Beam prediction method and apparatus

Abstract

Provided in embodiments of the present application are a beam prediction method and apparatus. The method comprises: a terminal device receives, from a network device, configuration information used for beam management, wherein the configuration information at least comprises one or more resource sets used for temporal beam prediction and / or spatial beam prediction; and the terminal device performs spatial beam prediction or temporal beam prediction on the basis of the configuration information by using an AI / ML model / functionality.

Description

Beam prediction method and device Technical Field

[0001] The embodiments of this application relate to the field of communication technology. Background Technology

[0002] In NR Rel-18, artificial intelligence / machine learning (AI / ML) for the air interface was studied. AI / ML can be used for the following use cases: Channel State Information (CSI) feedback enhancement, beam management, and positioning enhancement. CSI feedback enhancement can include CSI prediction and CSI compression; beam management can include spatial beam prediction (BM case-1) and temporal beam prediction (BM case-2); positioning enhancement can include direct positioning and AI / ML-assisted positioning.

[0003] In some sub-use cases, a two-sided model can be used, meaning the AI / ML model is on both the terminal device side and the network device side. In other sub-use cases, a one-sided model can be used, meaning the AI / ML model is on either the terminal device side or the network device side. For beam management, the AI / ML model can be on both the terminal device side and / or the network device side.

[0004] It should be noted that the above introduction to the technical background is only for the purpose of providing a clear and complete explanation of the technical solutions of this application and facilitating understanding by those skilled in the art. It should not be assumed that these technical solutions are known to those skilled in the art simply because they have been described in the background section of this application.

[0005] Summary of the Invention

[0006] The inventors discovered that terminal devices and / or network devices can perform beam management using AI / ML functions / models. However, current AI / ML-based beam management is not accurate enough and requires enhancements such as the configuration and / or measurement of reference signals. Further research is needed on how to perform beam management in detail.

[0007] To address at least one of the above-mentioned problems, embodiments of this application provide a beam prediction method and apparatus.

[0008] According to one aspect of the embodiments of this application, a beam prediction method is provided, comprising:

[0009] The terminal device receives configuration information for beam management from the network device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0010] The terminal device performs temporal beam prediction or spatial beam prediction based on the configuration information, using AI / ML models / functions.

[0011] According to another aspect of the embodiments of this application, a beam prediction device is provided, comprising:

[0012] A receiver that receives configuration information for beam management from a network device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0013] The processor, based on an AI / ML model / function, performs temporal beam prediction or spatial beam prediction according to the configuration information.

[0014] According to another aspect of the embodiments of this application, a beam prediction method is provided, comprising:

[0015] The network device sends configuration information for beam management to the terminal device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0016] The configuration information is used by the terminal device to perform spatial beam prediction or temporal beam prediction based on AI / ML models / functions.

[0017] According to another aspect of the embodiments of this application, a beam prediction device is provided, comprising:

[0018] A transmitter that sends configuration information for beam management to a terminal device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction.

[0019] The configuration information is used by the terminal device to perform spatial beam prediction or temporal beam prediction based on AI / ML models / functions.

[0020] According to another aspect of the embodiments of this application, a communication system is provided, comprising:

[0021] A network device that transmits configuration information for beam management; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0022] The terminal device receives configuration information for beam management from the network device; based on the AI / ML model / function, it performs spatial beam prediction or temporal beam prediction according to the configuration information.

[0023] The beneficial effects of this application's embodiments include: the terminal device receives configuration information from a network device, the configuration information including at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; and based on AI / ML functions / models, performs spatial beam prediction and / or temporal beam prediction according to the configuration information. This improves the accuracy of beam management and enhances the performance and efficiency of AI / ML.

[0024] Specific embodiments of this application are disclosed in detail with reference to the following description and accompanying drawings, indicating how the principles of this application can be adopted. It should be understood that the embodiments of this application are not limited in scope. Within the spirit and scope of the appended claims, embodiments of this application include many changes, modifications, and equivalents.

[0025] Features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0026] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, whole, step, or component, but does not exclude the presence or addition of one or more other features, wholes, steps, or components. Attached Figure Description

[0027] The elements and features described in one drawing or embodiment of this application may be combined with elements and features shown in one or more other drawings or embodiments. Furthermore, in the drawings, similar reference numerals denote corresponding parts in several drawings and can be used to indicate corresponding parts used in more than one embodiment.

[0028] Figure 1 is a schematic diagram of a communication system according to an embodiment of this application;

[0029] Figure 2 is a schematic diagram of AI / ML used for beam management;

[0030] Figure 3 is a schematic diagram of a beam prediction method according to an embodiment of this application;

[0031] Figure 4 is another schematic diagram of the beam management method according to an embodiment of this application;

[0032] Figure 5 is a schematic diagram of the measurement window and prediction window according to an embodiment of this application;

[0033] Figure 6 is an example diagram of an aperiodic CSI-RS configuration according to an embodiment of this application;

[0034] Figure 7 is another example diagram of the non-periodic CSI-RS configuration according to an embodiment of this application;

[0035] Figure 8 is another example diagram of the non-periodic CSI-RS configuration according to an embodiment of this application;

[0036] Figure 9 is an example diagram of the release of the CSI processing unit according to an embodiment of this application;

[0037] Figure 10 is another example diagram of the release of the CSI processing unit according to an embodiment of this application;

[0038] Figure 11 is a schematic diagram of a beam prediction method according to an embodiment of this application;

[0039] Figure 12 is a schematic diagram of a beam prediction device according to an embodiment of this application;

[0040] Figure 13 is a schematic diagram of a beam prediction device according to an embodiment of this application;

[0041] Figure 14 is a schematic diagram of a terminal device according to an embodiment of this application;

[0042] Figure 15 is a schematic diagram of a network device according to an embodiment of this application. Detailed Implementation

[0043] Referring to the accompanying drawings, the foregoing and other features of this application will become apparent from the following description. Specific embodiments of this application are specifically disclosed in the description and drawings, illustrating partial implementations in which the principles of this application may be employed. It should be understood that this application is not limited to the described embodiments; rather, it includes all modifications, variations, and equivalents falling within the scope of the appended claims.

[0044] In the embodiments of this application, the terms "first," "second," etc., are used to distinguish different elements by name, but do not indicate the spatial arrangement or chronological order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one or more of the terms listed in association and all combinations thereof. The terms "comprising," "including," "having," etc., refer to the presence of the stated features, elements, components, or assemblies, but do not exclude the presence or addition of one or more other features, elements, components, or assemblies.

[0045] In the embodiments of this application, the singular forms "a," "the," etc., including the plural forms, should be broadly understood as "a kind" or "a class" rather than limited to the meaning of "an." Furthermore, the term "the" should be understood to include both the singular and plural forms, unless the context explicitly indicates otherwise. Additionally, the term "according to" should be understood as "at least partially based on…," and the term "based on" should be understood as "at least partially based on…," unless the context explicitly indicates otherwise.

[0046] In the embodiments of this application, the term "communication network" or "wireless communication network" may refer to a network that conforms to any of the following communication standards, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), etc.

[0047] Furthermore, communication between devices in a communication system can be carried out according to communication protocols at any stage, including but not limited to the following communication protocols: 1G (generation), 2G, 2.5G, 2.75G, 3G, 4G, 4.5G and 5G, New Radio (NR), future 6G, etc., and / or other currently known or future communication protocols.

[0048] In the embodiments of this application, the term "network device" refers, for example, to a device in a communication system that connects a terminal device to a communication network and provides services to that terminal device. Network devices may include, but are not limited to, the following devices: base station (BS), access point (AP), transmission reception point (TRP), broadcast transmitter, mobile management entity (MME), gateway, server, radio network controller (RNC), base station controller (BSC), etc.

[0049] The term "base station" can include, but is not limited to, NodeBs (or NBs), evolved NodeBs (eNodeBs or eNBs), 5G base stations (gNBs), IAB hosts, etc. It can also include Remote Radio Heads (RRHs), Remote Radio Units (RRUs), relays, or low-power nodes (e.g., femeto, pico, etc.). The term "base station" can encompass some or all of its functions, and each base station can provide communication coverage to a specific geographic area. The term "cell" can refer to a base station and / or its coverage area, depending on the context in which the term is used.

[0050] In the embodiments of this application, the terms "User Equipment" (UE) or "Terminal Equipment" (TE) refer, for example, to a device that accesses a communication network and receives network services through a network device. A terminal device can be fixed or mobile, and may also be referred to as a mobile station (MS), terminal, subscriber station (SS), access terminal (AT), station, etc.

[0051] The terminal device may include, but is not limited to, the following devices: cellular phone, personal digital assistant (PDA), wireless modem, wireless communication device, handheld device, machine-type communication device, laptop computer, cordless phone, smartphone, smartwatch, digital camera, etc.

[0052] For example, in scenarios such as the Internet of Things (IoT), terminal devices can also be machines or devices for monitoring or measurement, such as including but not limited to: machine-type communication (MTC) terminals, vehicle communication terminals, device-to-device (D2D) terminals, machine-to-machine (M2M) terminals, and so on.

[0053] Furthermore, the terms "network side" or "network equipment side" refer to one side of the network, which can be a base station or include one or more network devices as described above. The terms "user side," "terminal side," or "terminal equipment side" refer to the side of the user or terminal, which can be a UE or include one or more terminal devices as described above. Unless otherwise specified, "equipment" can refer to either network equipment or terminal equipment.

[0054] The following examples illustrate the scenarios of embodiments of this application, but this application is not limited thereto.

[0055] Figure 1 is a schematic diagram of a communication system according to an embodiment of this application, illustrating the case of a terminal device and a network device as examples. As shown in Figure 1, the communication system 100 may include a network device 101 and terminal devices 102 and 103. For simplicity, Figure 1 only illustrates the case of two terminal devices and one network device, but the embodiments of this application are not limited to this.

[0056] In this embodiment of the application, network device 101 and terminal devices 102 and 103 can transmit existing services or services that can be implemented in the future. For example, these services may include, but are not limited to: enhanced mobile broadband (eMBB), massive machine-type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0057] It is worth noting that Figure 1 shows that both terminal devices 102 and 103 are within the coverage area of ​​network device 101, but this application is not limited to this. Both terminal devices 102 and 103 may be outside the coverage area of ​​network device 101, or one terminal device 102 may be within the coverage area of ​​network device 101 while the other terminal device 103 may be outside the coverage area of ​​network device 101.

[0058] In the embodiments of this application, higher-layer signaling may be, for example, Radio Resource Control (RRC) signaling; for example, referred to as an RRC message, including MIB, system information, dedicated RRC messages; or referred to as an RRC information element. Higher-layer signaling may also be, for example, Medium Access Control (MAC) signaling; or referred to as a MAC control element. However, this application is not limited to these.

[0059] Since Rel-15, NR 5G has introduced beam management. The beam management process is based on beam sweeping. For example, the gNB needs to send beams to the UE in sequence, and the UE can select the best one or more beams and provide feedback.

[0060] The gNB can configure reference signals for the UE, such as Channel State Information Reference Signal (CSI-RS) / Synchronization Signal Block (SSB) for beam scanning and beam measurement. To indicate which beam to select for communication, the gNB configures Transmission Configuration Indication (TCI) states and indicates which TCI states are used. For example, the gNB can configure a list of TCI states via RRC, and then select a subset of the configured TCI states (e.g., 8 TCI states) to be active via MAC CE, and indicate the active TCI state to the UE via DCI (e.g., via the TCI indication field in the DCI).

[0061] In Rel-19, AI / ML-based beam management was introduced. AI / ML-based beam management in Rel-19 (BM Case-1 and BM Case-2, with NW-side and / or UE-side models) can reduce overhead.

[0062] Figure 2 is a schematic diagram of AI / ML used for beam management. As shown in Figure 2, one or more reference signals (which may be referred to as RS for measurement or RS for inference) in the second reference signal resource set (set B) can be received and measured by the terminal device. The measurement results can be used as input to AI / ML. One or more reference signals (which may be referred to as RS for prediction) in the first reference signal resource set (set A) can be used by the terminal device as output to AI / ML, for example, the measurement results can be used as labeled data or ground truth data for AI / ML. For details regarding AI / ML and sets A and B, please refer to relevant technologies, which will not be elaborated here.

[0063] As shown in Figure 2, for example, AI / ML-based beam management can predict the information corresponding to set A (a larger number of reference signals) based on the measurement results of set B (a smaller number of reference signals), and can perform beam prediction in the spatial / temporal domains.

[0064] The above provides an illustrative description of beam management, but this application is not limited thereto. Furthermore, the above embodiments can be considered as part of the embodiments of this application, applicable to this application, and can also be implemented in combination with one or more of the following embodiments.

[0065] In the embodiments of this application, one or more AI / ML models can be configured and run in network devices and / or terminal devices. AI / ML models can be used for various signal processing functions in wireless communication, such as CSI prediction, CSI compression, beam prediction, positioning management, etc.; this application is not limited thereto.

[0066] First aspect of the embodiments

[0067] This application provides a beam prediction method, which is described from the perspective of the terminal device.

[0068] Figure 3 is a schematic diagram of a beam prediction method according to an embodiment of this application. As shown in Figure 3, the method includes:

[0069] 301, The terminal device receives configuration information for beam management from the network device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0070] 302, the terminal device performs spatial beam prediction or temporal beam prediction based on the configuration information, using an AI / ML model / function.

[0071] It is worth noting that Figure 3 above is only an illustrative description of the embodiments of this application, but this application is not limited thereto. For example, the execution order between various operations can be appropriately adjusted, and other operations can be added or some operations can be removed. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the description in Figure 3 above.

[0072] In some embodiments, a functionality refers to an AI / ML feature / feature group enabled by a configuration, wherein the configuration is supported based on conditions indicated by UE capabilities.

[0073] For example, an AL / ML function can be one or more functions, or one or more logical models, or one or more sub-functions, or one or more features, or one or more feature groups.

[0074] For example, the function could be to use AI / ML for spatial beam prediction, or to use AI / ML for temporal beam prediction, or to use AI / ML for CSI prediction, or to use AI / ML for direct positioning, or to use AI / ML for assisted positioning, and so on.

[0075] In some embodiments, the AI / ML function / model can be used for beam management. One or more reference signals are used for measurement, and the measurement results are input to the AI / ML function / model. Another one or more reference signals are used to input the output of the AI / ML function / model for inference.

[0076] For ease of description, beam management based on AI / ML functionality / model will be referred to as model inference or inference operation, training data collection based on AI / ML functionality / model will be referred to as training data collection (training data collection can also use non-AI / ML methods), and performance monitoring based on AI / ML functionality / model will be referred to as performance monitoring.

[0077] In some embodiments, the configuration information may include configuration information for one or more reference signals, such as CSI-RS configuration information, etc. This application is not limited thereto; further details regarding specific configuration information can be found in related technologies. The configuration information may include configuration information for training data collection, and / or configuration information for model inference, and / or configuration information for performance monitoring.

[0078] Figure 4 is another schematic diagram of the beam management method according to an embodiment of this application, illustrated using a terminal device configured with AI / ML as an example. As shown in Figure 4, the method includes:

[0079] 401. The terminal device receives configuration information from the network device; for example, the configuration information includes a second set of reference signal resources (set B) for measurement and a first set of reference signal resources (set A) for prediction.

[0080] 402, The terminal device receives the reference signal;

[0081] 403. The terminal device performs reference signal measurements and inputs the measurement results into the AI / ML function / model; for example, the measurement results of the reference signal in set B are used as input to AI / ML, and the reference signal in set A is used for prediction (or inference); and

[0082] 404, the terminal device sends the prediction result to the network device.

[0083] For example, the AI / ML function resides on the terminal device side. After enabling or activating the AI / ML function, the terminal device performs measurements based on reference signals from the network side, uses AI / ML to perform beam prediction based on the measurement results, and sends the prediction results to the network device.

[0084] It is worth noting that Figure 4 above is only an illustrative description of the embodiments of this application, but this application is not limited thereto. For example, the execution order between various operations can be appropriately adjusted, and other operations can be added or some operations can be removed. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the description in Figure 4 above.

[0085] In some embodiments, for BM case-2 with a terminal-side model, the terminal device can measure reference signals transmitted over one or more time instances within a measurement / observation window. The terminal-side AI / ML model / function can predict the beam quality of one or more future time instances (i.e., the prediction window).

[0086] Figure 5 is a schematic diagram of the measurement window and prediction window according to an embodiment of this application. As shown in Figure 5, the measurement window may include multiple time instances (T1 to T4), on which CSI-RS can be sent. The terminal device can measure these CSI-RS and input the measurement results into an AI / ML model / function for inference, thereby predicting the beam quality of multiple time instances (T5 to T8) in the prediction window. As shown in Figure 5, the terminal device can report the inference results to the network device.

[0087] The above illustrations demonstrate AI / ML-based beam management, but this application is not limited thereto.

[0088] For BM case-2, if periodic / semi-persistent CSI-RS is used, the UE needs to continuously measure CSI-RS, which is a significant overhead. Aperiodic CSI-RS helps the gNB understand the UE's beam quality and has less overhead. The following will illustrate how to configure aperiodic CSI-RS, using BM case-2 as an example, but it is not limited thereto; some embodiments are also applicable to BM case-1.

[0089] In some embodiments, for time beam prediction with a terminal-side model, one or more aperiodic CSI-RS resource sets are configured.

[0090] For example, in BM case-2 with a UE-side model, aperiodic CSI-RS can be configured for set B so that the UE can perform reference signal measurements, i.e., for the measurement window / observation window. One or more sets of aperiodic CSI-RS resources can be configured.

[0091] In some embodiments, the number of reference signal resources in an aperiodic reference signal resource set can be greater than 16. For example, in an aperiodic CSI-RS resource set, the number of CSI-RS resources can be greater than 16, no longer limited to 16.

[0092] In some embodiments, an aperiodic reference signal resource set is configured, the aperiodic reference signal resource set comprising multiple subsets (or sub-configurations or groups), wherein the number of reference signal resources in a subset is the same size as a second reference signal resource set (set B) for beam measurement, and a subset corresponds to a time instance in a measurement window (or observation window) for inference.

[0093] For example, an aperiodic CSI-RS resource set can be configured, comprising multiple aperiodic CSI-RS resources. These aperiodic CSI-RS resources can be grouped into multiple subsets / sub-resource sets / resource groups / sub-configurations.

[0094] For example, within a subset / subresource set / resource group / subconfiguration, the number of CSI-RS resources is the same as the size of set B. The slot offsets of the subset / subresource set / resource group / subconfiguration may differ, and one subset / subresource set / resource group / subconfiguration corresponds to a time instance within the measurement window.

[0095] For example, you can configure a time slot offset for the first subset / sub-resource set / resource group / sub-configuration, and also configure the time interval between two consecutive subsets / sub-source sets / resource groups / sub-configurations.

[0096] Figure 6 is an example diagram of an aperiodic CSI-RS configuration according to an embodiment of this application. As shown in Figure 6, an NZP CSI-RS resource set is configured, which includes: CSI-RS resource subset #1, CSI-RS resource subset #2, CSI-RS resource subset #3, and CSI-RS resource subset #4. Each CSI-RS resource subset includes M CSI-RS resources (CSI-RS resource #1 to CSI-RS resource #M), for example, M is the size of set B.

[0097] As shown in Figure 6, each CSI-RS resource subset corresponds to a time instance in the measurement window (or observation window). For example, CSI-RS resource subset #1 corresponds to time instance T1, CSI-RS resource subset #2 corresponds to time instance T2, CSI-RS resource subset #3 corresponds to time instance T3, and CSI-RS resource subset #4 corresponds to time instance T4.

[0098] In some embodiments, an aperiodic reference signal resource set is configured, the aperiodic reference signal resource set including a plurality of reference signal resources, wherein the number of reference signal resources in the aperiodic reference signal resource set is the same size as a second reference signal resource set (set B) for beam measurement, and the aperiodic reference signal resource set is configured with a plurality of triggering offset values, one value corresponding to a time instance in a measurement window (or observation window) for inference.

[0099] For example, an aperiodic CSI-RS resource set can be configured, comprising multiple aperiodic CSI-RS resources. The number of these aperiodic CSI-RS resources is the same as the size of set B. The aperiodic CSI-RS resource set can be configured with multiple values ​​for the aperiodic triggering offset, each value corresponding to a time instance within the measurement window. Thus, based on the configured triggering offset values, the aperiodic CSI-RS resource set will be repeatedly transmitted across multiple time instances within the measurement window.

[0100] For example, for aperiodic CSI-RS resource sets, a trigger offset list, such as aperiodic TriggeringOffsetList, can be configured. This trigger offset list can include multiple trigger offsets, each of which is used to trigger a transmission for that aperiodic CSI-RS resource set once.

[0101] Figure 7 is another example diagram of an aperiodic CSI-RS configuration according to an embodiment of this application. As shown in Figure 6, an NZP CSI-RS resource set is configured, for example, CSI-RS resource set #1. The CSI-RS resource set #1 includes M CSI-RS resources (CSI-RS resource #1 to CSI-RS resource #M), for example, M is the size of set B.

[0102] As shown in Figure 7, DCI can be used to trigger aperiodic CSI-RS. The multiple values ​​for the aperiodic trigger offset are {2, 4, 6, 8}, each corresponding to a time instance in the measurement window. For example, value 2 triggers CSI-RS resource set #1 to transmit on time instance T1, value 4 triggers CSI-RS resource set #1 to transmit on time instance T2, value 6 triggers CSI-RS resource set #1 to transmit on time instance T3, and value 8 triggers CSI-RS resource set #1 to transmit on time instance T4.

[0103] In some embodiments, a plurality of aperiodic reference signal resource sets are configured, each aperiodic reference signal resource set including a plurality of reference signal resources, wherein the number of reference signal resources in one aperiodic reference signal resource set is the same size as the second reference signal resource set (set B) used for beam measurement, and one aperiodic reference signal resource set corresponds to a time instance in a measurement window (or observation window) used for inference.

[0104] For example, multiple aperiodic CSI-RS resource sets can be configured. One aperiodic CSI-RS resource set corresponds to one time instance in the measurement window; that is, the number of aperiodic CSI resource sets is the same as the number of time instances in the measurement window. Within an aperiodic CSI-RS resource set, the number of CSI-RS resources is the same as the size of set B.

[0105] For example, all aperiodic CSI-RS resource sets in a measurement window can be triggered by the same DCI, or aperiodic CSI-RS resource sets in a measurement window can be triggered by different DCIs respectively.

[0106] Figure 8 is another example diagram of the non-periodic CSI-RS configuration according to an embodiment of this application. As shown in Figure 8, multiple CSI-RS resource sets are configured, including: CSI-RS resource set #1, CSI-RS resource set #2, CSI-RS resource set #3, and CSI-RS resource set #4. Each CSI-RS resource set includes M CSI-RS resources (CSI-RS resource #1 to CSI-RS resource #M), for example, M is the size of set B.

[0107] As shown in Figure 8, each CSI-RS resource set corresponds to a time instance in the measurement window (or observation window). For example, CSI-RS resource set #1 corresponds to time instance T1, CSI-RS resource set #2 corresponds to time instance T2, CSI-RS resource set #3 corresponds to time instance T3, and CSI-RS resource set #4 corresponds to time instance T4.

[0108] The above has explained aperiodic resource sets; the following will explain periodic / semi-persistent resource sets.

[0109] In some embodiments, for time beam prediction with an end-side model, one or more periodic or semi-persistent CSI-RS resource sets are configured.

[0110] For example, in BM Case-2 with a UE-side model, periodic CSI-RS / semi-persistent CSI-RS can be configured for set B so that the UE can perform reference signal measurements; that is, periodic CSI-RS / semi-persistent CSI-RS is used for the measurement window. One set of periodic / semi-persistent CSI-RS resources can be configured, or multiple sets of periodic / semi-persistent CSI-RS resources can be configured.

[0111] In some embodiments, a periodic or semi-persistent set of reference signal resources is configured, the set of periodic or semi-persistent reference signal resources comprising multiple subsets (or sub-configurations or groups), wherein the number of reference signal resources in a subset is the same size as a second set of reference signal resources (set B) for beam measurement, and a subset corresponds to a time instance in a measurement window (or observation window) for inference.

[0112] For example, a periodic / semi-persistent CSI-RS resource set can be configured, which includes multiple periodic or semi-persistent CSI-RS resources. These periodic / semi-persistent CSI-RS resources can be grouped into multiple subsets / sub-resource sets / resource groups / sub-configurations.

[0113] For example, within a subset / subresource set / resource group / subconfiguration, the number of CSI-RS resources is the same as the size of set B. A subset / subresource set / resource group / subconfiguration corresponds to a time instance within a measurement window.

[0114] In some embodiments, a periodic or semi-persistent reference signal resource set is configured, the periodic or semi-persistent reference signal resource set comprising a plurality of reference signal resources, wherein the number of reference signal resources in the periodic or semi-persistent reference signal resource set is the same size as a second reference signal resource set (set B) for beam measurement, and the periodic or semi-persistent reference signal resource set is indicated to not be transmitted on at least a portion of time instances in the measurement window (or observation window) and / or prediction window used for inference.

[0115] For example, a set of periodic / semi-persistent CSI-RS resources can be configured, which includes multiple periodic or semi-persistent CSI-RS resources. The number of these CSI-RS resources is the same as the size of set B.

[0116] For example, periodic / semi-persistent CSI-RS resource sets can be explicitly configured so that they are not transmitted on one or more time instances in the measurement window and / or prediction window. For example, a bitmap can be configured with a length equal to the total number of time instances in the measurement window and prediction window.

[0117] For example, periodic / semi-persistent CSI-RS resource sets can be implicitly configured so that they are not transmitted over time instances in the measurement and / or prediction windows. For instance, the number of time instances in the prediction window can be configured, and periodic / semi-persistent CSI-RS resource sets are not sent after the time slot containing the inference results report.

[0118] In some embodiments, a plurality of periodic or semi-persistent reference signal resource sets are configured, each periodic or semi-persistent reference signal resource set including a plurality of reference signal resources, wherein the number of reference signal resources in a periodic or semi-persistent reference signal resource set is the same size as a second reference signal resource set (set B) used for beam measurement, and a periodic or semi-persistent reference signal resource set corresponds to a time instance in a measurement window (or observation window) used for inference.

[0119] For example, multiple periodic / semi-persistent CSI-RS resource sets can be configured. Each periodic or semi-persistent CSI-RS resource set corresponds to a time instance within a measurement window; that is, the number of resources in a periodic or semi-persistent CSI-RS resource set is the same as the number of time instances within the measurement window. Within a periodic / semi-persistent CSI-RS resource set, the number of CSI-RS resources is the same as the size of set B.

[0120] The above provides an illustrative explanation of the model inference process. The following section will describe the collection of training data.

[0121] In some embodiments, for training data collection, if the second reference signal resource set (set B) used for measurement is different from the first reference signal resource set (set A) used for prediction, then a resource set is configured that includes information corresponding to both the second reference signal resource set (set B) and the first reference signal resource set (set A).

[0122] For example, for training data collection, if set B is different from set A, such as the reference signal in set B being SSB and the reference signal in set A being CSI-RS, then a resource set can be configured for the UE, where the resource set includes both SSB and CSI-RS.

[0123] For example, a new resource indicator can be defined that identifies the SSB and CSI-RS. The collected data includes both the new resource indicator representing beam information and the corresponding L1-RSRP.

[0124] For example, a resource set can be divided into two parts / subsets / groups, one for the SSB and the other for the CSI-RS. The SSBRI and CSI-RS can be identified using SSBRI and CRI, respectively. The collected data includes the SSBRI or CRI and the corresponding L1-RRP.

[0125] The above data collection examples can be applied to both BM case-1 and BM case-2. Furthermore, they can be applied to both network-side and terminal-side models.

[0126] The above provides an illustrative overview of the resource set. The following provides a further illustrative overview of the CSI processing unit (CPU). The following embodiments can be implemented in conjunction with the foregoing embodiments, or they can be implemented independently; this application is not limited thereto.

[0127] In NR, the concept of a CSI processing unit (CPU) is introduced into the CSI report, including beam management reports and CSI reports. If the UE supports NR... CPU Synchronous CSI calculation (N) CPU Simultaneous CSI calculations) can be said to have N for processing CSI reports. CPU CSI processing unit.

[0128] NR specifies CSI processing standards for different report quantities, including the number of CPUs used and the CPU usage time. For non-periodic CSI reports, CPU occupation extends from the first symbol after the PDCCH triggers the CSI report to the last symbol of the PUSCH carrying that CSI report. For periodic / semi-persistent CSI reports, CPU occupation extends from the first symbol of the CSI-RS / SSB to the last symbol of the PUSCH / PUCCH carrying the CSI report.

[0129] However, for BM case-2, the UE needs to measure multiple time instances within a measurement window. If the aforementioned CSI processing standard is followed, the CPU will be occupied throughout the entire measurement window. Considering that the intervals between time instances within a measurement window may be relatively long, the CPU occupation time will result in a waste of UE processing power. The following embodiments of this application illustrate this situation.

[0130] In some embodiments, for time beam prediction with an end-side model, the CSI processing unit (CPU) is released after reference signal measurements are performed on one or more time instances in the measurement window (or observation window) used for inference.

[0131] For example, in time-beam prediction with an end-side model, the CSI processing unit (CPU) is released after the reference signal measurement is performed for each time instance in the measurement window (or observation window) used for inference. For each time instance, CPU usage extends from the first symbol of the CSI-RS / SSB to the last symbol of the CSI-RS / SSB.

[0132] For example, in time beam prediction with a terminal-side model, the CSI processing unit (CPU) is released after a reference signal measurement is performed on one or more time instances (e.g., the first, or the first two, etc.) in the measurement window (or observation window) used for inference.

[0133] Figure 9 is an example diagram of CSI processing unit release according to an embodiment of this application. As shown in Figure 9, for example, for BM case-2 with a UE-side model, for model inference operations, CPU usage is released after each time instance in the measurement window is measured. For each time instance, CPU usage extends from the first symbol of CSI-RS to the last symbol of CSI-RS.

[0134] In some embodiments, for time beam prediction with a terminal-side model, the CSI processing unit (CPU) is released after the reference signal measurement for all time instances in the measurement window (or observation window) used for inference except for the last time instance;

[0135] For the last time instance in the measurement window (or observation window), the CSI processing unit (CPU) is occupied from the first symbol of the reference signal in the last time instance until the last symbol of the uplink channel carrying the inference result report.

[0136] Figure 10 is another example diagram of CSI processing unit release in an embodiment of this application. As shown in Figure 10, for example, for BM case-2 with UE-side model, for model inference operation, in the measurement window, after measurement is performed in each time instance (T1, T2, T3 shown in Figure 10) except for the last time instance in the measurement window, CPU usage is released.

[0137] As shown in Figure 10, for the last time instance in the measurement window (T4 shown in Figure 10), CPU usage starts from the first symbol of the CSI-RS / SSB in that time instance and ends at the last symbol of the PUSCH / PUCCH that carries the inference result report.

[0138] The above explains the model inference process; the following section will explain the performance monitoring process.

[0139] In some embodiments, for time beam prediction with an end-side model, the CSI processing unit (CPU) is released after reference signal measurements are performed on one or more time instances in the prediction window and / or the measurement window (or observation window) associated with performance monitoring.

[0140] For example, in BM case-2 with a UE-side model, for performance monitoring, CPU usage is released after measurement is performed in one or more time instances (e.g., the first, or the first two, etc.) within the measurement window, and / or, CPU usage is released after measurement of the reference signal used for monitoring is performed in one or more time instances (e.g., the first, or the first two, etc.) within the prediction window.

[0141] In some embodiments, for time beam prediction with an end-side model, for each time instance in the prediction window for performance monitoring and / or the measurement window (or observation window) associated with performance monitoring, the occupancy of the CSI processing unit (CPU) is released after the reference signal is measured.

[0142] For example, in BM case-2 with a UE-side model, for performance monitoring, CPU usage is released after measurement at each time instance within the measurement window, and / or, CPU usage is released after measurement of the reference signal used for monitoring at each time point within the prediction window. For each time instance, CPU usage ranges from the first symbol of the CSI-RS to the last symbol of the CSI-RS.

[0143] In some embodiments, for time beam prediction with a terminal-side model, for all time instances in the prediction window used for performance monitoring except the last time instance, the CSI processing unit (CPU) is released after the reference signal measurement; for the last time instance in the prediction window used for performance monitoring, the CSI processing unit (CPU) is occupied from the first symbol of the reference signal in the last time instance until the last symbol of the uplink channel carrying the monitoring result report.

[0144] For example, in BM case-2 with a UE-side model, for performance monitoring, CPU usage is released after each time instance in the measurement window is measured. In the prediction window, CPU usage is released after each time instance except the last time instance, after the reference signal used for monitoring is measured; for the last time instance in the prediction window, CPU usage starts from the first symbol of the CSI-RS / SSB in that time instance and ends at the last symbol of the PUSCH / PUCCH carrying the report.

[0145] In some embodiments, for spatial beam prediction with an end-side model, if a time window for performance monitoring is configured, the occupancy of the CSI processing unit (CPU) is released after reference signal measurements are performed for one or more time instances of that time window.

[0146] For example, in BM case-1 with a UE-side model, CPU occupancy is released after measurement for each time instance within that time window. For each time instance, CPU occupancy ranges from the first symbol of the CSI-RS / SSB to the last symbol of the CSI-RS / SSB.

[0147] For example, if performance is reported after all instances within the time window are measured, then CPU usage is released after each instance except the last one is measured within the time window. For the last instance in the time window, CPU usage starts from the first symbol of the CSI-RS / SSB in that instance and ends at the last symbol of the PUSCH / PUCCH carrying the report.

[0148] The embodiments of this application can be applied to both the UE-side model and the gNB-side model, but this application is not limited thereto. Furthermore, the AI / ML in the embodiments of this application can be used for beam management, such as temporal beam prediction and / or spatial beam prediction, but this application is not limited thereto; for example, non-AI / ML methods can also be used for data collection.

[0149] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0150] As can be seen from the above embodiments, the terminal device receives configuration information from the network device, the configuration information including at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; based on AI / ML functions / models, spatial beam prediction and / or temporal beam prediction are performed according to the configuration information. This improves the accuracy of beam management and enhances the performance and efficiency of AI / ML.

[0151] Second aspect of the embodiments

[0152] This application provides a beam prediction method, described from the perspective of a network device. Embodiments of the second aspect can be combined with embodiments of the first aspect, and details identical to those of the first aspect will not be repeated.

[0153] Figure 11 is a schematic diagram of a beam prediction method according to an embodiment of this application. As shown in Figure 11, the method includes:

[0154] 1101, The network device sends configuration information for beam management to the terminal device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction.

[0155] As shown in Figure 11, the method may further include:

[0156] 1102, The terminal device performs spatial beam prediction or temporal beam prediction based on the configuration information, using an AI / ML model / function.

[0157] It is worth noting that Figure 11 above is only an illustrative description of the embodiments of this application, but this application is not limited thereto. For example, the execution order between various operations can be appropriately adjusted, and other operations can be added or some operations can be removed. Those skilled in the art can make appropriate modifications based on the above content, and are not limited to the description in Figure 11 above.

[0158] In some embodiments, for time beam prediction with a terminal-side model, one or more aperiodic CSI-RS resource sets are configured.

[0159] In some embodiments, the number of reference signal resources in a non-periodic reference signal resource set can be greater than 16.

[0160] In some embodiments, an aperiodic reference signal resource set is configured, the aperiodic reference signal resource set comprising multiple subsets (or sub-configurations or groups).

[0161] The number of reference signal resources in a subset is the same as the size of the second reference signal resource set (set B) used for beam measurement, and a subset corresponds to a time instance in the measurement window (or observation window) used for inference.

[0162] In some embodiments, an aperiodic reference signal resource set is configured, the aperiodic reference signal resource set comprising a plurality of reference signal resources.

[0163] The number of reference signal resources in the aperiodic reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and the aperiodic reference signal resource set is configured with multiple values ​​of triggering offset, each value corresponding to a time instance in the measurement window (or observation window) used for inference.

[0164] In some embodiments, a plurality of aperiodic reference signal resource sets are configured, and one aperiodic reference signal resource set includes a plurality of reference signal resources.

[0165] In this context, the number of reference signal resources in an aperiodic reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and an aperiodic reference signal resource set corresponds to a time instance in the measurement window (or observation window) used for inference.

[0166] In some embodiments, for time beam prediction with a terminal-side model,

[0167] One or more periodic or semi-persistent CSI-RS resource sets are configured.

[0168] In some embodiments, a set of periodic or semi-persistent reference signal resources is configured, the set of periodic or semi-persistent reference signal resources comprising multiple subsets (or sub-configurations or groups).

[0169] The number of reference signal resources in a subset is the same as the size of the second reference signal resource set (set B) used for beam measurement, and a subset corresponds to a time instance in the measurement window (or observation window) used for inference.

[0170] In some embodiments, a set of periodic or semi-persistent reference signal resources is configured, the set of periodic or semi-persistent reference signal resources including a plurality of reference signal resources.

[0171] The number of reference signal resources in the periodic or semi-persistent reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and the periodic or semi-persistent reference signal resource set is indicated to not be transmitted on at least a portion of the time instances in the measurement window (or observation window) and / or prediction window used for inference.

[0172] In some embodiments, a plurality of periodic or semi-persistent reference signal resource sets are configured, wherein a periodic or semi-persistent reference signal resource set includes a plurality of reference signal resources.

[0173] The number of reference signal resources in a periodic or semi-persistent reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and a periodic or semi-persistent reference signal resource set corresponds to a time instance in the measurement window (or observation window) used for inference.

[0174] In some embodiments, for training data collection,

[0175] If the second reference signal resource set (set B) used for measurement is different from the first reference signal resource set (set A) used for prediction, then a resource set is configured that includes information corresponding to both the second reference signal resource set (set B) and the first reference signal resource set (set A).

[0176] In some embodiments, for time beam prediction with a terminal-side model,

[0177] After the reference signal is measured for one or more time instances in the measurement window (or observation window) used for inference, the CSI processing unit (CPU) is released from its occupancy.

[0178] In some embodiments, for time beam prediction with a terminal-side model,

[0179] After the reference signal is measured for each time instance in the measurement window (or observation window) used for inference, the CSI processing unit (CPU) is released from its occupancy.

[0180] In some embodiments, for time beam prediction with a terminal-side model,

[0181] For all time instances in the measurement window (or observation window) used for inference except the last time instance, the CSI processing unit (CPU) is released after the reference signal is measured;

[0182] For the last time instance in the measurement window (or observation window), the CSI processing unit (CPU) is occupied from the first symbol of the reference signal in the last time instance until the last symbol of the uplink channel carrying the inference result report.

[0183] In some embodiments, for time beam prediction with a terminal-side model,

[0184] After reference signal measurements are performed on one or more time instances in the prediction window and / or the measurement window (or observation window) associated with performance monitoring, the CSI processing unit (CPU) is released.

[0185] In some embodiments, for time beam prediction with a terminal-side model,

[0186] For each time instance in the prediction window and / or the measurement window (or observation window) associated with performance monitoring, the CSI processing unit (CPU) is released after the reference signal is measured.

[0187] In some embodiments, for time beam prediction with a terminal-side model,

[0188] For all time instances in the prediction window used for performance monitoring except the last time instance, the CSI processing unit (CPU) is released after the reference signal is measured.

[0189] For the last time instance in the prediction window used for performance monitoring, the CSI processing unit (CPU) is occupied from the first symbol of the reference signal in the last time instance until the last symbol of the uplink channel carrying the monitoring result report.

[0190] In some embodiments, for spatial beam prediction with a terminal-side model,

[0191] If a time window for performance monitoring is configured, the CSI processing unit is released after the reference signal is measured for each time instance within that time window.

[0192] In some embodiments, for spatial beam prediction with a terminal-side model,

[0193] If a time window for performance monitoring is configured, the CSI processing unit is released after the reference signal is measured for all time instances within that time window except the last time instance.

[0194] For the last time instance in the time window, CPU usage begins from the first symbol of the reference signal in the last time instance and ends at the last symbol of the uplink channel carrying the detection result report.

[0195] In some embodiments, the network device may receive feedback information and / or report information sent by the terminal device. For example, the terminal device may report inference results and / or performance monitoring results and / or training data collection results to the network device, but this application is not limited thereto.

[0196] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0197] As can be seen from the above embodiments, the terminal device receives configuration information from the network device, the configuration information including at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; based on AI / ML functions / models, spatial beam prediction and / or temporal beam prediction are performed according to the configuration information. This improves the accuracy of beam management and enhances the performance and efficiency of AI / ML.

[0198] Third aspect of the embodiments

[0199] This application provides a beam prediction device. This device may be, for example, a terminal device, or one or more components or parts configured within a terminal device; details identical to those in the first and second aspects will not be repeated.

[0200] Figure 12 is a schematic diagram of a beam prediction device according to an embodiment of this application. As shown in Figure 12, the beam prediction device 1200 according to an embodiment of this application includes:

[0201] Receiver 1201 receives configuration information for beam management from a network device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0202] The processor 1202 performs spatial beam prediction or temporal beam prediction based on the configuration information, using an AI / ML model / function.

[0203] In some embodiments, as shown in FIG12, the beam prediction device 1200 may further include a transmitter 1203, which sends report information / feedback information to network devices, but this application is not limited thereto.

[0204] In some embodiments, for time beam prediction with a terminal-side model, one or more aperiodic CSI-RS resource sets are configured.

[0205] In some embodiments, the number of reference signal resources in a non-periodic reference signal resource set can be greater than 16.

[0206] In some embodiments, an aperiodic reference signal resource set is configured, the aperiodic reference signal resource set comprising multiple subsets (or sub-configurations or groups).

[0207] The number of reference signal resources in a subset is the same as the size of the second reference signal resource set (set B) used for beam measurement, and a subset corresponds to a time instance in the measurement window (or observation window) used for inference.

[0208] In some embodiments, an aperiodic reference signal resource set is configured, the aperiodic reference signal resource set comprising a plurality of reference signal resources.

[0209] The number of reference signal resources in the aperiodic reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and the aperiodic reference signal resource set is configured with multiple values ​​of triggering offset, each value corresponding to a time instance in the measurement window (or observation window) used for inference.

[0210] In some embodiments, a plurality of aperiodic reference signal resource sets are configured, and one aperiodic reference signal resource set includes a plurality of reference signal resources.

[0211] In this context, the number of reference signal resources in an aperiodic reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and an aperiodic reference signal resource set corresponds to a time instance in the measurement window (or observation window) used for inference.

[0212] In some embodiments, for time beam prediction with a terminal-side model,

[0213] One or more periodic or semi-persistent CSI-RS resource sets are configured.

[0214] In some embodiments, a set of periodic or semi-persistent reference signal resources is configured, the set of periodic or semi-persistent reference signal resources comprising multiple subsets (or sub-configurations or groups).

[0215] The number of reference signal resources in a subset is the same as the size of the second reference signal resource set (set B) used for beam measurement, and a subset corresponds to a time instance in the measurement window (or observation window) used for inference.

[0216] In some embodiments, a set of periodic or semi-persistent reference signal resources is configured, the set of periodic or semi-persistent reference signal resources including a plurality of reference signal resources.

[0217] The number of reference signal resources in the periodic or semi-persistent reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and the periodic or semi-persistent reference signal resource set is indicated to not be transmitted on at least a portion of the time instances in the measurement window (or observation window) and / or prediction window used for inference.

[0218] In some embodiments, a plurality of periodic or semi-persistent reference signal resource sets are configured, wherein a periodic or semi-persistent reference signal resource set includes a plurality of reference signal resources.

[0219] The number of reference signal resources in a periodic or semi-persistent reference signal resource set is the same as the size of the second reference signal resource set (set B) used for beam measurement, and a periodic or semi-persistent reference signal resource set corresponds to a time instance in the measurement window (or observation window) used for inference.

[0220] In some embodiments, for training data collection,

[0221] If the second reference signal resource set (set B) used for measurement is different from the first reference signal resource set (set A) used for prediction, then a resource set is configured that includes information corresponding to both the second reference signal resource set (set B) and the first reference signal resource set (set A).

[0222] In some embodiments, for time beam prediction with a terminal-side model,

[0223] After the reference signal is measured for one or more time instances in the measurement window (or observation window) used for inference, the CSI processing unit (CPU) is released from its occupancy.

[0224] In some embodiments, for time beam prediction with a terminal-side model,

[0225] After the reference signal is measured for each time instance in the measurement window (or observation window) used for inference, the CSI processing unit (CPU) is released from its occupancy.

[0226] In some embodiments, for time beam prediction with a terminal-side model,

[0227] For all time instances in the measurement window (or observation window) used for inference except the last time instance, the CSI processing unit (CPU) is released after the reference signal is measured;

[0228] For the last time instance in the measurement window (or observation window), the CSI processing unit (CPU) is occupied from the first symbol of the reference signal in the last time instance until the last symbol of the uplink channel carrying the inference result report.

[0229] In some embodiments, for time beam prediction with a terminal-side model,

[0230] After reference signal measurements are performed on one or more time instances in the prediction window and / or the measurement window (or observation window) associated with performance monitoring, the CSI processing unit (CPU) is released.

[0231] In some embodiments, for time beam prediction with a terminal-side model,

[0232] For each time instance in the prediction window and / or the measurement window (or observation window) associated with performance monitoring, the CSI processing unit (CPU) is released after the reference signal is measured.

[0233] In some embodiments, for time beam prediction with a terminal-side model,

[0234] For all time instances in the prediction window used for performance monitoring except the last time instance, the CSI processing unit (CPU) is released after the reference signal is measured.

[0235] For the last time instance in the prediction window used for performance monitoring, the CSI processing unit (CPU) is occupied from the first symbol of the reference signal in the last time instance until the last symbol of the uplink channel carrying the monitoring result report.

[0236] In some embodiments, for spatial beam prediction with a terminal-side model,

[0237] If a time window for performance monitoring is configured, the CSI processing unit is released after the reference signal is measured for each time instance within that time window.

[0238] In some embodiments, for spatial beam prediction with a terminal-side model,

[0239] If a time window for performance monitoring is configured, the CSI processing unit is released after the reference signal is measured for all time instances within that time window except the last time instance.

[0240] For the last time instance in the time window, CPU usage begins from the first symbol of the reference signal in the last time instance and ends at the last symbol of the uplink channel carrying the detection result report.

[0241] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0242] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The beam prediction device 1200 may also include other components or modules, and for details regarding these components or modules, please refer to relevant technologies.

[0243] Furthermore, for simplicity, Figure 12 only illustrates the connection relationships or signal flow between the various components or modules, but those skilled in the art should understand that various related technologies such as bus connections can be used. The aforementioned components or modules can be implemented using hardware facilities such as processors, memory, transmitters, and receivers; this application does not limit this implementation.

[0244] As can be seen from the above embodiments, the terminal device receives configuration information from the network device, the configuration information including at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; based on AI / ML functions / models, spatial beam prediction and / or temporal beam prediction are performed according to the configuration information. This improves the accuracy of beam management and enhances the performance and efficiency of AI / ML.

[0245] Fourth aspect of the embodiment

[0246] This application provides a beam prediction device. This device may be, for example, a network device, or one or more components or parts configured within a network device; details identical to those in the embodiments of the first to third aspects will not be repeated.

[0247] Figure 13 is another schematic diagram of a beam prediction device according to an embodiment of this application. As shown in Figure 13, the beam prediction device 1300 includes:

[0248] Transmitter 1301 sends configuration information for beam management to a terminal device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction.

[0249] The terminal device, based on AI / ML models / functions, performs spatial beam prediction or temporal beam prediction according to the configuration information.

[0250] In some embodiments, as shown in FIG13, the beam prediction device 1300 may further include:

[0251] Receiver 1302 receives report information / feedback information sent by terminal equipment, but this application is not limited thereto.

[0252] The above embodiments are merely illustrative examples of embodiments of this application, but this application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0253] It is worth noting that the above description only covers the components or modules relevant to this application, but this application is not limited thereto. The beam prediction device 1300 may also include other components or modules, and for details regarding these components or modules, please refer to relevant technologies.

[0254] Furthermore, for simplicity, Figure 13 only illustrates the connection relationships or signal flow between the various components or modules, but those skilled in the art should understand that various related technologies such as bus connections can be used. The aforementioned components or modules can be implemented using hardware facilities such as processors, memory, transmitters, and receivers; this application does not limit this implementation.

[0255] As can be seen from the above embodiments, the terminal device receives configuration information from the network device, the configuration information including at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; based on AI / ML functions / models, spatial beam prediction and / or temporal beam prediction are performed according to the configuration information. This improves the accuracy of beam management and enhances the performance and efficiency of AI / ML.

[0256] Fifth aspect of the embodiment

[0257] This application also provides a communication system, which can be referred to FIG1. ​​The contents that are the same as those in the embodiments of the first to fourth aspects will not be repeated.

[0258] In some embodiments, the communication system 100 may include at least:

[0259] A network device that transmits configuration information for beam management; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0260] The terminal device receives configuration information for beam management from the network device; based on the AI / ML model / function, it performs spatial beam prediction or temporal beam prediction according to the configuration information.

[0261] This application also provides a terminal device, but the application is not limited thereto and may also include other devices.

[0262] Figure 14 is a schematic diagram of a terminal device according to an embodiment of this application. As shown in Figure 14, the terminal device 1400 may include a processor 1410 and a memory 1420; the memory 1420 stores data and programs and is coupled to the processor 1410. It is worth noting that this figure is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunications functions or other functions.

[0263] For example, processor 1410 may be configured to execute a program to implement the beam prediction method as described in the embodiments of the first aspect. For example, processor 1410 may be configured to perform the following control: receive configuration information for beam management from a network device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; and perform spatial beam prediction or temporal beam prediction based on an AI / ML model / function and according to the configuration information.

[0264] As shown in Figure 14, the terminal device 1400 may further include: a communication module 1430, an input unit 1440, a display 1450, and a power supply 1460. The functions of these components are similar to those in the prior art and will not be described in detail here. It is worth noting that the terminal device 1400 does not necessarily include all the components shown in Figure 14; these components are not essential. Furthermore, the terminal device 1400 may also include components not shown in Figure 14, which can be referred to in the prior art.

[0265] This application also provides a network device, such as a base station, but this application is not limited to this and may also include other network devices.

[0266] Figure 15 is a schematic diagram of the network device configuration according to an embodiment of this application. As shown in Figure 15, the network device 1500 may include: a processor 1510 (e.g., a central processing unit CPU) and a memory 1520; the memory 1520 is coupled to the processor 1510. The memory 1520 can store various data; in addition, it also stores an information processing program 1530, and executes the program 1530 under the control of the processor 1510.

[0267] For example, processor 1510 may be configured to execute a program to implement the beam prediction method as described in the embodiments of the second aspect. For example, processor 1510 may be configured to perform control such as sending configuration information for beam management to a terminal device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; wherein the configuration information is used by the terminal device to perform spatial beam prediction or temporal beam prediction based on an AI / ML model / function.

[0268] In addition, as shown in Figure 15, network device 1500 may also include: transceiver 1540 and antenna 1550, etc.; the functions of the above components are similar to those in the prior art, and will not be described in detail here. It is worth noting that network device 1500 does not necessarily include all the components shown in Figure 15; in addition, network device 1500 may also include components not shown in Figure 15, which can be referred to in the prior art.

[0269] This application also provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to perform the beam prediction method described in the first aspect of the embodiment.

[0270] This application also provides a storage medium storing a computer program, wherein the computer program causes a terminal device to execute the beam prediction method described in the first aspect of the embodiment.

[0271] This application also provides a computer program, wherein when the program is executed in a network device, the program causes the network device to perform the beam prediction method described in the second aspect of the embodiment.

[0272] This application also provides a storage medium storing a computer program, wherein the computer program causes a network device to perform the beam prediction method described in the second aspect of the embodiment.

[0273] The apparatus and methods described above in this application can be implemented in hardware or in combination with software. This application relates to a computer-readable program that, when executed by a logic component, enables the logic component to implement the apparatus or components described above, or to implement the various methods or steps described above. This application also relates to storage media for storing the above programs, such as hard disks, magnetic disks, optical disks, DVDs, flash memory, etc.

[0274] The methods / apparatus described in conjunction with the embodiments of this application can be directly embodied in hardware, software modules executed by a processor, or a combination of both. For example, one or more and / or combinations of one or more functional block diagrams shown in the figures can correspond to various software modules in a computer program flow, or to various hardware modules. These software modules can correspond to the various steps shown in the figures, respectively. These hardware modules can be implemented, for example, using a field-programmable gate array (FPGA) to embed these software modules.

[0275] The software module can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. A storage medium can be coupled to the processor, enabling the processor to read information from and write information to the storage medium; or the storage medium can be an integral part of the processor. The processor and storage medium can reside in an ASIC. The software module can be stored in the memory of a mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a high-capacity MEGA-SIM card or a high-capacity flash memory device, the software module can be stored in the MEGA-SIM card or the high-capacity flash memory device.

[0276] One or more and / or one or more combinations of functional blocks described in the accompanying drawings can be implemented as a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, or any suitable combination thereof for performing the functions described herein. One or more and / or one or more combinations of functional blocks described in the accompanying drawings can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0277] The present application has been described above with reference to specific embodiments. However, those skilled in the art should understand that these descriptions are exemplary and not intended to limit the scope of protection of the present application. Those skilled in the art can make various modifications and variations to the present application based on its spirit and principles, and these modifications and variations are also within the scope of the present application.

[0278] Regarding the implementation methods including the above embodiments, the following notes are also disclosed:

[0279] 1. A beam prediction method, comprising:

[0280] The terminal device receives configuration information for beam management from the network device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0281] The terminal device performs spatial beam prediction or temporal beam prediction based on the configuration information, using AI / ML models / functions.

[0282] 2. A beam prediction method, comprising:

[0283] The network device sends configuration information for beam management to the terminal device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction;

[0284] The configuration information is used by the terminal device to perform spatial beam prediction or temporal beam prediction based on AI / ML models / functions.

[0285] 3. A terminal device comprising a memory and a processor, the memory storing a computer program and the processor being configured to execute the computer program to implement the beam prediction method as described in Appendix 1.

[0286] 4. A network device comprising a memory and a processor, the memory storing a computer program and the processor being configured to execute the computer program to implement the beam prediction method as described in Appendix 2.

[0287] 5. A computer program product comprising at least a computer program that, when executed by a processor, causes a terminal device to perform the beam prediction method as described in Appendix 1.

[0288] 6. A computer program product comprising at least a computer program that, when executed by a processor, causes a network device to perform the beam prediction method as described in Appendix 2.

Claims

1. A beam prediction device, comprising: A receiver that receives configuration information for beam management from a network device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; The processor, based on an AI / ML model / function, performs spatial beam prediction or temporal beam prediction according to the configuration information.

2. The apparatus according to claim 1, wherein, For time beam prediction with terminal-side model One or more sets of aperiodic reference signal resources are configured.

3. The apparatus according to claim 2, wherein, The number of reference signal resources in a non-periodic reference signal resource set can be greater than 16.

4. The apparatus according to claim 2, wherein, An aperiodic reference signal resource set is configured, the aperiodic reference signal resource set comprising multiple subsets. The number of reference signal resources in a subset is the same as the size of the second set of reference signal resources used for beam measurement, and a subset corresponds to a time instance in the measurement window used for inference.

5. The apparatus according to claim 2, wherein, An aperiodic reference signal resource set is configured, the aperiodic reference signal resource set comprising multiple reference signal resources. The number of reference signal resources in the aperiodic reference signal resource set is the same as the size of the second reference signal resource set used for beam measurement, and the aperiodic reference signal resource set is configured with multiple values ​​for trigger offset, one value corresponding to a time instance in the measurement window used for inference.

6. The apparatus according to claim 2, wherein, Multiple sets of aperiodic reference signal resources are configured, and each set of aperiodic reference signal resources includes multiple reference signal resources. The number of reference signal resources in a non-periodic reference signal resource set is the same as the size of the second reference signal resource set used for beam measurement, and a non-periodic reference signal resource set corresponds to a time instance in the measurement window used for inference.

7. The apparatus according to claim 1, wherein, For time beam prediction with terminal-side model One or more periodic or semi-persistent reference signal resource sets are configured.

8. The apparatus according to claim 7, wherein, A set of periodic or semi-persistent reference signal resources is configured, the set of periodic or semi-persistent reference signal resources comprising multiple subsets. The number of reference signal resources in a subset is the same as the size of the second set of reference signal resources used for beam measurement, and a subset corresponds to a time instance in the measurement window used for inference.

9. The apparatus according to claim 7, wherein, A set of periodic or semi-persistent reference signal resources is configured, the set of periodic or semi-persistent reference signal resources comprising multiple reference signal resources. The number of reference signal resources in the periodic or semi-persistent reference signal resource set is the same as the size of the second reference signal resource set used for beam measurement, and the periodic or semi-persistent reference signal resource set is indicated to be not transmitted on at least a portion of the time instances in the measurement window and / or prediction window used for inference.

10. The apparatus according to claim 7, wherein, Multiple sets of periodic or semi-persistent reference signal resources are configured, and each set of periodic or semi-persistent reference signal resources includes multiple reference signal resources. The number of reference signal resources in a periodic or semi-persistent reference signal resource set is the same as the size of the second reference signal resource set used for beam measurement, and a periodic or semi-persistent reference signal resource set corresponds to a time instance in the measurement window used for inference.

11. The apparatus according to claim 1, wherein, For training data collection, If the second set of reference signal resources used for measurement is different from the first set of reference signal resources used for prediction, then a resource set is configured that includes information corresponding to both the second and first sets of reference signal resources.

12. The apparatus according to claim 1, wherein, For time beam prediction with terminal-side model After the reference signal is measured for each time instance in the measurement window used for inference, the CSI processing unit is released from its occupancy.

13. The apparatus according to claim 1, wherein, For time beam prediction with terminal-side model For all time instances in the measurement window used for inference except the last time instance, the CSI processing unit is released after the reference signal is measured; For the last time instance in the measurement window, the CSI processing unit is occupied from the first symbol of the reference signal in the last time instance until the last symbol of the uplink channel carrying the inference result report.

14. The apparatus according to claim 1, wherein, For time beam prediction with terminal-side model For each time instance in the prediction window and / or measurement window associated with performance monitoring used for performance monitoring, the CSI processing unit is released after the reference signal is measured.

15. The apparatus according to claim 1, wherein, For time beam prediction with terminal-side model For all time instances in the prediction window used for performance monitoring except the last time instance, in the reference signal The CSI processing unit is released after the measurement; For the last time instance in the prediction window used for performance monitoring, the occupancy of the CSI processing unit begins from the first symbol of the reference signal in the last time instance and ends with the last symbol of the uplink channel carrying the monitoring result report.

16. The apparatus according to claim 1, wherein, For spatial beam prediction with terminal-side models If a time window for performance monitoring is configured, the CSI processing unit is released after the reference signal is measured for each time instance within that time window.

17. The apparatus according to claim 1, wherein, For spatial beam prediction with terminal-side models If a time window for performance monitoring is configured, the CSI processing unit is released after the reference signal is measured for all time instances within that time window except the last time instance. For the last time instance in the time window, CPU usage begins from the first symbol of the reference signal in the last time instance and ends at the last symbol of the uplink channel carrying the detection result report.

18. A beam prediction device, comprising: A transmitter that sends configuration information for beam management to a terminal device; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction. The configuration information is used by the terminal device to perform spatial beam prediction or temporal beam prediction based on AI / ML models / functions.

19. The apparatus according to claim 18, wherein, For time beam prediction with terminal-side model One or more aperiodic reference signal resource sets are configured, and / or one or more periodic or semi-persistent reference signal resource sets are configured.

20. A communication system, comprising: A network device that transmits configuration information for beam management; wherein the configuration information includes at least one or more resource sets for temporal beam prediction and / or spatial beam prediction; The terminal device receives configuration information for beam management from the network device; based on the AI / ML model / function, it performs spatial beam prediction or temporal beam prediction according to the configuration information.

Images