronic device 300.

[0053] The processing circuitry 330 of the electronic device 300 can be configured to perform one or more operations, thereby providing various functions of the electronic device 300. For example, the processing circuitry 330 can perform corresponding operations by executing one or more executable instructions stored in the storage unit 320. The processing circuitry 330 can be used to implement one or more steps performed by a network device or control device in various methods according to some embodiments of this disclosure.

[0054] According to some embodiments of this disclosure, the processing circuit 330 can be configured to perform the autonomous monitoring method for beam prediction models described herein.

[0055] Specifically, processing circuitry 330 can be configured to receive an event from the UE. This event is based on a comparison between specific measured beam information in the measured beam information set and specific predicted beam information in the predicted beam information set. The specific measured beam information may be associated with one or more specific beams in the measured beam information set, while the specific predicted beam information may be associated with the same one or more specific beams in the predicted beam information set of the beam prediction model. The predicted beam information set is generated by the beam prediction model based at least in part on the measured beam information set. In particular, the one or more specific beams may be at least one common beam shared by both the measured beam information set and the predicted beam information set. In other words, processing circuitry 330 can be configured to receive an event from the UE indicating the result of a comparison between the specific measured beam information and the specific predicted beam information associated with the at least one common beam.

[0056] In response to receiving the event, processing circuitry 330 can be configured to send an indication to the UE, which may be associated with model monitoring or one or more LCM operations. For example, processing circuitry 330 can be configured to initiate additional monitoring of the beam prediction model deployed at the UE. As another example, processing circuitry 330 can be configured to initiate one or more LCM operations on the beam prediction model. These LCM operations may include, but are not limited to, model deactivation, model activation, model switching, or model selection.

[0057] According to some embodiments of this disclosure, processing circuitry 330 may include a model management unit 331. Model management unit 331 may be configured to receive from the UE an event associated with a comparison between specific measured beam information and specific predicted beam information. Model management unit 331 may be configured to specify a corresponding action based on the received event, such as initiating model monitoring or one or more LCM operations. For example, in response to receiving an event containing a prediction failure indication of a beam prediction model, model management unit 331 may initiate additional model monitoring. This additional model monitoring may differ from the autonomous monitoring described in this disclosure. For example, the additional model monitoring may include additional beam measurements for each beam in the predicted beam set. Additionally or alternatively, in response to receiving an event containing a prediction failure indication of a beam prediction model, model management unit 331 may initiate model deactivation or model switching. In response to receiving an event containing a prediction success indication of a beam prediction model, model management unit 331 may not initiate additional model monitoring. Additionally or alternatively, model management unit 331 may initiate model activation or model selection. It should be understood that the model management unit 331 can be configured to specify any appropriate action based on the received events without restriction.

[0058] Details of the method performed by the processing circuit 330 will be further described below. It should be understood that the processing circuit 330 in FIG3 is merely exemplary. The processing circuit 330 may include one or more additional units for performing the techniques of this disclosure.

[0059] It should be noted that the various units described above are exemplary and / or preferred modules for implementing the processes described in this disclosure. These modules may be hardware units (such as central processing units, field-programmable gate arrays, digital signal processors, or application-specific integrated circuits) and / or software modules (such as computer-readable programs). The modules for implementing the various steps described below are not described exhaustively above. However, wherever there is a step that performs a certain process, there may be corresponding modules or units (implemented by hardware and / or software) for implementing the same process. All combinations of the steps described below and the units corresponding to these steps are included in the disclosure of this disclosure, provided that the technical solutions they constitute are complete and applicable.

[0060] Furthermore, devices composed of various units can be incorporated as functional modules into hardware devices such as computers. In addition to these functional modules, electronic devices can, of course, have other hardware or software components.

[0061] 3. Exemplary Method

[0062] Figure 4 illustrates a flowchart of a method 400 for autonomous monitoring of a beam prediction model according to some embodiments of the present disclosure. Method 400 can be executed at a UE. For example, method 400 can be executed by UE 120. UE 120 can be implemented by the aforementioned electronic device 200. Accordingly, method 400 can be executed by the processing circuitry 230 of electronic device 200.

[0063] Method 400 may begin at step 410. In step 410, the UE may be configured to compare specific measured beam information and specific predicted beam information associated with at least one common beam. Specifically, the UE may be configured to compare: (1) specific measured beam information in the measured beam information set, which is associated with one or more specific beams in the measured beam information set; and (2) specific predicted beam information in the predicted beam information set, which is associated with the one or more specific beams in the predicted beam set of the beam prediction model. The predicted beam set is generated by the beam prediction model at least in part based on the measured beam information set. The one or more specific beams are at least one common beam shared by both the measured beam set and the predicted beam set.

[0064] The beam prediction model disclosed herein refers to a model trained using AI or machine learning techniques. This model can be trained to predict one or more optimal beams for communication. For example, the beam prediction model can be trained to predict one or more available beams from a larger beam set (e.g., a complete set of selectable beams) based at least in part on a set of measured beam information associated with a smaller beam set (e.g., a set of measured beams or a subset thereof). The one or more available beams or a subset thereof can be selected as the prediction beam set. For example, the beam prediction model can output an output beam set containing one or more available beams and / or prediction information associated with each available beam (e.g., predicted reference signal reception strength, predicted probability of becoming the optimal beam, etc.). The prediction beam set of the beam prediction model may include a subset of available beams from the output beam set that have the best prediction information.

[0065] It should be understood that the beam prediction model of this disclosure can be an artificial intelligence model obtained using any existing or future-developed technology. Exemplary artificial intelligence models include, but are not limited to, models trained by convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTMs), generative models, random forests, and their variations and augmentation algorithms. Each artificial intelligence model can be represented by a set of model parameters characterizing the model. For example, for a CNN model, the set of model parameters characterizing the model may include, but is not limited to, one or more parameters describing the number of layers of the neural network, the number and distribution of neurons in each layer, the connections between neurons, the weights of connections between each neuron, etc. For other types of models, other types of set of model parameters may be used to characterize them. The beam prediction model used in this disclosure can be trained using various appropriate techniques, including training techniques that have been developed and those that may be developed in the future. Training of the beam prediction model can be performed in advance. Specifically, the beam prediction model can be trained iteratively using a labeled training dataset and then tested using a test dataset. Training of the beam prediction model is not the focus of this disclosure, and therefore this disclosure does not limit it. The trained beam prediction model can be deployed at or in association with the UE. The UE can provide the beam prediction model with a set of measured beam information, and the beam prediction model can generate corresponding prediction results based at least in part on the set of measured beam information.

[0066] According to some embodiments of this disclosure, the UE can obtain the measured beam information set through various suitable methods. For example, before performing the comparison in step 410, the UE can perform beam measurements with respect to the measured beam set. The measured beam set can be configured by a network device. Beam measurements may include the network device transmitting a reference signal to the UE on each beam in the measured beam set, and the UE measuring the actual received strength of the reference signal on each beam (referred to as the measured reference signal received strength). The measured beam information set may include the measured reference signal received strength.

[0067] According to some embodiments of this disclosure, the UE can provide a set of measured beam information associated with all beams in the measured beam set to a prediction beam model to generate the prediction beam set.

[0068] According to some embodiments of this disclosure, the UE can select a subset of beams with the best measurement results from the measurement beam set as an input beam set, and provide the measured beam information associated with the input beam set to the beam prediction model to generate the predicted beam set. For example, the UE can select M beams with the highest measured reference signal received strength from the measurement beam set as the input beam set, where M is a specified integer. The selected input beam set and its associated information (e.g., measured reference signal received strength) can be organized into a measured beam information set for provision to the beam prediction model. In some embodiments, the M beams can be sorted. For example, the M beams can be sorted in descending order of measured reference signal received strength.

[0069] According to some embodiments of this disclosure, the UE can obtain the predicted beam information set of the beam prediction model through various suitable methods. For example, the UE can provide the measured beam information set associated with the measured beam set or the input beam set to the beam prediction model. The beam prediction model can generate an output beam set and / or prediction information associated with each beam in the output beam set (e.g., predicted reference signal received strength, prediction probability of becoming the best beam, etc.). In some embodiments, the predicted beam set can be a subset of the output beam set with the best prediction results. For example, the UE can select K beams in the output beam set with the highest predicted reference signal received strength or the highest prediction probability as the predicted beam set, where K is a specified integer. K can be the same as M, or K can be different from M. In some embodiments, the beam prediction model can directly provide the K beams with the highest predicted reference signal received strength or the highest prediction probability as the predicted beam set. The predicted beam information set can include the predicted beam set and / or the prediction information for each beam in the predicted beam set. In some embodiments, the K beams can be sorted. For example, the K beams can be sorted in descending order of the predicted reference signal received strength. Alternatively, the K beams can be sorted in descending order of the predicted probability of becoming the optimal beam. In some embodiments, the predicted beam information set may include the sorted K beams, but not the specific prediction information. That is, the predicted beam information set may be a sorted set of predicted beams.

[0070] According to some embodiments of this disclosure, both specific measured beam information and specific predicted beam information are associated with at least one common beam shared by the measured beam set and the predicted beam set. In this disclosure, a common beam refers to a beam that exists both in the measured beam set and in the predicted beam set generated based on the measured beam set (or the input beam set). In some embodiments, if a first beam in the measured beam set and a second beam in the predicted beam set have the same direction and resources, the first beam and the second beam can be considered to constitute a common beam, regardless of whether the first beam and the second beam have the same width. For example, the first beam can be a wide beam, and the second beam can be a narrow beam. As another example, the first beam can be a narrow beam, and the second beam can be a wide beam.

[0071] In some embodiments, the UE can determine one or more common beams with the same or corresponding identification information by comparing the identification information of each beam in the measurement beam set and the identification information of each beam in the prediction beam set. For example, the identification information may be a resource identifier for each beam, or any other information capable of distinguishing different beams. The UE can determine a common beam set between the measurement beam set and the prediction beam set. If the common beam set includes at least one beam, the UE can use the techniques of this disclosure to perform autonomous monitoring of the beam prediction model based on that at least one beam.

[0072] According to some embodiments of this disclosure, the UE can perform a comparison between specific measured beam information and specific predicted beam information based on one or more criteria. This comparison can determine whether one or more characteristics of the common beam are consistent across the measured beam set and the predicted beam set.

[0073] In some embodiments, the one or more characteristics being compared may include a reference signal received strength. Accordingly, the one or more criteria may be based on the reference signal received strength corresponding to a common beam. In this case, specific measured beam information may include the measured reference signal received strength associated with at least one common beam, and specific predicted beam information may include the predicted reference signal received strength associated with the at least one common beam. Accordingly, the measured reference signal received strength and the predicted reference signal received strength may be compared to see if they are consistent. For example, the difference between the measured reference signal received strength and the predicted reference signal received strength may be determined and compared to a specified threshold. The reference signal received strength may be characterized using reference signal received power (RSRP) or any other suitable metric.

[0074] In some embodiments, the compared one or more characteristics may include the relative order of multiple common beams. Accordingly, the one or more criteria may be based on the distribution of the common beams in the measured beam set and the predicted beam set. In this case, specific measured beam information may include a first distribution of the measured beam set, and specific predicted beam information may include a second distribution of the predicted beam set. It can be determined whether the first distribution and the second distribution match.

[0075] In some embodiments, determining that the first distribution matches the second distribution includes determining that at least one common beam has the same order in both the measured beam set and the predicted beam set. The beam ordering can be based on the received strength of a reference signal or the probability of being the optimal beam. For example, in the measured beam set, beams can be ordered according to the measured reference signal strength. In the predicted beam set, beams can be ordered according to the predicted received reference signal strength or the predicted probability of being the optimal beam. If at least one common beam has the same order in both the measured beam set and the predicted beam set, then the first distribution and the second distribution match.

[0076] Additionally or alternatively, determining that the first distribution matches the second distribution includes determining that the beam ordered first in the first distribution exists in the second distribution.

[0077] In some embodiments, the one or more criteria may be based on both the received strength and distribution of a reference signal. Additionally or alternatively, in other embodiments, the one or more criteria may be based on any other suitable characteristic corresponding to a common beam.

[0078] Method 400 may proceed to step 420. In step 420, the UE may be configured to report an event to the network device based at least on the comparison in step 410. In response to the result of the comparison satisfying a specified condition, the UE may generate a prediction success indication or a prediction failure indication for the beam prediction model. Based on the generated indication, the UE may report the corresponding event to the network device.

[0079] In some embodiments, if it is determined that one or more characteristics of the common beam are consistent across the measured beam set and the predicted beam set, the UE can generate a prediction success indication for the beam prediction model. The prediction success indication indicates that the performance of the current beam prediction model has passed autonomous monitoring and demonstrates that the current beam prediction model possesses a certain level of reliability and accuracy.

[0080] If one or more characteristics of the common beam are determined to be inconsistent in the measurement beam set and the prediction beam set, the UE can generate a prediction failure indication for the beam prediction model. The prediction failure indication indicates that the performance of the current beam prediction model has failed autonomous monitoring and that the current beam prediction model lacks reliability and accuracy.

[0081] For example, a prediction success indication can be generated if the difference between the measured reference signal received strength and the predicted reference signal received strength associated with the common beam is less than a specified threshold. Otherwise, a prediction failure indication can be generated. This specified threshold can be characterized using an absolute or relative value (e.g., a percentage). Alternatively or additionally, a prediction success indication can be generated if the first and second distributions associated with the common beam match. Otherwise, a prediction failure indication can be generated. The UE can report the corresponding event to the network device, which can be a prediction success event or a prediction failure event.

[0082] According to some embodiments of this disclosure, a specified number N of beams can be selected from at least one determined common beam to be used for performing the aforementioned comparison. In some embodiments, N can be 1. Accordingly, a single beam in the set of common beams with the maximum reference signal received strength / maximum predicted probability of becoming the best beam can be selected. The aforementioned comparison can be performed with respect to specific measured beam information and specific predicted beam information associated with this single beam.

[0083] Alternatively, the selected N common beams may include multiple beams. In this case, the UE can compare the measured beam information and predicted beam information associated with each of the multiple common beams separately. The UE can then determine the event to report to the network device based on the comparison of the multiple common beams. For example, if the comparison result gives a prediction failure indication for more than a specified threshold of the multiple common beams, the UE can report an event containing the prediction failure indication to the network device. Otherwise, the UE can report an event containing a prediction success indication to the network device. The specified threshold can be characterized by an absolute number or a relative number (e.g., a percentage).

[0084] According to embodiments of this disclosure, method 400 may optionally include one or more additional operations.

[0085] In some alternative embodiments, the UE can be configured to receive an indication from the network device in response to a reported event. In some embodiments, this indication from the network device can trigger model monitoring. The UE can then put the beam prediction model into monitoring mode based on this indication from the network device.

[0086] According to some embodiments of this disclosure, model monitoring triggered by an instruction from a network device may include the network device performing an additional beam scan against a set of predicted beams provided by a beam prediction model. Specifically, the network device may configure a reference signal for each beam in the set of predicted beams and transmit the configured reference signal to the UE using that beam. The UE may perform beam measurements on the reference signals and compare the results with the set of predicted beam information. This additional beam scan is performed after the beam prediction model provides the set of predicted beams, thus introducing additional reference signal transmission overhead and additional beam scan delay.

[0087] The autonomous monitoring disclosed herein differs from model monitoring triggered by instructions from network devices. As previously stated, the autonomous monitoring of this disclosure is performed autonomously by the UE on the beam prediction model deployed at the UE. More importantly, the autonomous monitoring of this disclosure advantageously utilizes the set of measured beam information as input to the beam prediction model. The autonomous monitoring of this disclosure does not require additional beam scanning after the beam prediction model provides its prediction results; instead, it uses beam measurements prior to the prediction results. Therefore, the autonomous monitoring of this disclosure avoids the additional reference signal transmission overhead and additional beam scanning delay introduced by conventional model monitoring. Furthermore, for fast time-varying fading channels, due to the additional beam scanning delay, the channel characteristics at the time of performing the additional beam scanning may be significantly different from the previous channel characteristics. Therefore, model monitoring based on additional beam scanning may produce significant bias. In other words, the autonomous monitoring technique of this disclosure can verify the reliability and accuracy of the beam prediction model with low overhead, low latency, and high accuracy.

[0088] If the autonomous monitoring of this disclosure determines that the beam prediction model is not reliable and accurate enough, model monitoring can be optionally triggered to further test the model using additional beam scans.

[0089] In some alternative embodiments, the indication from the network device can trigger one or more LCM operations. The UE can further perform a specified LCM operation based on the indication. The one or more LCM operations may include at least one of model deactivation, model activation, model switching, or model selection.

[0090] For example, in some embodiments, if the UE reports an event containing a prediction failure indication to the network device, the network device may send a model deactivation indication to the UE. In response to this indication, the UE may deactivate (e.g., disable) the deployed beam prediction model. In some embodiments, the UE may remove the disabled beam prediction model. In some embodiments, the UE may request a new beam prediction model from the network device.

[0091] For example, in some embodiments, if the UE reports an event containing a prediction failure indication to the network device, the network device can send a model switching indication to the UE. In response to this indication, the UE can switch its deployed beam prediction model to another model.

[0092] For example, in some embodiments, if the UE reports an event to the network device containing a prediction success indication, the network device may send a model activation indication to the UE. In response to this indication, if the beam prediction model has not yet been activated (e.g., previously in a test deployment phase), the UE may activate the deployed beam prediction model. The activated beam prediction model can then be used to predict the beams actually used for communication. If the beam prediction model is already activated, the UE can continue to use the deployed beam prediction model.

[0093] For example, in some embodiments, if the UE reports an event to the network device that includes a prediction failure / success indication for a plurality of optional beam prediction models, the network device may send a model selection indication to the UE. This indication can specify the selected beam prediction model from the plurality of optional beam prediction models. In response to this indication, the UE may deploy, activate, or use the selected beam prediction model.

[0094] It should be understood that the aforementioned LCM operations are merely exemplary. Other LCM operations may be used in other embodiments.

[0095] According to some embodiments of this disclosure, with the autonomous monitoring of the beam prediction model, the UE can report one or more candidate beams to the network device.

[0096] In some embodiments, if the reported event includes a prediction success indication, the UE can be configured to select one or more candidate beams from the predicted beam set to report to the network device. For example, the one or more candidate beams may be a specified number of beams in the predicted beam set that have the highest predicted reference signal received strength and / or the highest prediction probability of becoming the best beam.

[0097] In some embodiments, if the reported event includes a prediction failure indication, the UE can be configured to select one or more candidate beams from the measured beam set (instead of the predicted beam set) to report to the network device.

[0098] For example, the UE can select one or more beams from the set of measurement beams that have the best measurement results (e.g., the maximum measured reference signal received strength) and report them to the network device.

[0099] Alternatively or additionally, the UE may select one or more beams from the measured beam set that meet the beam failure recovery threshold and report them to the network device. In this case, if the number of beams in the measured beam set that meet the beam failure recovery threshold is less than a predetermined threshold, a beam scanning procedure associated with the complete set of available beams may need to be performed to determine the optimal beam. For example, the UE may send an instruction to the network device requesting the network device to revert to a regular beam scanning-based beam management procedure to determine the optimal beam.

[0100] It should be understood that the above description is merely an exemplary embodiment of method 400. Details of various embodiments of method 400, as well as additional or optional embodiments, will be further described below.

[0101] Figure 5 illustrates a flowchart of a method 500 for autonomous monitoring of a beam prediction model according to some embodiments of the present disclosure. Method 500 can be executed on the network side. For example, method 500 can be executed by a network device (e.g., a base station). The device for executing method 500 can be implemented by the aforementioned electronic device 300. Accordingly, method 500 can be executed by the processing circuitry 330 of the electronic device 300.

[0102] Method 500 may begin at step 510. In step 510, the network device may be configured to receive an event from the UE based on a comparison of: (1) a specific measured beam information in a measured beam information set, which is associated with one or more specific beams in the UE's measured beam information set; and (2) a specific predicted beam information in a predicted beam information set, which is associated with the one or more specific beams in the predicted beam information set of a beam prediction model. The predicted beam information set is generated by the beam prediction model at least in part based on the measured beam information set, and the one or more specific beams are at least one common beam shared by both the measured beam information set and the predicted beam information set.

[0103] Method 500 may proceed to step 520. In step 520, in response to receiving an event, the network device may be configured to send an indication to the UE, the indication being associated with model monitoring or one or more LCM operations.

[0104] According to some embodiments of this disclosure, in response to receiving an event, the network device may send an indication associated with a specified LCM operation to the UE. The LCM operation may include at least one of the following: model deactivation, model activation, model switching, or model selection.

[0105] In some embodiments, if the UE reports an event containing a prediction failure indication to the network device, the network device may send a model deactivation indication to the UE to deactivate the deployed beam prediction model.

[0106] In some embodiments, if the UE reports an event containing a prediction failure indication to the network device, the network device may send a model switching indication to the UE to switch the beam prediction model deployed by the UE to another model.

[0107] In some embodiments, if the UE reports an event containing a prediction success indication to the network device, the network device may send a model activation indication to the UE to instruct the UE to activate the deployed beam prediction model or continue using the already activated beam prediction model.

[0108] In some embodiments, if the UE reports an event to the network device that includes a prediction failure / success indication for a plurality of optional beam prediction models, the network device may send a model selection indication to the UE to instruct the UE to specify the selected beam prediction model from the plurality of optional beam prediction models.

[0109] It should be understood that the aforementioned LCM operation is merely exemplary. In other embodiments, the network device may use any suitable LCM operation based on the type of event and the state of the current beam prediction model.

[0110] According to some embodiments of this disclosure, in response to receiving an event, the network device can send an indication associated with model monitoring to the UE. This indication can cause the beam prediction model to enter a monitoring state. In the monitoring state, the network device can perform an additional beam scan against the set of predicted beams provided by the beam prediction model. Specifically, the network device can configure a reference signal for each beam in the set of predicted beams and send the configured reference signal to the UE using that beam. The UE can perform beam measurements on the reference signals and compare the beam measurement results with the set of predicted beam information. This additional beam scan is optional and can be used to further determine the performance of the beam prediction model.

[0111] According to embodiments of this disclosure, method 500 may optionally include one or more additional operations.

[0112] In some alternative embodiments, the network device may be configured to configure a set of measurement beams for beam measurement to the UE. The UE may perform beam measurements against the set of measurement beams and determine, based on the beam measurement results, inputs to be provided to a beam prediction model. These inputs may include a set of measured beam information associated with the set of measurement beams and / or the set of input beams. The set of input beams may be a subset of beams selected from the set of measurement beams. The beam prediction model may determine an output set of beams (or further determine a set of predicted beams) and / or prediction information for each beam therein based on the received set of measured beam information associated with the set of measurement beams and / or the set of input beams.

[0113] In some alternative embodiments, the network device may be configured to further receive one or more candidate beams reported by the UE.

[0114] For example, when the UE receives an event containing a prediction success indication, the reported one or more candidate beams may be a subset of the predicted beam set. This subset may include a specified number of beams in the predicted beam set that satisfy predetermined conditions. For example, this subset may include one or more beams in the predicted beam set that have the highest predicted reference signal received strength or the highest prediction probability of becoming the best beam.

[0115] For example, when the UE receives an event containing a prediction failure indication, the reported one or more candidate beams may be a subset of the measurement beam set. This subset may include a specified number of beams in the measurement beam set that meet predetermined conditions. For instance, the subset may include one or more beams in the measurement beam set that have the maximum measured reference signal received strength. Alternatively, the subset may include one or more beams in the measurement beam set that meet a beam failure recovery threshold.

[0116] In some cases, network devices can select the best beam from one or more candidate beams for subsequent communication with the UE.

[0117] In some cases, the network device may receive an indication from the UE to revert to a regular beam-scan-based beam management procedure. For example, the UE may send this indication if the number of beams in the measured beam set that meet the beam failure recovery threshold is less than a specified threshold. In response to this indication, the network device may perform a regular beam-scan-based beam management procedure with the UE to determine the optimal beam.

[0118] It should be understood that the above description is merely an exemplary embodiment of method 500. Details of various embodiments of method 500, as well as additional or optional embodiments, will be further described below.

[0119] 4. Exemplary Process

[0120] Figure 6 illustrates a schematic diagram of a process 600 for autonomous monitoring of a beam prediction model according to some embodiments of the present disclosure. Process 600 can be performed by a network device (e.g., a base station BS) and a UE.

[0121] In step 601, the network device can be configured to configure a measurement beam set to the UE. The configured measurement beam set can be represented as Set C. Set C can be significantly smaller than the full optional beam set. The full optional beam set can be represented as Set A. For example, assuming Set A includes 64 optional beams, the configured Set C can include only 8 beams. It should be understood that the set size used herein is merely an example and not a limitation. Other sizes of Set A or Set C are also possible.

[0122] In step 602, the UE may perform beam measurements. For example, the UE may be configured to perform beam measurements on each beam in Set C. Specifically, the UE may receive reference signals transmitted on each corresponding beam in Set C from the network device and measure the reference signal received strength. The measured reference signal received strength may be characterized using RSRP. In some embodiments, Layer 1 RSRP (L1-RSRP) may be used. In other embodiments, other RSRPs may be used. Additionally or alternatively, any metric capable of characterizing the quality of reference signal reception may be used instead of, or in combination with, the reference signal received strength. Performing beam measurements on only 8 beams in Set C, compared to performing beam measurements on 64 selectable beams in Set A, can significantly reduce reference signal transmission overhead and beam scanning delay.

[0123] In some alternative embodiments, the UE may determine the input beam set in step 603. This input beam set may be represented as Set B. For example, the UE may select Set B from Set C based on the beam measurement results in step 602. Specifically, the UE may select M beams from Set C that have the best beam measurement results (e.g., maximum measured RSRP) to form Set B. Therefore, Set B may be a subset of Set C. In this example, M may be a specified integer not greater than 8. In one example, assume M = 4. Accordingly, the UE may select 4 beams with the maximum measured RSRP from the 8 beams in Set C as Set B. Assume that the 8 beams in Set C may be identified as B1 to B8, and arranged in descending order of measured RSRP as B1, B3, B5, B6, B2, B4, B7, B8. Accordingly, the selected Set B includes the first 4 beams B1, B3, B5, B6. It should be understood that the value of M and the order of the beams used herein are merely examples and not limitations.

[0124] In some alternative embodiments, the UE may not determine Set B from Set C, but instead use Set C as input to the beam prediction model. Accordingly, step 603 may be omitted.

[0125] In step 604, the UE can use a beam prediction model to generate an output beam set. The beam prediction model used can be a spatial beam prediction model. That is, the beam prediction model can predict one or more available beams for communication based on current beam measurements (without relying on historical beam measurements). Compared to temporal beam prediction, spatial beam prediction can be viewed as a real-time beam prediction. That is, in one round of prediction, the spatial beam prediction model predicts candidate beams for the current round based on measurements of a small number of beams in that round. In contrast, the temporal beam prediction model predicts candidate beams for multiple future times based on collected historical data.

[0126] Specifically, the UE can provide Set C (or optionally, Set B determined in step 603) and its associated beam measurement results to the beam prediction model. The beam prediction model can then generate one or more predicted available beams based on this information, as an output beam set. The output beam set may include one or more beams from the 64 beams of Set A. These one or more beams may include the same beams as Set C, or they may include beams different from those in Set C.

[0127] In step 604, the beam prediction model may optionally generate prediction information for each beam in the output beam set. This prediction information may characterize one or more characteristics of each beam. In some embodiments, the prediction information may include the predicted reference signal received strength for each beam. In other embodiments, the prediction information may include the predicted probability that each beam will become the optimal beam. In still other embodiments, the prediction information may include other characteristics of each beam. In yet another embodiment, the beam prediction model does not output prediction information for each beam, but the output beam set is sorted according to specific prediction information. For example, the beam prediction model may output an output beam set sorted according to the predicted reference signal received strength or the predicted probability of becoming the optimal beam.

[0128] In step 605, the UE may determine the predicted beam set. For example, the UE may determine the predicted beam set from the output beam set generated in step 604. In some embodiments, the UE may select a specified number of beams with the maximum predicted reference signal received strength from the output beam set. Additionally or alternatively, the UE may select a specified number of beams with the maximum prediction probability of becoming the optimal beam from the output beam set. This specified number may be represented as K. K may be equal to M or may not be equal to M. The selected K beams may form the predicted beam set. The predicted beam set may include one or more beams that are the same as the measured beam set, or it may include one or more beams that are different from the measured beam set.

[0129] As an example, assume the size of the prediction beam set is K = 4. Furthermore, assume the four beams in the prediction beam set are B1, B3, B10, and B15. Optionally, assume these four beams are already arranged in descending order of predicted RSRP or predicted probability. It should be understood that the value of K and the chosen prediction beam set used here are merely examples and not limitations.

[0130] In some embodiments, the beam prediction model can be configured to directly output a specified number (K) of beams as a predicted beam set in step 604. Accordingly, step 605 can be omitted.

[0131] In step 606, the UE can determine the common beam set of the measurement beam set (Set C) and the prediction beam set. For example, the UE can determine each common beam existing in both the measurement beam set and the prediction beam set by comparing the identification information of each beam.

[0132] If there is no common beam between the measured beam set and the predicted beam set, process 600 can be terminated. Otherwise, the process can continue to step 607. In step 607, the UE can compare the specific measured beam information and the specific predicted beam information associated with the common beam.

[0133] In some embodiments, the UE can compare the predicted reference signal received strength (RSS) of each common beam with the measured RSS received strength. In response to the predicted RSS received strength associated with a common beam being close to the measured RSS received strength (e.g., the difference is less than a specified threshold), it can be determined that the beam prediction model's prediction for that beam is accurate (or the prediction is successful). Otherwise, it can be determined that the beam prediction model's prediction for that beam is inaccurate (or the prediction fails).

[0134] In some embodiments, the UE can select a specified number (N) of common beams from the common beam set to perform the aforementioned comparison. For example, if N = 1, the UE can select a single beam from the common beam set to perform the aforementioned comparison. If N is greater than 1, the UE can select the first N common beams from the common beam set to perform the aforementioned comparison. Specifically, the UE can compare the measured beam information and predicted beam information associated with each of the N beams.

[0135] For example, in the aforementioned example, the common beam set may include beams B1 and B3. Accordingly, the UE can compare the predicted reference signal received strength (RSS) of each of the common beams B1 and B3 with the measured RSS received strength. When the common beam set includes multiple beams, the number of successfully predicted beams can be determined and compared with a specified threshold. If this number is greater than the specified threshold, the beam prediction model can be determined overall to be accurate (or predicted successfully). Otherwise, the beam prediction model can be determined overall to be inaccurate (or predicted unsuccessfully).

[0136] It is understood that, in alternative embodiments, the number of beams that fail to be predicted may also be compared with another specified threshold to determine whether the beam prediction model is successful or unsuccessful.

[0137] In some embodiments, the UE can compare a first distribution in the measured beam set with a second distribution in the predicted beam set to determine whether the first and second distributions match. If the first and second distributions match, it can be determined that the beam prediction model's prediction is accurate (or the prediction is successful). If the first and second distributions do not match, it can be determined that the beam prediction model's prediction is inaccurate (or the prediction fails). For example, the comparison of the first and second distributions can be performed when the beam prediction model does not output the predicted reference signal received strength.

[0138] Determining a match between the first and second distributions involves identifying at least one common beam that has the same ordering in both the measured beam set and the predicted beam set. The beam ordering can be based on the received strength of a reference signal or the probability of being the optimal beam. For example, in the measured beam set, beams can be ordered according to the measured reference signal strength. In the predicted beam set, beams can be ordered according to the predicted received reference signal strength or the predicted probability of being the optimal beam. If at least one common beam has the same ordering in both the measured and predicted beam sets, then a match between the first and second distributions can be determined.

[0139] For example, in the aforementioned example, the common beams B1 and B3 have the same order in both the ordered set of measurement beams and the ordered set of prediction beams, thus confirming that the predictions of the beam prediction model are accurate.

[0140] Additionally or alternatively, determining that the first distribution matches the second distribution may include determining that the beam ordered first in the first distribution exists in the second distribution.

[0141] For example, in the aforementioned example, if the predicted beam set determined in step 605 includes B3, B6, B10, and B15, then beam B1, which ranks first in the first distribution of the measured beam set, does not exist in the second distribution of the predicted beam set. Therefore, it can be determined that the beam prediction model's prediction is inaccurate. This is because the predicted beam set includes beams B3 and B6 with lower measured RSRP, but does not include beams B1 and B5 with higher measured RSRP. Obviously, beams B1 and B5 with higher measured RSRP are more likely to be the optimal beams than beams B3 and B6 with lower measured RSRP.

[0142] For example, in the aforementioned example, if the predicted beam set determined in step 605 includes B1, B9, B14, and B15, then the common beam determined in step 606 only includes B1. In this case, the beam B1, which ranks first in the first distribution of the measurement beam set, also exists in the second distribution of the predicted beam set, thus confirming the accuracy of the beam prediction model.

[0143] It should be understood that the foregoing embodiments for determining the match between the first and second distributions are merely exemplary and not intended to constitute a limitation. In other embodiments, other aspects of the first and second distributions may be compared to determine whether the first and second distributions match.

[0144] In step 608, the UE may generate an event to be sent to the network device based on the comparison in step 607. For example, if the comparison in step 607 indicates that the beam prediction model has failed, the UE may generate an event containing a prediction failure indication. If the comparison in step 607 indicates that the beam prediction model has succeeded, the UE may generate an event containing a prediction success indication.

[0145] In step 609, the UE may report the generated event to the network device. In some embodiments, the generated event may include indication bits. For example, prediction success indication and prediction failure indication may be indicated by binary bits. For example, a 0 value of the binary bit may be used as a prediction success indication and a 1 value may be used as a prediction failure indication. Alternatively, a 1 value of the binary bit may be used as a prediction success indication and a 0 value may be used as a prediction failure indication. Other indication methods are also possible and are not limited thereto.

[0146] Optionally, the UE can select different candidate beams for different events and report the selected candidate beams to the network device in step 609.

[0147] For example, for an event that includes a prediction success indication, the UE can select candidate beams from the prediction beam set to report. The selected candidate beams can be a specified number of beams with the maximum predicted reference signal received strength. Alternatively, the selected candidate beams can be a specified number of beams with the maximum prediction probability.

[0148] Even for events that include a prediction failure indication, the UE can select candidate beams from the measured beam set (Set C) for reporting. For example, the selected candidate beams could be a specified number of beams with the maximum measured reference signal received strength. Alternatively, the selected candidate beams could be a specified number of beams that meet the beam failure recovery threshold. In this way, candidate beams can still be provided to the network device even when the beam prediction model's performance is poor.

[0149] In some cases, if the measured beam set does not contain a specified number of beams that meet the beam failure recovery threshold, the UE may request the network device to perform a beam scanning procedure for the complete optional beam set Set A. In response to this request, the UE and the network device may perform a standard beam scanning-based beam management procedure to determine the optimal beam.

[0150] In step 610, in response to an event reported by the UE, the network device can be configured to send an indication to the UE relating to model monitoring or one or more LCM operations. The UE can then perform model monitoring and / or one or more LCM operations (not shown) in response to the indication.

[0151] According to some embodiments of this disclosure, in response to receiving an event, the network device may send an indication associated with a specified LCM operation to the UE. The LCM operation may include at least one of the following: model deactivation, model activation, model switching, or model selection.

[0152] In some embodiments, if the UE reports an event containing a prediction failure indication to the network device, the network device may send a model deactivation indication to the UE to deactivate the deployed beam prediction model.

[0153] In some embodiments, if the UE reports an event containing a prediction failure indication to the network device, the network device may send a model switching indication to the UE to switch the beam prediction model deployed by the UE to another model.

[0154] In some embodiments, if the UE reports an event containing a prediction success indication to the network device, the network device may send a model activation indication to the UE to instruct the UE to activate the deployed beam prediction model or continue using the already activated beam prediction model.

[0155] In some embodiments, if the UE reports an event to the network device that includes a prediction failure / success indication for a plurality of optional beam prediction models, the network device may send a model selection indication to the UE to instruct the UE to specify the selected beam prediction model from the plurality of optional beam prediction models.

[0156] According to some embodiments of this disclosure, in response to receiving an event, the network device can send an indication associated with model monitoring to the UE. This indication can cause the beam prediction model to enter a monitoring state. In the monitoring state, the network device can perform an additional beam scan against the set of predicted beams provided by the beam prediction model. Specifically, the network device can configure a reference signal for each beam in the set of predicted beams and send the configured reference signal to the UE using that beam. The UE can perform beam measurements on the reference signals and compare the beam measurement results with the set of predicted beam information. This additional beam scan is optional and can be used to further determine the performance of the beam prediction model.

[0157] The technology disclosed herein enables autonomous monitoring of beam prediction models. This autonomous monitoring compares the predicted beam information set of the beam prediction model with a previously measured beam information set, and generates events indicative of the performance of the beam prediction model based on this comparison. Network devices can then determine, based on these events, whether further model monitoring and / or one or more LCM operations are required. This autonomous monitoring can reduce additional reference signal resource overhead or beam scanning latency. The autonomous monitoring of this disclosure offers advantages such as high accuracy, low latency, and low overhead.

[0158] 5. Application Product Examples

[0159] The technology disclosed herein can be applied to a variety of products.

[0160] For example, the control device / base station mentioned in this disclosure can be implemented as any type of base station, such as an eNB, including macro eNBs and small eNBs. A small eNB can be an eNB covering a cell smaller than a macro cell, such as a pico eNB, a micro eNB, and a femtopic eNB. It can also be implemented as a gNB, such as a macro gNB and a small gNB. A small gNB can be a gNB covering a cell smaller than a macro cell, such as a pico gNB, a micro gNB, and a femtopic gNB. Alternatively, the base station can be implemented as any other type of base station, such as a NodeB and a Base Transceiver Station (BTS). A base station may include: a subject configured to control wireless communication (also called a base station device); and one or more remote radio heads (RRHs) located in a different location from the subject. Furthermore, the various types of terminals described below can operate as base stations by temporarily or semi-persistently performing base station functions. For example, the terminal devices mentioned in this disclosure can be implemented as mobile terminals (such as smartphones, tablet PCs, laptop PCs, portable gaming terminals, portable / dongle-type mobile routers, and digital camera devices) or in-vehicle terminals (such as car navigation devices) in some embodiments. The terminal devices can also be implemented as terminals performing machine-to-machine (M2M) communication (also known as machine-type communication (MTC) terminals). Furthermore, the terminal devices can be wireless communication modules (such as integrated circuit modules comprising a single chip) installed on each of the aforementioned terminals.

[0161] The following will describe application examples according to this disclosure with reference to the accompanying drawings.

[0162] [Example of a base station]

[0163] It should be understood that the term "base station" as used in this disclosure has the full breadth of its usual meaning and includes at least a wireless communication station used as part of a wireless communication system or radio system to facilitate communication. Examples of base stations may include, but are not limited to, the following: a base station may be one or both of a Base Transceiver Station (BTS) and a Base Station Controller (BSC) in a GSM system; one or both of a Radio Network Controller (RNC) and a Node B in a WCDMA system; an eNB in ​​LTE and LTE-Advanced systems; or a corresponding network node in a future communication system (e.g., a gNB, eLTE eNB, etc., that may appear in a 5G communication system). Some functions of the base station in this disclosure may also be implemented as an entity that controls communication in D2D, M2M, and V2V communication scenarios, or as an entity that plays a role in spectrum coordination in cognitive radio communication scenarios.

[0164] First Example

[0165] Figure 7 is a block diagram illustrating a first example of an exemplary configuration of a gNB to which the technologies of this disclosure can be applied. The gNB 2100 includes a plurality of antennas 2110 and a base station device 2120. The base station device 2120 and each antenna 2110 can be connected to each other via RF cables. In one implementation, the gNB 2100 (or base station device 2120) herein may correspond to the aforementioned control-side electronics.

[0166] Each of the antennas 2110 includes one or more antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used by the base station equipment 2120 to transmit and receive wireless signals. As shown in Figure 7, the gNB 2100 may include multiple antennas 2110. For example, the multiple antennas 2110 may be compatible with multiple frequency bands used by the gNB 2100.

[0167] The base station equipment 2120 includes a controller 2121, a memory 2122, a network interface 2123, and a wireless communication interface 2125.

[0168] The controller 2121 can be, for example, a CPU or a DSP, and operates various higher-level functions of the base station equipment 2120. For example, the controller 2121 determines the location information of a target terminal device among at least one terminal devices based on the location information of at least one terminal device on the terminal side of the wireless communication system and the specific location configuration information of at least one terminal device obtained from the wireless communication interface 2125. The controller 2121 may have logical functions that perform controls such as radio resource control, radio bearer control, mobility management, access control, and scheduling. This control can be performed in conjunction with nearby gNBs or core network nodes. The memory 2122 includes RAM and ROM, and stores programs executed by the controller 2121 and various types of control data (such as terminal lists, transmission power data, and scheduling data).

[0169] Network interface 2123 is a communication interface for connecting base station equipment 2120 to core network 2124. Controller 2121 can communicate with core network nodes or other gNBs via network interface 2123. In this case, gNB 2100 and core network nodes or other gNBs can be connected to each other via logical interfaces (such as S1 and X2 interfaces). Network interface 2123 can also be a wired communication interface or a wireless communication interface for wireless backhaul. If network interface 2123 is a wireless communication interface, it can use a higher frequency band for wireless communication compared to the frequency band used by wireless communication interface 2125.

[0170] Wireless communication interface 2125 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless connectivity to terminals located in the cell of gNB 2100 via antenna 2110. Wireless communication interface 2125 typically includes, for example, a baseband (BB) processor 2126 and RF circuitry 2127. BB processor 2126 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing at layers (e.g., L1, Media Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP)). Instead of controller 2121, BB processor 2126 may have some or all of the above-described logical functions. BB processor 2126 may be a memory storing communication control programs, or a module including a processor and associated circuitry configured to execute programs. Update programs can change the functionality of BB processor 2126. The module may be a card or blade inserted into a slot in base station equipment 2120. Alternatively, the module may be a chip mounted on a card or blade. Meanwhile, the RF circuit 2127 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 2110. Although Figure 7 shows an example of an RF circuit 2127 connected to one antenna 2110, this disclosure is not limited to the illustration, but an RF circuit 2127 may be connected to multiple antennas 2110 simultaneously.

[0171] As shown in Figure 7, the wireless communication interface 2125 may include multiple BB processors 2126. For example, the multiple BB processors 2126 may be compatible with multiple frequency bands used by the gNB 2100. As shown in Figure 7, the wireless communication interface 2125 may include multiple RF circuits 2127. For example, the multiple RF circuits 2127 may be compatible with multiple antenna elements. Although Figure 7 shows an example in which the wireless communication interface 2125 includes multiple BB processors 2126 and multiple RF circuits 2127, the wireless communication interface 2125 may also include a single BB processor 2126 or a single RF circuit 2127.

[0172] Second example

[0173] Figure 8 is a block diagram illustrating a second example of an exemplary configuration of a gNB to which the technologies of this disclosure can be applied.

[0174] The gNB 2200 includes multiple antennas 2210, RRH 2220, and base station equipment 2230. RRH 2220 and each antenna...

[0175] 2210 can be connected to each other via RF cables. Base station equipment 2230 and RRH 2220 can be connected to each other via high-speed lines such as fiber optic cables. In one implementation, gNB 2200 (or base station equipment 2230) here can correspond to the aforementioned control-side electronic equipment.

[0176] Each of the antennas 2210 includes one or more antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used by the RRH 2220 to transmit and receive wireless signals. As shown in Figure 8, the gNB 2200 may include multiple antennas 2210. For example, multiple antennas 2210 may be compatible with multiple frequency bands used by the gNB 2200.

[0177] The base station device 2230 includes a controller 2231, a memory 2232, a network interface 2233, a wireless communication interface 2234, and a connection interface 2236. The controller 2231, memory 2232, and network interface 2233 are the same as the controller 2121, memory 2122, and network interface 2123 described with reference to FIG7.

[0178] Wireless communication interface 2234 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to RRH 2220 via RRH 2220 and antenna 2210. Wireless communication interface 2234 typically includes, for example, a BB processor 2235. The BB processor 2235 is identical to the BB processor 2126 described with reference to FIG7, except that it is connected to the RF circuitry 2222 of RRH 2220 via connection interface 2236. As shown in FIG8, wireless communication interface 2234 may include multiple BB processors 2235. For example, multiple BB processors 2235 may be compatible with multiple frequency bands used by gNB 2200. Although FIG8 shows an example in which wireless communication interface 2234 includes multiple BB processors 2235, wireless communication interface 2234 may also include a single BB processor 2235.

[0179] Connection interface 2236 is an interface for connecting base station device 2230 (wireless communication interface 2234) to RRH 2220. Connection interface 2236 may also be a communication module for connecting base station device 2230 (wireless communication interface 2234) to the aforementioned high-speed line of RRH 2220 for communication.

[0180] RRH 2220 includes a connectivity interface 2223 and a wireless communication interface 2221.

[0181] Connection interface 2223 is an interface for connecting RRH 2220 (wireless communication interface 2221) to base station equipment 2230. Connection interface 2223 can also be a communication module for communication in the aforementioned high-speed line.

[0182] Wireless communication interface 2221 transmits and receives wireless signals via antenna 2210. Wireless communication interface 2221 typically includes, for example, RF circuitry 2222. RF circuitry 2222 may include, for example, a mixer, filter, and amplifier, and transmits and receives wireless signals via antenna 2210. Although Figure 8 shows an example of an RF circuitry 2222 connected to one antenna 2210, this disclosure is not limited to this illustration, and an RF circuitry 2222 may be connected to multiple antennas 2210 simultaneously.

[0183] As shown in Figure 8, the wireless communication interface 2221 may include multiple RF circuits 2222. For example, multiple RF circuits 2222 may support multiple antenna elements. Although Figure 8 shows an example in which the wireless communication interface 2221 includes multiple RF circuits 2222, the wireless communication interface 2221 may also include a single RF circuit 2222.

[0184] [Examples regarding user equipment / terminal equipment]

[0185] First Example

[0186] Figure 9 is a block diagram illustrating an example configuration of a communication device 2300 (e.g., a smartphone, communicator, etc.) to which the technologies of this disclosure can be applied. The communication device 2300 includes a processor 2301, a memory 2302, a storage device 2303, an external connection interface 2304, a camera device 2306, a sensor 2307, a microphone 2308, an input device 2309, a display device 2310, a speaker 2311, a wireless communication interface 2312, one or more antenna switches 2315, one or more antennas 2316, a bus 2317, a battery 2318, and an auxiliary controller 2319. In one implementation, the communication device 2300 (or processor 2301) described herein may correspond to the aforementioned transmitting device or terminal-side electronic device.

[0187] Processor 2301 may be, for example, a CPU or a System-on-a-Chip (SoC), and controls the application layer and other layer functions of communication device 2300. Memory 2302 includes RAM and ROM, and stores data and programs executed by processor 2301. Storage device 2303 may include storage media such as semiconductor memory and hard disk. External connection interface 2304 is an interface for connecting external devices (such as memory cards and Universal Serial Bus (USB) devices) to communication device 2300.

[0188] Camera device 2306 includes an image sensor (such as a charge-coupled device (CCD) and complementary metal-oxide-semiconductor (CMOS)) and generates captured images. Sensor 2307 may include a set of sensors, such as a measurement sensor, a gyroscope sensor, a geomagnetic sensor, and an accelerometer. Microphone 2308 converts sound input to communication device 2300 into an audio signal. Input device 2309 includes, for example, a touch sensor, keypad, keyboard, buttons, or switches configured to detect touches on the screen of display device 2310 and receives operations or information input from the user. Display device 2310 includes a screen (such as a liquid crystal display (LCD) and an organic light-emitting diode (OLED) display) and displays the output image of communication device 2300. Speaker 2311 converts the audio signal output from communication device 2300 into sound.

[0189] The wireless communication interface 2312 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 2312 typically includes, for example, a BB processor 2313 and RF circuitry 2314. The BB processor 2313 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for wireless communication. Meanwhile, the RF circuitry 2314 can include, for example, mixers, filters, and amplifiers, and transmits and receives wireless signals via antenna 2316. The wireless communication interface 2312 can be a single chip module on which the BB processor 2313 and RF circuitry 2314 are integrated. As shown in Figure 9, the wireless communication interface 2312 can include multiple BB processors 2313 and multiple RF circuits 2314. Although Figure 9 shows an example where the wireless communication interface 2312 includes multiple BB processors 2313 and multiple RF circuits 2314, the wireless communication interface 2312 can also include a single BB processor 2313 or a single RF circuitry 2314.

[0190] In addition to cellular communication schemes, the wireless communication interface 2312 can support other types of wireless communication schemes, such as short-range wireless communication schemes, near-field communication schemes, and wireless local area network (LAN) schemes. In this case, the wireless communication interface 2312 may include a BB processor 2313 and RF circuitry 2314 for each wireless communication scheme.

[0191] Each of the antenna switches 2315 switches the connection destination of the antenna 2316 among multiple circuits (e.g., circuits for different wireless communication schemes) included in the wireless communication interface 2312.

[0192] Each of the antennas 2316 includes one or more antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals through the wireless communication interface 2312. As shown in FIG9, the communication device 2300 may include multiple antennas 2316. Although FIG9 shows an example in which the communication device 2300 includes multiple antennas 2316, the communication device 2300 may also include a single antenna 2316.

[0193] Furthermore, the communication device 2300 may include an antenna 2316 for each wireless communication scheme. In this case, the antenna switch 2315 may be omitted from the configuration of the communication device 2300.

[0194] Bus 2317 connects processor 2301, memory 2302, storage device 2303, external connection interface 2304, camera device 2306, sensor 2307, microphone 2308, input device 2309, display device 2310, speaker 2311, wireless communication interface 2312, and auxiliary controller 2319 to each other. Battery 2318 supplies power to the various blocks of communication device 2300 shown in FIG. 9 via feeders, which are partially shown as dashed lines in the figure. Auxiliary controller 2319 operates the minimum necessary functions of communication device 2300, for example, in sleep mode.

[0195] Second example

[0196] Figure 10 is a block diagram illustrating an example configuration of an automotive navigation device 2400 to which the technologies of this disclosure can be applied. The automotive navigation device 2400 includes a processor 2401, a memory 2402, a Global Positioning System (GPS) module 2404, a sensor 2405, a data interface 2406, a content player 2407, a storage medium interface 2408, an input device 2409, a display device 2510, a speaker 2411, a wireless communication interface 2413, one or more antenna switches 2416, one or more antennas 2417, and a battery 2418. In one implementation, the automotive navigation device 2400 (or processor 2401) herein may correspond to a transmitting device or a terminal-side electronic device.

[0197] The processor 2401 can be, for example, a CPU or a SoC, and controls the navigation function and other functions of the car navigation device 2400. The memory 2402 includes RAM and ROM, and stores data and programs executed by the processor 2401.

[0198] GPS module 2404 uses GPS signals received from GPS satellites to measure the location (such as latitude, longitude, and altitude) of car navigation device 2400. Sensor 2405 may include a set of sensors, such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. Data interface 2406 is connected to, for example, an in-vehicle network 2421 via a terminal not shown, and acquires data generated by the vehicle (such as vehicle speed data).

[0199] Content player 2407 reproduces content stored on storage media (such as CDs and DVDs), which is inserted into storage media interface 2408. Input device 2409 includes, for example, a touch sensor, button, or switch configured to detect touch on the screen of display device 2510, and receives operations or information input from the user. Display device 2510 includes a screen such as an LCD or OLED display and displays images or reproduced content for navigation functions. Speaker 2411 outputs sound for navigation functions or reproduced content.

[0200] The wireless communication interface 2413 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 2413 typically includes, for example, a BB processor 2414 and RF circuitry 2415. The BB processor 2414 can perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for wireless communication. Meanwhile, the RF circuitry 2415 can include, for example, mixers, filters, and amplifiers, and transmits and receives wireless signals via antenna 2417. The wireless communication interface 2413 can also be a chip module on which the BB processor 2414 and RF circuitry 2415 are integrated. As shown in Figure 10, the wireless communication interface 2413 can include multiple BB processors 2414 and multiple RF circuits 2415. Although Figure 10 shows an example where the wireless communication interface 2413 includes multiple BB processors 2414 and multiple RF circuits 2415, the wireless communication interface 2413 can also include a single BB processor 2414 or a single RF circuitry 2415.

[0201] In addition to cellular communication schemes, wireless communication interface 2413 can support other types of wireless communication schemes, such as short-range wireless communication schemes, near-field communication schemes, and wireless LAN schemes. In this case, for each wireless communication scheme, wireless communication interface 2413 may include BB processor 2414 and RF circuitry 2415.

[0202] Each of the antenna switches 2416 switches the connection destination of the antenna 2417 among multiple circuits (such as circuits for different wireless communication schemes) included in the wireless communication interface 2413.

[0203] Each of the antennas 2417 includes one or more antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals through the wireless communication interface 2413. As shown in Figure 10, the car navigation device 2400 may include multiple antennas 2417. Although Figure 10 shows an example in which the car navigation device 2400 includes multiple antennas 2417, the car navigation device 2400 may also include a single antenna 2417.

[0204] Furthermore, the car navigation device 2400 may include an antenna 2417 for each wireless communication scheme. In this case, the antenna switch 2416 can be omitted from the configuration of the car navigation device 2400.

[0205] Battery 2418 supplies power to the various blocks of the car navigation device 2400 shown in Figure 10 via feeders, which are partially shown as dashed lines in the figure. Battery 2418 accumulates the power supplied from the vehicle.

[0206] The technology disclosed herein can also be implemented as an in-vehicle system (or vehicle) 2420 including one or more blocks of a car navigation device 2400, an in-vehicle network 2421, and a vehicle module 2422. The vehicle module 2422 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 2421.

[0207] Exemplary embodiments of the present disclosure have been described above with reference to the accompanying drawings; however, the present disclosure is by no means limited to the examples described above. Various changes and modifications can be made by those skilled in the art within the scope of the appended claims, and it should be understood that such changes and modifications naturally fall within the technical scope of the present disclosure.

[0208] It should be understood that the machine-executable instructions in a machine-readable storage medium or program product according to embodiments of this disclosure can be configured to perform operations corresponding to the above-described device and method embodiments. Embodiments of the machine-readable storage medium or program product will be clear to those skilled in the art when referring to the above-described device and method embodiments, and therefore will not be described again. Machine-readable storage media and program products used to carry or include the above-described machine-executable instructions also fall within the scope of this disclosure. Such storage media may include, but are not limited to, floppy disks, optical disks, magneto-optical disks, memory cards, memory sticks, etc.

[0209] Furthermore, it should be understood that the aforementioned series of processes and devices can also be implemented via software and / or firmware. In the case of software and / or firmware implementation, the corresponding program constituting the software is stored in the storage medium of the relevant device, and when the program is executed, it can perform various functions.

[0210] For example, the multiple functions included in one unit in the above embodiments can be implemented by separate devices. Alternatively, the multiple functions implemented by multiple units in the above embodiments can be implemented by separate devices respectively. In addition, one of the above functions can be implemented by multiple units. Needless to say, such a configuration is included within the scope of the present disclosure.

[0211] In this specification, the steps described in the flowcharts include not only processes executed sequentially in time, but also processes executed in parallel or individually, rather than necessarily in time. Furthermore, even within steps processed in time, it goes without saying that the order can be appropriately changed.

[0212] 6. Example embodiments of this disclosure

[0213] This disclosure includes, but is not limited to, the following embodiments and combinations thereof:

[0214] 1. An electronic device comprising: at least one processing unit; and at least one storage unit, the at least one storage unit comprising computer program code, which, when executed by the at least one processing unit, causes the electronic device to perform the following operations: comparing: (1) obtaining specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beam information; (2) predicting specific predicted beam information in a set of beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams are at least one common beam shared by both the set of measured beams and the set of predicted beams; and reporting an event to a network device, at least based on the comparison.

[0215] 2. The electronic device as described in Example 1, wherein the operation further includes: prior to the comparison: performing beam measurement with respect to the measured beam set; selecting a subset of beams with the best measurement results from the measured beam set as an input beam set; and providing the measured beam information associated with the input beam set to the beam prediction model to generate the predicted beam set.

[0216] 3. The electronic device as described in Embodiment 1, wherein the specific measured beam information includes a measured reference signal received strength associated with the at least one common beam, and the specific predicted beam information includes a predicted reference signal received strength associated with the at least one common beam, and wherein the comparison includes: comparing the difference between the measured reference signal received strength and the predicted reference signal received strength with a specified threshold.

[0217] 4. The electronic device as described in Embodiment 1, wherein the specific measured beam information includes a first distribution of the at least one common beam in the measured beam set, and the specific predicted beam information includes a second distribution of the at least one common beam in the predicted beam set, and wherein the comparison includes: determining that the first distribution matches the second distribution.

[0218] 5. The electronic device as described in Example 4, wherein determining that the first distribution matches the second distribution includes: determining that the at least one common beam has the same order in the measured beam set and the predicted beam set.

[0219] 6. The electronic device as described in Example 5, wherein the sorting is based on the reference signal received strength or the probability of becoming the optimal beam.

[0220] 7. The electronic device as described in Example 1, wherein the operation further includes: receiving an indication from the network device in response to the event; and triggering model monitoring or one or more lifecycle management operations based on the indication.

[0221] 8. The electronic device as described in Example 7, wherein the one or more lifecycle management operations include at least one of the following: model deactivation, model activation, model switching, or model selection.

[0222] 9. The electronic device as described in Example 1, wherein the event includes a prediction failure indication based on the comparison, and the operation further includes deactivating the beam prediction model.

[0223] 10. The electronic device of Embodiment 2, wherein the event includes a predicted failure indication based on the comparison, and the operation further includes: selecting one or more candidate beams from the set of measurement beams and reporting them to the network device, wherein the one or more candidate beams include: one or more beams in the set of measurement beams that have the best measurement results; or one or more beams in the set of measurement beams that meet the beam failure recovery threshold.

[0224] 11. The electronic device as described in Example 10, wherein the operation further includes:

[0225] In response to the number of one or more beams in the measured beam set that meet the beam failure recovery threshold being less than a predetermined number, a beam scanning process associated with the complete selectable beam set is performed.

[0226] 12. The electronic device as described in Embodiment 1, wherein the event includes a prediction success indication based on the comparison, and the operation further includes: selecting one or more candidate beams from the predicted beam set and reporting them to the network device.

[0227] 13. The electronic device as described in Example 1, wherein the beam prediction model is a spatial beam prediction model.

[0228] 14. The electronic device of Embodiment 1, wherein the at least one common beam comprises a plurality of beams, and wherein the comparison comprises: comparing measured beam information and predicted beam information associated with each of the plurality of beams, respectively; and determining an event to be reported to a network device based on the comparison of the plurality of beams.

[0229] 15. An electronic device comprising: at least one processing unit; and at least one storage unit, the at least one storage unit including computer program code, which, when executed by the at least one processing unit, causes the electronic device to perform the following operations: receiving an event from a user equipment (UE), the event being based on a comparison of: (1) specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beams of the UE; (2) predicting specific predicted beam information in a set of predicted beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams being at least one common beam shared by both the set of measured beams and the set of predicted beams; and, in response to receiving the event, sending an indication to the UE, the indication being associated with model monitoring or one or more lifecycle management operations.

[0230] 16. The electronic device as described in Example 15, wherein the one or more lifecycle management operations include at least one of the following: model deactivation, model activation, model switching, or model selection.

[0231] 17. The electronic device as described in Example 15, wherein the operation further includes: configuring the measurement beam set to the UE for performing beam measurement.

[0232] 18. The electronic device of embodiment 17, wherein the event includes a prediction failure indication, and the operation further includes: receiving one or more candidate beams reported by the UE, the one or more candidate beams being a subset of the measurement beam set.

[0233] 19. The electronic device of embodiment 17, wherein the event includes a prediction success indication, and the operation further includes: receiving one or more candidate beams reported by the UE, the one or more candidate beams being a subset of the predicted beam set.

[0234] 20. A method comprising: comparing: (1) specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beams of a beam prediction model; (2) predicting specific predicted beam information in a set of measured beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of the beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams are at least one common beam shared by both the set of measured beams and the set of predicted beams; and reporting an event to a network device, at least based on the comparison.

[0235] 21. A method comprising: receiving an event from a UE, the event being based on a comparison of: (1) specific measured beam information in a set of measured beam information, the specific measured beam information being associated with one or more specific beams in a set of measured beams of the UE; (2) predicting specific predicted beam information in a set of beam information, the specific predicted beam information being associated with the one or more specific beams in a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model at least in part based on the set of measured beam information, and the one or more specific beams being at least one common beam shared by both the set of measured beams and the set of predicted beams; and in response to receiving the event, sending an indication to the UE, the indication being associated with model monitoring or one or more lifecycle management operations.

[0236] 22. A computer-readable storage medium storing one or more instructions, which, when executed by one or more processing circuits of an electronic device, cause the electronic device to perform the method as described in any one of Examples 20-21.

[0237] 23. A computer program product comprising a computer program that, when executed by a processor, is a method as described in any one of Examples 20-21.

Claims

1. An electronic device, comprising: at least one processing unit; and at least one memory unit including computer program code that, when executed by the at least one processing unit, causes the electronic device to perform: comparing: (1) particular measured beam information of a set of measured beam information, the particular measured beam information being associated with one or more particular beams of a set of measured beams; and (2) particular predicted beam information of a set of predicted beam information, the particular predicted beam information being associated with the one or more particular beams of a set of predicted beams of the beam prediction model, wherein the set of predicted beams is generated by the beam prediction model based at least in part on the set of measured beam information, the one or more particular beams being at least one common beam that is common to both the set of measured beams and the set of predicted beams; and reporting, to a network device, an event based at least on the comparing. The operations further include, prior to the comparing:

2. The electronic device of claim 1, wherein, performing beam measurements with respect to the set of measured beams; selecting, from the set of measured beams, a subset of beams having best measurement results as an input set of beams; providing measured beam information associated with the input set of beams to the beam prediction model to generate the set of predicted beams.

3. The electronic device of claim 1, wherein: the particular measured beam information includes a measured reference signal received strength associated with the at least one common beam, and the particular predicted beam information includes a predicted reference signal received strength associated with the at least one common beam, and wherein the comparing includes comparing a difference between the measured reference signal received strength and the predicted reference signal received strength to a specified threshold.

4. The electronic device of claim 1, wherein: the particular measured beam information includes a first distribution of the set of measured beams, and the particular predicted beam information includes a second distribution of the set of predicted beams, and wherein the comparing includes determining that the first distribution matches the second distribution. Determining that the first distribution matches the second distribution includes:

5. The electronic device of claim 4, wherein, determining that the at least one common beam has a same ranking in the set of measured beams and the set of predicted beams; or determining that a beam ranked first in the first distribution exists in the second distribution. The ranking is based on a reference signal received strength or a probability of being a best beam.

6. The electronic device of claim 5, wherein, The operations further include:

7. The electronic device of claim 1, wherein, receiving, from the network device, an indication in response to the event; and based on the indication, triggering a model monitoring or one or more lifecycle management operations. The one or more lifecycle management operations include at least one of: a model deactivation, a model activation, a model switch, or a model selection.

8. The electronic device of claim 7, wherein, The event includes a prediction failure indication based on the comparing, and the operations further include deactivating the beam prediction model.

9. The electronic device of claim 1, wherein, The event includes a prediction failure indication based on the comparing, and the operations further include:

10. The electronic device of claim 2, wherein, ​ from the set of measured beams, selecting one or more candidate beams to report to the network device, wherein the one or more candidate beams include: one or more beams of the set of measured beams having best measurement results; or one or more beams of the set of measured beams satisfying a beam failure recovery threshold.

11. The electronic device of claim 10, wherein, The operations further include: in response to a number of the one or more beams of the set of measured beams satisfying the beam failure recovery threshold being below a predetermined number, performing a beam sweeping procedure associated with a full set of optional beams.

12. The electronic device of claim 1, wherein, The event includes a predicted success indication based on the comparison, and the operations further include: from the set of predicted beams, selecting one or more candidate beams to report to the network device.

13. The electronic device of claim 1, wherein, The beam prediction model is a spatial domain beam prediction model.

14. The electronic device of claim 1, wherein, The at least one common beam includes a plurality of beams, and wherein the comparison includes: comparing the measured beam information and the predicted beam information associated with each of the plurality of beams, respectively; and determining an event to report to a network device based on the comparison of the plurality of beams.

15. An electronic device, comprising: at least one processing unit; and at least one storage unit including computer program code which, when executed by the at least one processing unit, causes the electronic device to perform the following operations: receiving, from a user equipment (UE), an event based on a comparison of (1) particular measured beam information of a set of measured beam information, the particular measured beam information being associated with one or more particular beams of a set of measured beams of the UE, and (2) particular predicted beam information of a set of predicted beam information, the particular predicted beam information being associated with the one or more particular beams of a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model based at least in part on the set of measured beam information, and the one or more particular beams are at least one common beam common to both the set of measured beams and the set of predicted beams; and in response to receiving the event, transmitting, to the UE, an indication associated with model monitoring or one or more lifecycle management operations.

16. The electronic device of claim 15, wherein, The one or more lifecycle management operations include at least one of: model deactivation, model activation, model switching, or model selection.

17. The electronic device of claim 15, wherein, The operations further include: configuring, to the UE, the set of measured beams for performing beam measurements.

18. The electronic device of claim 17, wherein, The event includes a predicted failure indication, and the operations further include: receiving, from the UE, one or more candidate beams reported by the UE, the one or more candidate beams being a subset of beams of the set of measured beams.

19. The electronic device of claim 17, wherein, The event includes a predicted success indication, and the operations further include: receiving, from the UE, one or more candidate beams reported by the UE, the one or more candidate beams being a subset of the set of predicted beams.

20. A method, comprising: comparing: (1) particular measured beam information of a set of measured beam information, the particular measured beam information being associated with one or more particular beams of a set of measured beams of a beam prediction model; (2) particular predicted beam information of a set of predicted beam information, the particular predicted beam information being associated with the one or more particular beams of a set of predicted beams of the beam prediction model, wherein the set of predicted beams is generated by the beam prediction model based at least in part on the set of measured beam information, the one or more particular beams being at least one common beam that is common to both the set of measured beams and the set of predicted beams; and reporting, to a network device, an event based at least on the comparison.

21. A method comprising: receiving, from a UE, an event, the event being based on a comparison of: (1) particular measured beam information of a set of measured beam information, the particular measured beam information being associated with one or more particular beams of a set of measured beams of the UE; (2) particular predicted beam information of a set of predicted beam information, the particular predicted beam information being associated with the one or more particular beams of a set of predicted beams of a beam prediction model, wherein the set of predicted beams is generated by the beam prediction model based at least in part on the set of measured beam information, the one or more particular beams being at least one common beam that is common to both the set of measured beams and the set of predicted beams; and in response to receiving the event, sending, to the UE, an indication, the indication being associated with model monitoring or one or more lifecycle management operations.

22. A computer-readable storage medium storing one or more instructions that, when executed by one or more processing circuits of an electronic device, cause the electronic device to perform the method of any of claims 20-21.

23. A computer program product comprising a computer program which, when executed by a processor, performs the method of any of claims 20-21.

Images