Communication methods and terminal devices

Abstract

An embodiment of the present disclosure relates to a communication method, an apparatus, and a computer storage medium, the method including: receiving, in a terminal device, from a network device, a configuration of Channel State Information (CSI) reporting indicating at least information related to at least one of a collection procedure of the network device for collecting one or more CSI reports collected from the terminal device, or an inference procedure of the network device for inferring one or more CSIs based on the collected one or more CSI reports; and transmitting the CSI report based on the information, the CSI report including at least one of a periodic CSI report, a semi-persistent CSI report, and a first type CSI report.

Description

[Technical Field]

[0001] Embodiments of this disclosure relate, as a whole, to the field of telecommunications, and more particularly to methods, apparatus and computer storage media for predicting channel state information (CSI) in the time domain. [Background technology]

[0002] Currently, the application of artificial intelligence / machine learning (AI / ML) methods is being considered in wireless communication, particularly in time-domain CSI or beam prediction. CSI / beam prediction is a continuous process, and control signaling can lead to frequent activation / deactivation or deactivation of CSI reports. [Overview of the Initiative] [Problems that the invention aims to solve]

[0003] Overall, exemplary embodiments of this disclosure provide methods, apparatus, and computer storage media for time-domain CSI prediction. [Means for solving the problem]

[0004] In a first aspect, a method is provided. The method includes, in a terminal device, receiving a setting of a Channel State Information (CSI) report that at least indicates information related to at least one of a collection procedure of the network device for collecting one or more CSI reports collected from the terminal device or an inference procedure of the network device for inferring one or more CSIs based on the one or more collected CSI reports, and transmitting the CSI report based on the information, wherein the CSI report includes at least one of a periodic CSI report, a semi-persistent CSI report, and a first type of CSI report.

[0005] In a second aspect, a method is provided. The method includes, in a network device, determining a setting of a Channel State Information (CSI) report that at least indicates information related to at least one of a collection procedure of the network device for collecting one or more CSI reports collected from the terminal device or an inference procedure of the network device for inferring one or more CSIs based on the one or more collected CSI reports, and transmitting the setting to the terminal device.

[0006] In a third aspect, a terminal device is provided. The terminal device includes a processor and a memory. The memory is coupled to the processor and stores instructions. When the instructions are executed by the processor, the instructions cause the network device to execute the method described in the first aspect of the present disclosure.

[0007] In a fourth aspect, a network device is provided. The network device includes a processor and a memory. The memory is coupled to the processor and stores instructions. When the instructions are executed by the processor, the instructions cause the network device to execute the method described in the second aspect of the present disclosure.

[0008] In a fifth aspect, a computer-readable medium storing instructions is provided. When the instructions are executed on at least one processor, the at least one processor is caused to execute the method according to the first aspect or the second aspect.

[0009] It should be understood that the summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure should be readily understandable from the following description. **Brief Description of the Drawings**

[0010] The above and other objects, features and advantages of the present disclosure will become more apparent by describing some embodiments of the present disclosure in more detail with reference to the accompanying drawings.

[0011] [Figure 1] FIG. is a diagram showing an exemplary communication network in which embodiments of the present disclosure can be implemented.

[0012] [Figure 2] FIG. is a signaling diagram showing an exemplary CSI prediction process in the time domain according to some embodiments of the present disclosure.

[0013] [Figure 3] FIG. is a diagram showing an example of CSI prediction in the time domain according to some embodiments of the present disclosure.

[0014] [Figure 4] FIG. is a diagram showing an example of CSI prediction in the time domain according to some embodiments of the present disclosure.

[0015] [Figure 5A] FIG. is a diagram showing an example of CSI prediction in the time domain according to some embodiments of the present disclosure. [Figure 5B] FIG. is a diagram showing an example of CSI prediction in the time domain according to some embodiments of the present disclosure.

[0016] [Figure 6] This figure shows an example of CSI prediction in the time domain according to some embodiments of the present disclosure.

[0017] [Figure 7] This figure shows an example of CSI prediction in the time domain according to some embodiments of the present disclosure.

[0018] [Figure 8] This figure shows an example of CSI prediction in the time domain according to some embodiments of the present disclosure.

[0019] [Figure 9] This flowchart shows an exemplary CSI prediction method in the time domain according to some embodiments of the present disclosure.

[0020] [Figure 10] This flowchart shows an exemplary CSI prediction method in the time domain according to some embodiments of the present disclosure.

[0021] [Figure 11] This is a schematic block diagram of an apparatus suitable for realizing the embodiments of the present disclosure.

[0022] In the diagram, identical or similar reference numbers represent identical or similar elements. [Modes for carrying out the invention]

[0023] Herein, the principles of the disclosure will be explained with reference to several exemplary embodiments. These embodiments are provided for illustrative purposes only and should be understood as helping those skilled in the art to understand and implement the disclosure, and should not be considered as implying any limitation on the scope of the disclosure. The disclosures described herein can be implemented in a variety of ways other than those described below.

[0024] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meanings as those generally understood by those skilled in the art.

[0025] References in this disclosure to “one embodiment,” “embodiment,” “exemplary embodiment,” etc., indicate that the described embodiment may include certain features, structures, or characteristics, but not all embodiments necessarily include such specific features, structures, or characteristics. Furthermore, such phrases do not necessarily refer to the same embodiment. Moreover, when describing certain features, structures, or characteristics in relation to an exemplary embodiment, it is considered that the influence of such features, structures, or characteristics in relation to other embodiments, whether or not they are explicitly described, is within the knowledge of those skilled in the art.

[0026] Terms such as "First" and "Second" may be used in this specification to describe various elements, but it should be understood that these elements should not be limited by these terms. These terms are used solely to distinguish the functions of various elements. As used herein, the term "and / or" includes any and all combinations of one or more of the terms described.

[0027] The terms used herein are for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. The singular forms “one” and “the foregoing” as used herein also include the plural forms unless expressly indicated in the context. Where used herein, the terms “include,” “encompass,” “have,” “equip,” “possess,” and / or “have” specify the presence of the described features, elements, and / or components, but should be further understood not to exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0028] As used herein, the term “communication network” includes fifth-generation (5G) systems, Long-Term Evolution (LTE), LTE-Advanced (LTE-A), and Wideband Code Division Multiple Access (WCDMA). (Registered trademark) This refers to networks conforming to any appropriate communication standard, such as Wideband Code Division Multiple Access, High-Speed ​​Packet Access (HSPA), and Narrow Band Internet of Things (NB-IoT). Furthermore, embodiments of this disclosure may be implemented in accordance with any generation of communication protocol currently known or to be developed in the future. Examples of communication protocols include, but are not limited to, first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G) communication protocols, 5.5G, 5G-Advanced networks, or sixth-generation (6G) networks, and / or any other protocol currently known or to be developed in the future. Embodiments of this disclosure can be applied to a variety of communication systems. Given the rapid development of communications, there will naturally be future types of communication technologies and systems that can embody this disclosure. This should not be considered to limit the scope of this disclosure to the aforementioned systems only.

[0029] As used herein, the term “network device” means a device capable of providing or hosting a cell or coverage on which terminal devices can communicate. Examples of network devices include, but are not limited to, low-power nodes such as Node B (NodeB or NB), Evolutionary Node B (eNodeB or eNB), Next Generation Node B (gNB), Transmit / Receive Point (TRP), Remote Radio Unit (RRU), Radio Head (RH), Remote Radio Head (RRH), IAB node, Femtonode, Piconode, Reconfigurable Intelligent Surface (RIS), and Network Control Repeater.

[0030] As used herein, the term “terminal device” refers to any device having wireless or wired communication capabilities. Examples of terminal devices include user equipment (UE), personal computers, desktops, mobile phones, cellular phones, smartphones, personal digital assistants (PDAs), portable computers, tablets, wearable devices, Internet of Things (IoT) devices, ultra-reliable low-latency communication (URLLC) devices, Internet of Everything (IoE) devices, machine-type communication (MTC) devices, in-vehicle devices for V2X communication where X is pedestrian, vehicle, or infrastructure / network, devices for integrated access and integrated access and backhaul (IAB), small data transmission (SDT), multicast and broadcast services (MBS), positioning, dynamic / flexible redundancy in commercial networks, reduced capability (RedCap), and high-altitude platforms (HAP) encompassing satellites and unmanned aircraft systems (UAS). This includes, but is not limited to, satellite-mounted vehicles or aircraft-mounted vehicles within a non-terrestrial network (NTN) including the Platform, extended reality (XR) devices that include different types of reality such as augmented reality (AR), mixed reality (MR), and virtual reality (VR), unmanned aerial vehicles (UAVs) that are aircraft without human pilots and are commonly referred to as drones, devices on high-speed trains (HST), or image acquisition devices such as digital cameras, sensor game devices, music storage and playback devices, or internet-connected home appliances that enable wireless or wired internet access and browsing.The “Terminal Device” may further have “Multicast / Broadcast” capabilities to support public safety and mission-critical, V2X applications, transparent IPv4 / IPv6 multicast distribution, IPTV, smart TV, wireless services, wireless software distribution, group communications, and IoT applications. It may also incorporate one or more Subscriber Identity Modules (SIMs), known as multi-SIMs. The term “Terminal Device” may be used interchangeably with UE, mobile station, subscriber station, mobile terminal, user terminal, or wireless device.

[0031] Terminal devices or network devices may possess artificial intelligence (AI) or machine learning capabilities. Generally, this includes a trained model derived from a large amount of data collected for a specific function, which can be used to predict certain information.

[0032] Terminal or network devices may operate on several frequency ranges, such as FR1 (410 MHz to 7125 MHz), FR2 (24.25 GHz to 71 GHz), frequency bands greater than 100 GHz, and terahertz (THz). Furthermore, they can operate on licensed / unlicensed / shared spectrum. Terminal devices may have two or more connections to network devices under Multi-Radio Dual Connectivity (MR-DC) application scenarios. Terminal or network devices can operate in full-duplex, flexible-duplex, or cross-split-duplex modes.

[0033] Network devices may have network energy saving, self-organizing network (SON) / drive test minimization (MDT) functions. Terminals may have power saving functions.

[0034] Embodiments of this disclosure may be implemented, for example, in test equipment such as signal generators, signal analyzers, spectrum analyzers, network analyzers, test terminal devices, test network devices, and channel emulators.

[0035] The functions described herein can be performed in fixed and / or wireless network nodes in various exemplary embodiments, but in other exemplary embodiments, the functions may be implemented in user device equipment (e.g., a mobile phone, tablet computer, laptop computer, desktop computer, mobile IoT device, or fixed IoT device). For example, user device equipment may optionally have the corresponding capabilities described in relation to fixed and / or wireless network nodes. User device equipment may be a control device such as a chipset or processor configured to control user device and / or user device when installed within user device equipment. Examples of such functions include bootstrap server functions and / or home subscriber servers, and can be implemented within user device equipment by providing user device equipment equipment with software configured to run from the perspective of these functions / nodes.

[0036] As used herein, the term “circuit” may mean a hardware circuit and / or a combination of a hardware circuit and software. For example, a circuit may be a combination of an analog and / or digital hardware circuit and software / firmware. In yet another example, a circuit may be any part of a hardware processor having a digital signal processor, software and one or more memories, which work together to cause a device such as a terminal or network device to perform various functions. In yet another example, a circuit may be a hardware circuit and / or a processor such as a microprocessor or a part thereof that requires software / firmware for operation, but the software may not be present if it is not required for operation. As used herein, the term “circuit” also includes the implementation of a hardware circuit or one or more processors alone, or a part of a hardware circuit or one or more processors and their (or their) accompanying software and / or firmware.

[0037] Figure 1 shows an exemplary communication network 100 on which embodiments of the present disclosure can be implemented. The network 100 includes a network device 120 and terminal devices 110-1, 110-2, ..., 110-N served by the network device 120. The serving area of ​​the network device 120 is referred to as cell 102. Hereinafter, terminal devices 110-1, 110-2..., 110-N may be collectively referred to as "UE 110" or "Terminal Device 110", and the network device 120 may be referred to as "gNB 120".

[0038] It should be understood that the number of network devices and terminal devices is given for illustrative purposes only and does not imply any limitation. The communication network 100 may include any suitable number of network devices and terminal devices suitable for carrying out embodiments of the present disclosure.

[0039] As mentioned above, the topic of time-domain CSI or beam prediction based on AI / ML, particularly discontinuous periodic CSI / beam measurement and reporting based on AI / ML, has already been discussed. For example, discussions on time-domain CSI or beam prediction may focus on scenarios such as unmanned energy mobility, e.g., trains, hypersonic transporters (HSTs), or highways.

[0040] For CSI / beam prediction in the time domain, it may be necessary to use periodic or semi-permanent reporting, particularly during the period in which inference data is collected. Periodic or semi-permanent reporting is unnecessary for inference (prediction) and application.

[0041] Periodic reporting may be set or released by radio resource control (RRC) signaling, which may indicate a period, an offset (i.e., a start slot), and may be associated with a periodic CSI reference signal (CSI-RS) resource.

[0042] Semi-persistent reporting may refer to semi-persistent CSI reporting based on a Physical Uplink Control Channel (PUCCH) and semi-persistent CSI reporting based on a Physical Uplink Shared Channel (PUSCH). PUCCH-based semi-persistent CSI reporting may be activated or deactivated by a Medium Access Control - Control Element (MAC-CE), while PUSCH-based semi-persistent CSI reporting may be activated or deactivated by Downlink Control Information (DCI).

[0043] For PUCCH-based semi-persistent CSI reporting, the CSI-ReportConfigID may be activated or deactivated by MAC-CE. The duration and / or offset may be set by RRC signaling. PUCCH-based semi-persistent CSI reporting may be associated with periodic / semi-persistent CSI-RS resources.

[0044] For push-based semi-persistent CSI reporting, the trigger state may be selected by DCI from the CSI-SemiPersistentOnPUSCH-TriggerStateList, and the trigger state may be associated with the semi-persistent CSI reporting. The duration may be set by RRC signaling. The offset may be selected by DCI from the offsetlist (set by RRC). Push-based semi-persistent CSI reporting may be associated with periodic / semi-persistent CSI-RS resources.

[0045] Periodic CSI-RS resources may be set or released by RRC signaling, while semi-persistent CSI-RS resources may be activated or deactivated by MAC-CE.

[0046] CSI / beam prediction is a continuous process that may include data acquisition procedures, inference procedures, and application procedures. Periodic or semi-persistent CSI reporting needs to be frequently set / activated or released / deactivated by control signaling, which can lead to excessive signaling overhead and delay. For example, in the acquisition procedure, the gNB may need to collect input data required for the AI / ML network (or model), which may be CSI / beams reported N times consecutively in the past. Meanwhile, in the inference procedure, the gNB may need to use the collected input data and the AI / ML network to predict the beam to be applied over a future period.

[0047] For example, assuming that an AI / ML model is deployed on the gNB side, the gNB may configure or enable periodic or semi-persistent CSI reporting and associated CSI-RS resources. In the case of periodic CSI-RS reporting, the gNB may configure periodic CSI reporting and associated periodic CSI resources (e.g., periodic CSI-RS resources) via their respective RRCs. Then, assuming that the reported beams are beam 1 to beam 4 in order, the UE may perform beam measurements based on the periodic CSI-RS resources and beam reporting within the uplink (UL) resources associated with the periodic CSI reporting. The gNB may predict the beam for the next period, for example, within the period of periodic CSI reporting (e.g., beam 5 (beam-5)). The gNB may then release the configuration of periodic CSI reporting and associated periodic CSI resources to reduce the overhead of beam measurement and reporting. Until beam 5 is about to fail, the gNB may set up another periodic CSI report and its associated periodic CSI resource via their respective RRCs.

[0048] In this process, the RRC signaling delay is large, for example, 10ms, and the overhead of frequent setting or releasing of PCSI reports / resources is also significant.

[0049] In the case of a semi-persistent CSI reporting scenario, the gNB may activate the semi-persistent CSI reporting and its associated SP CSI resource (e.g., SP CSI-RS resource) via their respective MAC-CEs. Optionally, the semi-persistent CSI reporting may also be activated by the DCI, and the associated CSI resource may be a P CSI resource set up by the RRC. Assuming the reported beams are beam 1 through beam 4 in order, the UE may perform beam measurements based on the SP CSI-RS resource and beam reporting within the UL resource associated with the semi-persistent CSI reporting. The gNB may predict the beam for the next period, for example, within the period of the semi-persistent CSI reporting (e.g., beam 5 (beam-5)). The gNB may then deactivate the semi-persistent CSI reporting and its associated SP CSI resource via their respective MAC-CEs to reduce the overhead of beam measurements and reporting. Until beam 5 is about to fail, the gNB may activate another semi-persistent CSI report and its associated SP CSI resource via their respective MAC-CEs.

[0050] In this process, the MAC-CE signaling delay is significant, for example, 3ms, and the overhead of frequent activation or deactivation of semi-persistent CSI reports / resources is also substantial.

[0051] To reduce the overhead and delay of RRC / MAC-CE / DCI signaling for periodic or semi-persistent reporting CSI reporting / reconfiguring or activating resources, an AI-based beam / CSI prediction mechanism in the time domain is expected to achieve and reduce unnecessary signaling and resource overhead.

[0052] In the solutions of this disclosure, the UE may receive a CSI reporting configuration from the gNB. This configuration provides information about at least one of the following: a gNB collection procedure for collecting one or more CSI reports collected from the UE, or a gNB inference procedure for inferring one or more CSIs based on the collected CSI reports. The UE may then transmit CSI reports based on this information. The CSI reports include at least one of periodic CSI reports, semi-permanent CSI reports, and a first type of CSI report.

[0053] In this way, the signaling overhead and delay caused by RRC / MAC-CE / DCI signaling for setting up or activating periodic or semi-permanent reporting CSI reports / resources can be significantly reduced.

[0054] The principles and embodiments of this disclosure will be described in detail below with reference to Figures 2 to 5.

[0055] Next, we refer to Figure 2, a signaling diagram illustrating an exemplary CSI prediction process in the time domain according to some embodiments of the present disclosure. For illustrative purposes, process 200 will be described with reference to Figure 1. Process 200 may involve UE 110 and gNB 120 as shown in Figure 1.

[0056] As shown in Figure 2, the gNB 120 may determine a CSI report configuration that provides at least information relating to at least one of the gNB's collection procedures for collecting one or more CSI reports collected from the UE, or the gNB's inference procedures for inferring one or more CSIs based on the collected CSI reports (202).

[0057] The gNB 120 may then send the CSI reporting settings to the UE 110 (204). Based on the received settings, the UE 110 may obtain information regarding at least one of the gNB's collection procedures for collecting one or more CSI reports collected from the UE, or the gNB's inference procedures for inferring one or more CSIs based on the collected CSI reports, and based on this information, may ensure that the CSIs are not expected to be reported to the gNB 120.

[0058] The process 200 may be described in more detail by the following embodiments with reference to Figures 3-5.

[0059] In an active Downlink (DL) Bandwidth Part (BWP) / Component Carrier (CC), UE 110 may be configured by gNB 120 to have periodic CSI reporting. The reporting resource (PUCCH) associated with the CSI reporting is allocated within the active UL BWP / CC with a subcarrier interval (SCS) of 15 kHz. Therefore, the number of slots within a single frame TIFF0007852724000001.tif1022 is 10. For example, as shown in Figure 3, frame 301 contains 10 slots. CSI report offset (i.e., starting slot) T offset and period T CSI These may be 2-slot and 5-slot, respectively. Assume the CSI report takes effect within frame 301, for example, within slot 331 of frame 301.

[0060] Based on the AI / ML network (or model), the CSI / beam corresponding to time M (in slot 335 of frame 303) can be predicted based on the reported CSI / beams corresponding to time M-4 (in slot 331 of frame 301), M-3 (in slot 332 of frame 301), M-2 (in slot 333 of frame 302), and M-1 (in slot 334 of SFN 302). Therefore, in slot 335 of SFN 303, UE 110 does not need to send the CSI report to gNB 120.

[0061] In some embodiments, the information included in the CSI report configuration may represent at least one of a first duration (which may also be referred to as "Duration of AI") that includes a second duration (which may also be referred to as "Duration of Collection") during which the collection procedure is performed by the network device and a third duration (which may also be referred to as "Duration of Inference") during which the inference procedure is performed by the network device.

[0062] In this case, the UE may use this information to ensure that the CSI report is not expected to be notified to the network device within the third duration.

[0063] In some embodiments, periodic or semi-persistent CSI reporting may also be associated with a Duration of AI, which includes a Duration of Collection and a Duration of Inference, where the Duration of Collection is used to indicate multiple slots in which the gNB or UE needs to collect input data required for inference in the AI / ML network, and where the Duration of Inference is used to indicate multiple slots in which the gNB or UE needs to predict (or infer) future CSI or beams based on the AI / ML network. That is, the Duration of Collection is used to indicate multiple slots in which the UE needs to send periodic or semi-persistent CSI reporting to the gNB, which may be analogous to the active time of CSI reporting. That is, the Duration of Inference is used to indicate multiple slots in which the UE does not need to send periodic or semi-persistent CSI reporting to the gNB, which may be analogous to the inactive time of CSI reporting.

[0064] Therefore, if a UE is configured to have DurationofAI, DurationofCollection, or DurationofInference, the UE will submit CSI reports within DurationofCollection, and the UE will drop CSI reports within DurationofInference, or the UE will not expect to report CSIs within DurationofInference. This may suggest that the gNB is unable to allocate CSI reporting resources.

[0065] In some embodiments, DurationofAI, DurationofCollection, or DurationofInference may be set or updated by control signaling, such as RRC signaling, MAC-CE, or DCI.

[0066] In some embodiments, DurationofAI includes Offset_DurationofAI, which indicates the starting slot (i.e., offset) of DurationofAI, and Period_DurationofAI, which indicates the duration of DurationofAI.

[0067] In some embodiments, Offset_DurationofAI or Period_DurationofAI may be set or updated by control signaling, such as RRC signaling, MAC-CE, or DCI.

[0068] In some embodiments, the UE may assume that the offset or duration of DurationofAI is the same as the offset or duration of the associated periodic or semi-permanent report. For example, as shown in Figure 3, DurationofCollection 311 and DurationofInference 312 are 16 slots and 5 slots, respectively (i.e., DurationofAI 310 is 21 slots), and the offset and duration of DurationofAI 320 are 2 slots and 5 slots, respectively.

[0069] In some embodiments, the duration of DurationofAI may be 0, meaning the UE should assume that the second DurationofAI starts immediately after the first DurationofAI has finished. As shown in Figure 4, DurationofCollection 411 and DurationofInference 412 are 16 slots and 9 slots, respectively, and the offset and duration of DurationofAI are 2 slots and 0 slots, respectively.

[0070] As shown in FIGS. 3 and 4, DurationofCollection and DurationofInference do not overlap, that is, DurationofInference starts within the first slot after the end of DurationofCollection. Also, DurationofInference may start before the end of DurationofCollection, that is, it is possible that DurationofCollection and DurationofInference partially overlap or even completely overlap.

[0071] In some embodiments, the information included in the CSI report setting may indicate a first number (hereinafter referred to as N C also referred to as) associated with the collection procedure and a second number (hereinafter referred to as N I also referred to as) associated with the inference procedure.

[0072] In this case, the UE may determine resources in the time domain that are not expected to be reported to the gNB 120 based on the first number and the second number.

[0073] In some embodiments, the periodic or semi-persistent reporting CSI report may be associated with NofAI including N C (N C ≧1) and N I (N I ≧1), where N C means that N C consecutively reported CSI / beams need to be used as input data for the AI / ML network, while N I refers to the number of prediction results output by the AI / ML network. FIGS. 5A and 5B show examples of CSI predictions corresponding to N C = 4, N I = 1 and N C = 4, N I = 2, respectively. In other words, for example, as shown in FIG. 5A, N CWithin a series of consecutive CSI reporting times, for example, within time points M-4 (slot 551), M-3 (slot 552), M-2 (slot 553), and M-1 (slot 554), the UE must send a CSI report. I During consecutive CSI reporting periods, for example, within time point M (slot 555), the UE is not required to report (or send) a CSI.

[0074] Therefore, UE is NofAI, N C or N I If configured to have, the UE may drop the Mth CSI report until the value of M satisfies the following conditions: TIFF0007852724000002.tif8110 Here, n I =1,2...,N I m=1,2, ...... (1)

[0075] Specifically, a UE may drop the Mth CSI report, which corresponds to the UE not expecting to report (or send) a CSI within the Mth PUCCH resource (or corresponding slot) associated with the CSI report. Furthermore, the Mth PUCCH resource associated with a CSI report refers to the Mth P / SP PUCCH transmission according to the RRC that sets up a P CSI report, or the MAC-CE that activates a semi-persistent CSI report. For example, the first PUCCH resource associated with a CSI report refers to the first periodic PUCCH transmission according to the RRC that sets up a periodic CSI report.

[0076] In some embodiments, NofAI, NC, or NI may be set or updated by control signaling, such as RRC signaling, MAC-CE, or DCI.

[0077] According to existing standards, for set periodic or semi-permanent reporting CSI reports, the UE is subject to SFN n f slots You may submit this CSI report within TIFF0007852724000003.tif99, where SFN n f and slot numbers within the frame TIFF0007852724000004.tif99 must satisfy the following conditions:

[0078] For PUCCH-based periodic or semi-permanent CSI reporting, periodic T CSI and slot offset T offset This is set by the higher-level parameter reportSlotConfig. Unless otherwise specified, the UE is SFN n that satisfies the following conditions f and slot numbers within the frame The CSI report should be sent within a frame containing TIFF0007852724000005.tif1011. TIFF0007852724000006.tif10141 Here, μ is the SCS setting of the UL BWP to which the CSI is sent.

[0079] For PUSCH-based semi-permanent CSI reporting, periodic T CSI This is set by the higher-level parameter reportSlotConfig. Unless otherwise specified, the UE is SFN n that satisfies the following conditions f and slot numbers within the frame The CSI report should be sent within a frame containing TIFF0007852724000007.tif1011. TIFF0007852724000008.tif9148 Here, TIFF0007852724000009.tif815 and TIFF0007852724000010.tif815 are the SFN and slot number within the frame of the initial semi-persistent PUSCH transmission according to the activated DCI, respectively.

[0080] The above conditions (abbreviated as n) f and n satisfying the condition referred to as TIFF0007852724000011.tif1011 f and It should be understood that TIFF0007852724000012.tif1011 may have multiple values. In practice, each CSI report associated with periodic or semi-permanent reporting has a specific n f and It may also be possible to use TIFF0007852724000013.tif1011.

[0081] In some embodiments, the plurality of determined n f and TIFF0007852724000014.tif1011 are, TIFF0007852724000015.tif812 and It may also be represented in ascending order by TIFF0007852724000016.tif1016, It is TIFF0007852724000017.tif616. Specifically, TIFF0007852724000018.tif812 and TIFF0007852724000019.tif1016 are each the (i+1)th determined n f and This refers to TIFF0007852724000020.tif1011.

[0082] Regarding PUCCH-based periodic or semi-permanent CSI reporting, TIFF0007852724000021.tif914 and TIFF0007852724000022.tif1016 refers to the SFN and slot number within the frame of the initial periodic or semi-persistent PUCCH transmission, respectively, according to the DCI that sets up the periodic CSI report, or the MAC CE that activates the semi-persistent CSI report.

[0083] Regarding PUSCH-based semi-permanent CSI reporting, TIFF0007852724000023.tif914 and TIFF0007852724000024.tif1016 refers to the SFN and slot number within the frame of the initial semi-persistent PUSCH transmission according to the DCI that activates the semi-persistent CSI report, respectively.

[0084] Figure 6 shows an example of a CSI forecast in the time domain according to some embodiments of the present disclosure. As shown in the figure, assume that the configured P CSI report takes effect from SFN 1. The UE needs to send the CSI report in slot 661 of frame 601, slot 602 of frame 601, slot 663 of frame 602, slot 664 of frame 602, slot 665 of frame 603, ... Therefore, TIFF0007852724000025.tif914 and TIFF0007852724000026.tif1016 is 1 and 2 respectively. TIFF0007852724000027.tif913 and TIFF0007852724000028.tif1017 is 1 and 7, TIFF0007852724000029.tif914 and TIFF0007852724000030.tif1118 is 2 and 2 respectively. TIFF0007852724000031.tif914 and TIFF0007852724000032.tif1118 is 2 and 7 respectively. TIFF0007852724000033.tif914 and TIFF0007852724000034.tif1017 is 3 and 2 respectively. TIFF0007852724000035.tif914 and TIFF0007852724000036.tif1017 is 3 and 7 respectively. TIFF0007852724000037.tif914 and TIFF0007852724000038.tif1118 is 4 and 2 respectively, that is, The filename is TIFF0007852724000039.tif12144.

[0085] UE is NofAI, N C or N I If configured to have, the UE satisfies the following, SFN n f and slot numbers within the frame You can also drop the CSI report within TIFF0007852724000040.tif99. TIFF0007852724000041.tif1030 TIFF0007852724000042.tif1337 TIFF0007852724000043.tif8121 Here, n I =1,2...,N I , m=1,2, ...... (4)

[0086] In other words, the UE does not expect to report a CSI within the SFN and slot number within the frame that meet the above conditions.

[0087] Figure 7 shows an example of CSI prediction in the time domain according to some embodiments of the present disclosure. As shown in the figure, N C =4, N I Assume = 1. The value of i is N C and N I It can be determined according to the following. The value of i is 4. Therefore, UE is SFN n that satisfies the following conditions. f and slot numbers within the frame You may drop the CSI report within TIFF0007852724000044.tif99, that is, within slot 775 of frame 703.

[0088] In some embodiments, the gNB 120 may indicate to the UE that the reported CSI report is a discontinuous periodic type CSI report (DP CSI).

[0089] Regarding the settings or parameters for DP CSI reporting, the settings or parameters associated with periodic or semi-permanent CSI reporting in Release 15 or 16 can be reused, unless the DP CSI reporting is associated with new parameters, such as DurationofAI, NofAI, etc.

[0090] In some embodiments, DP CSI reports may be set or released by the RRC and activated or deactivated by MAC-CE / DCI. For example, similar to periodic CSI reports, DP CSI reports (duration and offset) may be set by the RRC. Another example, similar to PUCCH-based semi-persistent CSI reports, DP CSI reports (duration and offset) may be set by the RRC and activated by MAC-CE. Similar to PUCCH-based semi-persistent CSI reports, a trigger state list associated with multiple DP CSI reports (duration) may be set by the RRC, and the trigger state (offset) may be activated by DCI. For example, DCI may be scrambled by a new radio network temporary identity (RNTI), e.g., DP-CSI-RNTI.

[0091] For DP CSI reporting, periodic or semi-permanent CSI-RS resources can be supported for CSI-RS resource configuration.

[0092] Specifically, if DL reporting is configured by RRC, only periodic CSI-RS resources can be supported. If DL reporting is configured and activated by MAC-CE / DCI, periodic or semi-persistent CSI-RS resources can be supported. For example, the supported combinations of CSI reporting settings and CSI-RS resource settings, and how CSI reporting is triggered for each CSI-RS resource setting, can be shown as follows. Table 1: Supported combinations of CSI reporting settings and CSI-RS resource settings, and how CSI reporting is triggered for each CSI-RS resource setting. TIFF0007852724000045.tif143163

[0093] In some embodiments, to reduce the central processing unit (CPU) required for configured CSI reporting, the UE can free up the CPU during periods when CSI reporting is not required.

[0094] Specifically, for CSI reports, if the following conditions are met, for example, if a periodic or semi-permanent CSI report is associated with Duration of AI, Duration of Collection, or Duration of Inference, or if a periodic or semi-permanent CSI report is associated with No of AI, N C or N I If associated with or if the CSI report is a DP CSI report (which may hereafter be referred to as satisfying the conditions of the first type), the UE may occupy the CPU only within the DurationofCollection or occupy the CPU except for reports within the DurationofInference. Also, the UE may occupy the CPU based on the value of M corresponding to reports that satisfy equation (1), or the SFN n corresponding to reports that satisfy equation (4). f and slot numbers within the frame Based on TIFF0007852724000046.tif1112, the CPU may be reduced.

[0095] For CSI reports that are not required, the UE may not receive the CSI-RS associated with the report in order to reduce power consumption. At the same time, to reduce the overhead of CSI measurement, the CSI-RS resource may not be configured by the gNB. Figure 8 shows an example of a CSI prediction in the time domain according to some embodiments of the present disclosure. For example, as shown in Figure 8, the UE does not expect to report a CSI within time M (in UL: slot 885 of frame 803), and within M, the transmission or reception of a CSI-RS associated with the CSI report (in DL: slot 886 of frame 802) is not expected.

[0096] For CSI reports, if the conditions of the first type are met, for periodic or semi-permanent CSI-RS, the UE optionally omits the CSI-RS resource for channel measurement within the most recent CSI-RS opportunity prior to the CSI reference resource corresponding to the CSI report within DurationofInference. Alternatively, the UE does not receive CSI-RS for channel measurement from the first symbol after PUCCH / PUSCH carrying the latest CSI report until the last symbol prior to the CSI reference resource corresponding to the CSI report within DurationofInference.

[0097] Furthermore, UE is a CSI reference resource corresponding to the CSI report, a value of M corresponding to a report that satisfies equation (1), or an SFN n corresponding to a report that satisfies equation (4). f and slot numbers within the frame In the most recent CSI-RS opportunity prior to TIFF0007852724000047.tif1112, it is also possible to omit the CSI-RS resource for channel measurement.

[0098] In other words, the UE, from the first symbol after PUCCH / PUSCH that carries the latest CSI report, is the CSI reference resource corresponding to the CSI report, the value of M corresponding to the report that satisfies equation (1), or the SFN n corresponding to the report that satisfies equation (4). fand slot numbers within the frame CSI-RS for channel measurement is not received until the last symbol preceding TIFF0007852724000048.tif1112.

[0099] Furthermore, if the gNB does not need to transmit periodic or semi-persistent CSI-RS within a certain period, the corresponding physical resources can be used for data transmission, such as PDSCH. Therefore, for PDSCH mapping to virtual resource blocks, the UE should assume that the corresponding physical resource blocks used for CSI-RS (i.e., non-zero power (NZP) CSI-RS) are available for PDSCH.

[0100] Furthermore, the time interval between the activation command indicating / updating the beam (i.e., the Transmission Coordination Indicator (TCI) state) and the most recent CSI-RS must be within 1280ms. When multiple beams can be predicted, if the UE does not receive the above CSI-RS corresponding to the CSI report within DurationofInference, (considering that the maximum duration of a periodic CSI is 640ms,) the time interval is likely to be longer than 1280ms. Therefore, to resolve this issue, the value of DurationofInference may optionally be limited to a threshold smaller than 1280ms. Alternatively, the above CSI report must also satisfy the condition that the time interval between the CSI report and the most recent CSI-RS is shorter than 1280ms.

[0101] According to existing standards, a UE supports only a limited number of active CSI-RS resources within an active BWP. In some embodiments, if a CSI report associated with a CSI-RS satisfies a first type of condition, the CSI-RS is inactive for a duration from the first symbol after a PUCCH / PUSCH carrying the latest CSI report to the last symbol before the CSI reference resource corresponding to the CSI report associated with the CSI-RS, where the CSI report is, for example, within DurationofInference, or the value of M corresponding to a report satisfying formula (1), or the SFN n corresponding to a report satisfying formula (4). f and slot numbers within the frame Satisfy TIFF0007852724000049.tif1112.

[0102] Furthermore, periodic or semi-permanent CSI reports associated with DurationofAI or NoofAI, or DP CSI reports, may conflict with other CSI reports in the time domain, particularly other periodic or semi-permanent CSI reports. In this case, the prioritization of these CSI reports needs to be clarified. Generally, since the collected data is used to predict future CSI or beams, if the time domain type of these conflicting CSI reports is the same, the CSI report used for AI / ML-based CSI / beam prediction should have a higher priority.

[0103] Therefore, if a CSI report associated with DurationofAI or NofAI conflicts with another CSI report not associated with DurationofAI or NofAI, and they are of the same type, the UE will prioritize sending the CSI report associated with DurationofAI or NofAI.

[0104] For example, for semi-persistent CSI reports transported on PUSCH and associated with DurationofAI or NofAI, y=1; for semi-persistent CSI reports transported on PUSCH and not associated with DurationofAI or NofAI, y=2; for semi-persistent CSI reports transported on PUCCH and associated with DurationofAI or NofAI, y=3; for semi-persistent CSI reports transported on PUCCH and not associated with DurationofAI or NofAI, y=4; for semi-persistent CSI reports transported on PUSCH and associated with DurationofAI or NofAI, y=5; and for semi-persistent CSI reports transported on PUSCH and not associated with DurationofAI or NofAI, y=6.

[0105] Alternatively, the priority values ​​may be determined according to y, w, k, c, and s. For example, TIFF0007852724000050.tif4168 Here, for non-periodic CSI reports carried on PUSCH, y=0; for semi-persistent CSI reports carried on PUSCH, y=1; for semi-persistent CSI reports carried on PUCCH, y=2; for periodic CSI reports carried on PUCCH, y=3; for CSI reports carrying Layer 1 Reference Signal Received Power (L1-RSRP), k=0; for CSI reports not carrying L1-RSRP or L1, k=1; c is the serving cell index; N cells is the value of the upper layer parameter maxNrofServingCells, s is reportConfigID, M s w=0 is the value of the upper-level parameter maxNrof-ReportConfigurations, where w=0 for CSI reports associated with DurationofAI or NofAI, and w=1 for CSI reports not associated with DurationofAI or NofAI.

[0106] Furthermore, if a DP CSI report associated with DurationofAI or NofAI conflicts with a periodic or semi-permanent CSI report, the UE may prioritize sending the DP CSI report.

[0107] For example, DP CSI reports, like periodic CSI reports, may be configured by RRC. Optionally, y=3 for DP CSI reports transported on PUCCH, and y=4 for periodic CSI reports transported on PUCCH. Another option is y=1 for DP CSI reports transported on PUCCH, y=2 for semi-permanent CSI reports transported on PUCCH, y=3 for semi-permanent CSI reports transported on PUCCH, and y=4 for periodic CSI reports transported on PUCCH.

[0108] For example, DP CSI reports may be activated by MAC-CE / DCI, similar to semi-permanent CSI reports. Optionally, y=1 for DP CSIs transported on PUSCH, y=2 for DP CSI reports transported on PUCCH, y=3 for semi-permanent CSI reports transported on PUSCH, y=4 for semi-permanent CSI reports transported on PUCCH, and y=5 for periodic CSI reports transported on PUCCH.

[0109] As described above, the gNB may determine the settings for CSI reporting, which include information that causes the UE to decide that reporting of CSI reports within a specific duration is dropped. In some embodiments, the gNB may set the above parameters based on whether the UE supports CSI / beam prediction in AI / ML-based durations, or on the ability of the UE to support AI / ML.

[0110] For example, gNB may use DurationofAI, DurationofCollection or DurationofInference, N, according to the capabilities reported by UE. C or N I The values ​​of can be determined, for example, the value of DurationofAI can be determined based on maxDurationofAI, which is the UE's capability and refers to the maximum DurationofAI that the UE can support; the value of DurationofCollection can be determined based on maxDurationofCollection, which is the UE's capability and refers to the maximum DurationofCollection that the UE can support; and the value of DurationofInference can be determined based on maxDurationofInference, which is the UE's capability and refers to the maximum DurationofInference that the UE can support. C The value of N is the number of UEs that can be supported. C maxN is the maximum value of UE's capabilities. C It can be determined based on N I The value of N is the number of UEs that can be supported. I maxN is the maximum value of UE's capabilities. I It can be determined based on this.

[0111] In some embodiments, the AI / ML (inference) functionality of the UE can be controlled by the gNB. Specifically, the gNB can turn the AI / ML functionality on or off through specific control signaling (RRC / MAC-CE / DCI). For example, the UE may be configured by the RRC to have an enable parameter used to activate the AI / ML functionality; otherwise, the AI / ML functionality will not be permitted on the UE side. In this case, if the AI / ML functionality is disabled, the UE may need to stop any current AI / ML-related behavior. Therefore, enabling the AI / ML functionality should be a prerequisite for all the UE behaviors mentioned above.

[0112] In some embodiments, the UE may receive a control command indicating that the AI / ML functionality has been enabled.

[0113] The solution of this disclosure, as described with reference to Figures 2-8, proposes an AI-based time-domain beam / CSI prediction mechanism. This solution significantly reduces the signaling overhead and delay associated with RRC / MAC-CE / DCI signaling for setting up or activating periodic or semi-persistent reporting CSI reports / resources.

[0114] Next, we refer to Figure 9, which is a flowchart of an exemplary method 900 relating to some embodiments of the present disclosure. Method 900 can be implemented in a terminal device 110 as shown in Figure 1. Method 900 may include additional blocks not shown and / or some of the illustrated blocks may be omitted, and it should be understood that the scope of the present disclosure is not limited in this respect.

[0115] In 910, the terminal device receives from the network device a Channel State Information (CSI) report configuration that includes at least information relating to at least one of the following: the network device's collection procedure for collecting one or more CSI reports collected from the terminal device, or the network device's inference procedure for inferring one or more CSIs based on the collected CSI reports.

[0116] In 920, the terminal device transmits the CSI report based on the information, wherein the CSI report includes at least one of a periodic CSI report, a semi-permanent CSI report, and a first type of CSI report.

[0117] In some embodiments, the information indicates at least one of a first duration, the second duration, or the third duration, which includes a second duration during which the collection procedure is performed by the network device and a third duration during which the inference procedure is performed by the network device.

[0118] In some embodiments, the second duration and the third duration do not overlap with each other, or at least partially overlap.

[0119] In some embodiments, the settings are received via at least one of wireless resource control signaling, media access control elements, or downlink control information.

[0120] In some embodiments, the method further includes receiving instructions from the network device for the first duration offset and the duration of the first duration.

[0121] In some embodiments, the instructions are received via at least one of the following: wireless resource control signaling, media access control elements, or downlink control information.

[0122] In some embodiments, the method further includes determining the offset of the first duration and the duration of the first duration based on the start point and duration associated with the CSI report.

[0123] In some embodiments, the method further includes ensuring that the terminal device does not report the CSI report within the third duration.

[0124] In some embodiments, the information represents a first number associated with the collection procedure and a second number associated with the inference procedure, wherein the first number is the number of sequential CSI reports used as input data for the inference procedure, and the second number is the number of prediction results output in the inference procedure.

[0125] In some embodiments, the method further includes determining which CSI reports to drop based on the first number and the second number.

[0126] In some embodiments, the method further includes determining a target frame number and a target slot number within the target frame based on the first number and the second number, and determining the CSI report to be dropped based on the target frame number and the target slot number.

[0127] In some embodiments, the method further includes receiving instructions from the network device via radio resource control signaling that the CSI report is set as the first type of CSI report, that the first type of CSI report is a discontinuous periodic type of CSI report, or that the CSI report is released from the first type of CSI report.

[0128] In some embodiments, the method further includes receiving an instruction from the network device, via at least one of media access control elements or downlink control information, that the CSI report be activated as the first type of CSI report or deactivated from the first type of CSI report, wherein the first type of CSI report is a discontinuous periodic type CSI report.

[0129] In some embodiments, downlink control information is scrambled by discontinuous periodic CSI radio network transient identities.

[0130] In some embodiments, the method further includes occupying the central processing unit of the terminal device during the second duration, or releasing the central processing unit of the terminal device during the third duration.

[0131] In some embodiments, the method further includes freeing the central processing unit of the terminal device for the CSI report determined based on the first number and the second number.

[0132] In some embodiments, the method further includes freeing the central processing unit of the terminal device for the CSI report determined based on the target frame number and the target slot number.

[0133] In some embodiments, the method further includes omitting one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report within the third duration, or preventing the terminal device from receiving a CSI reference signal for channel measurement from the first symbol after the uplink channel carrying the most recent CSI report to the last symbol before the CSI reference resource corresponding to the CSI report within the third duration.

[0134] In some embodiments, the method further includes omitting one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report determined based on the first number and the second number, or preventing the terminal device from receiving a CSI reference signal for channel measurement from the first symbol after the uplink channel carrying the most recent CSI report to the last symbol before the CSI reference resource corresponding to the CSI report determined based on the first number and the second number.

[0135] In some embodiments, the method further includes omitting one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report determined based on the target frame number and the target slot number, or preventing the terminal device from receiving a CSI reference signal for channel measurement from the first symbol after the uplink channel carrying the most recent CSI report to the last symbol before the CSI reference resource corresponding to the CSI report determined based on the target frame number and the target slot number.

[0136] In some embodiments, the third duration is shorter than a threshold duration shorter than 1280 ms.

[0137] In some embodiments, the time interval between the CSI report and the latest CSI-RS may be shorter than 1280 ms.

[0138] In some embodiments, the method further includes determining that a CSI reference signal is inactive for a duration from the first symbol after the uplink channel carrying the most recent CSI report to the last symbol before the CSI reference resource corresponding to the CSI report associated with the CSI reference signal.

[0139] In some embodiments, the method further includes reporting the CSI report associated with the information in accordance with the determination that the CSI report associated with the information has conflicted with another CSI report not associated with the information.

[0140] In some embodiments, the method further comprises reporting the CSI report upon determination that the CSI report is set as the first type of CSI report and that the CSI report has conflicted with another CSI report set as a periodic or semi-permanent type CSI report, wherein the first type of CSI report is a discontinuous periodic type CSI report.

[0141] In some embodiments, the method further includes receiving a control command from the network device indicating that the artificial intelligence or machine learning function has been activated, and the collection procedure and the inference procedure are performed by the artificial intelligence or machine learning function.

[0142] In some embodiments, the method further includes reporting to the network device the capabilities of one or more of the terminal devices, including the maximum duration of the collection procedure and the inference procedure permitted to be supported by the terminal device, the maximum duration of the collection procedure permitted to be supported by the terminal device, the maximum duration of the inference procedure permitted to be supported by the terminal device, the maximum value for a first number associated with the collection procedure permitted to be supported by the terminal device, or the maximum value for a second number associated with the inference procedure permitted to be supported by the terminal device.

[0143] In some embodiments, the terminal device includes a terminal device, and the network device includes a network device.

[0144] Next, we refer to Figure 10, a flowchart of an exemplary method 1000 relating to some embodiments of the present disclosure. Method 1000 can be implemented in a network device 120 as shown in Figure 1. Method 1000 may include additional blocks not shown and / or some of the illustrated blocks may be omitted, and it should be understood that the scope of the present disclosure is not limited in this respect.

[0145] In 1010, the network device determines the settings for a Channel State Information (CSI) report that includes at least information relating to at least one of the following: a collection procedure for the network device for collecting one or more CSI reports collected from the terminal device, or an inference procedure for the network device for inferring one or more CSIs based on the collected CSI reports.

[0146] In 1020, the network device sends this setting to the terminal device.

[0147] In some embodiments, the information indicates at least one of a first duration, the second duration, or the third duration, which includes a second duration during which the collection procedure is performed by the network device and a third duration during which the inference procedure is performed by the network device.

[0148] In some embodiments, the second duration and the third duration do not overlap with each other, or at least partially overlap.

[0149] In some embodiments, the information represents a first number associated with the collection procedure and a second number associated with the inference procedure, wherein the first number is the number of sequential CSI reports used as input data for the inference procedure, and the second number is the number of prediction results output in the inference procedure.

[0150] In some embodiments, the method further includes determining the setting based on the capabilities of one or more terminal devices, including the maximum duration of the collection procedure and the inference procedure permitted to be supported by the terminal device, the maximum duration of the collection procedure permitted to be supported by the terminal device, the maximum duration of the inference procedure permitted to be supported by the terminal device, the maximum value for a first number associated with the collection procedure permitted to be supported by the terminal device, or the maximum value for a second number associated with the inference procedure permitted to be supported by the terminal device.

[0151] In some embodiments, the settings are transmitted via at least one of wireless resource control signaling, media access control elements, or downlink control information.

[0152] In some embodiments, the method further includes transmitting to the terminal device an instruction for the offset of the first duration and the duration of the first duration.

[0153] In some embodiments, the instructions are transmitted via at least one of wireless resource control signaling, media access control elements, or downlink control information.

[0154] In some embodiments, the method further includes transmitting to the terminal device via radio resource control signaling an instruction that the CSI report is set as the first type of CSI report, that the first type of CSI report is a discontinuous periodic type of CSI report, or that the CSI report is released from being the first type of CSI report.

[0155] In some embodiments, the method further includes transmitting to the terminal device, via at least one of media access control elements or downlink control information, an instruction that the CSI report is to be activated as the first type of CSI report or deactivated from the first type of CSI report, wherein the first type of CSI report is a discontinuous periodic type CSI report.

[0156] In some embodiments, downlink control information is scrambled by discontinuous periodic CSI radio network transient identities.

[0157] In some embodiments, the method further includes transmitting a control command to the terminal device indicating that the artificial intelligence or machine learning function has been enabled, and the collection procedure and the inference procedure are performed by the artificial intelligence or machine learning function.

[0158] Details regarding the time-domain CSI prediction relating to this disclosure have already been described with reference to Figures 2 to 10. Next, exemplary implementations of the terminal device 110 will be described below. In some embodiments, the terminal device 110 includes a circuit, the circuit is

[0159] In some embodiments, the terminal device 110 includes a circuit which is configured to receive a Channel State Information (CSI) report configuration from a network device which includes at least information relating to at least one of the following: a network device collection procedure for collecting one or more CSI reports collected from the terminal device, or a network device inference procedure for inferring one or more CSIs based on the collected CSI reports, and to transmit the CSI reports based on the information which include at least one of periodic CSI reports, semi-persistent CSI reports, and first type CSI reports.

[0160] In some embodiments, the information indicates at least one of a first duration, the second duration, or the third duration, which includes a second duration during which the collection procedure is performed by the network device and a third duration during which the inference procedure is performed by the network device.

[0161] In some embodiments, the second duration and the third duration do not overlap with each other, or at least partially overlap.

[0162] In some embodiments, the settings are received via at least one of wireless resource control signaling, media access control elements, or downlink control information.

[0163] In some embodiments, the terminal device 110 includes a circuit configured to receive instructions from the network device for the first duration offset and the duration of the first duration.

[0164] In some embodiments, the instructions are received via at least one of the following: wireless resource control signaling, media access control elements, or downlink control information.

[0165] In some embodiments, the terminal device 110 includes a circuit configured to determine the offset of the first duration and the duration of the first duration based on the start point and duration associated with the CSI report.

[0166] In some embodiments, the terminal device 110 includes a circuit configured to prevent the terminal device from reporting the CSI report within the third duration.

[0167] In some embodiments, the information represents a first number associated with the collection procedure and a second number associated with the inference procedure, wherein the first number is the number of sequential CSI reports used as input data for the inference procedure, and the second number is the number of prediction results output in the inference procedure.

[0168] In some embodiments, the terminal device 110 includes a circuit configured to determine which CSI reports are dropped based on the first number and the second number.

[0169] In some embodiments, the terminal device 110 includes a circuit configured to determine a target frame number and a target slot number within a target frame based on the first number and the second number, and to determine which CSI report to drop based on the target frame number and the target slot number.

[0170] In some embodiments, the terminal device 110 includes a circuit configured to receive instructions from the network device via wireless resource control signaling indicating that the CSI report is set as the first type of CSI report, that the first type of CSI report is a discontinuous periodic type of CSI report, or that the CSI report is released from the first type of CSI report.

[0171] In some embodiments, the terminal device 110 includes a circuit configured to receive instructions from the network device, via at least one of media access control elements or downlink control information, that the CSI report be activated as the first type of CSI report or deactivated from the first type of CSI report, wherein the first type of CSI report is a discontinuous periodic type CSI report.

[0172] In some embodiments, downlink control information is scrambled by discontinuous periodic CSI radio network transient identities.

[0173] In some embodiments, the terminal device 110 includes a circuit configured to either occupy the terminal device's central processing unit during a second duration or to release the terminal device's central processing unit during a third duration.

[0174] In some embodiments, the terminal device 110 includes a circuit configured to release the central processing unit of the terminal device for the CSI report determined based on the first number and the second number.

[0175] In some embodiments, the terminal device 110 includes a circuit configured to release the central processing unit of the terminal device for the CSI report determined based on the target frame number and the target slot number.

[0176] In some embodiments, the terminal device 110 includes a circuit configured to omit one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report within the third duration, or to prevent the terminal device from receiving a CSI reference signal for channel measurement from the first symbol after the uplink channel carrying the latest CSI report to the last symbol before the CSI reference resource corresponding to the CSI report within the third duration.

[0177] In some embodiments, the terminal device 110 includes a circuit configured to omit one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report determined based on the first number and the second number, or to prevent the terminal device from receiving a CSI reference signal for channel measurement from the first symbol after the uplink channel carrying the most recent CSI report until the last symbol before the CSI reference resource corresponding to the CSI report determined based on the first number and the second number.

[0178] In some embodiments, the terminal device 110 includes a circuit which is configured to omit one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report determined based on the target frame number and the target slot number, or to prevent the terminal device from receiving a CSI reference signal for channel measurement from the first symbol after the uplink channel carrying the most recent CSI report to the last symbol before the CSI reference resource corresponding to the CSI report determined based on the target frame number and the target slot number.

[0179] In some embodiments, the third duration is shorter than a threshold duration shorter than 1280 ms.

[0180] In some embodiments, the time interval between the CSI report and the latest CSI-RS may be shorter than 1280 ms.

[0181] In some embodiments, the terminal device 110 includes a circuit configured to determine that a CSI reference signal is inactive for a duration from the first symbol after the uplink channel carrying the most recent CSI report to the last symbol before the CSI reference resource corresponding to the CSI report associated with the CSI reference signal.

[0182] In some embodiments, the terminal device 110 includes a circuit configured to perform reporting of the CSI report based on the information, in accordance with the determination that a CSI report configured to have the information has conflicted with another CSI report configured to have the information.

[0183] In some embodiments, the terminal device 110 includes a circuit configured to perform reporting of the CSI report upon determination that the CSI report is set as the first type of CSI report and has conflicted with another CSI report set as the first type of CSI report, the first type of CSI report being a discontinuous periodic type CSI report.

[0184] In some embodiments, the terminal device 110 includes a circuit configured to receive a control command from the network device indicating that the artificial intelligence or machine learning function has been activated, and the collection procedure and the inference procedure are executed by the artificial intelligence or machine learning function.

[0185] In some embodiments, the terminal device 110 includes a circuit configured to report to the network device one or more capabilities of the terminal device, including the maximum duration of the collection procedure and the inference procedure permitted to be supported by the terminal device, the maximum duration of the collection procedure permitted to be supported by the terminal device, the maximum duration of the inference procedure permitted to be supported by the terminal device, the maximum value for a first number associated with the collection procedure permitted to be supported by the terminal device, or the maximum value for a second number associated with the inference procedure permitted to be supported by the terminal device.

[0186] Next, exemplary implementations of the network device 120 will be described below. In some embodiments, the network device 120 includes a circuit which determines a Channel State Information (CSI) report setting that indicates at least one of the following: a collection procedure of the network device for collecting one or more CSI reports collected from the terminal device, or an inference procedure of the network device for inferring one or more CSIs based on the collected CSI reports, and is configured to transmit the setting to the terminal device.

[0187] In some embodiments, the information indicates at least one of a first duration, the second duration, or the third duration, which includes a second duration during which the collection procedure is performed by the network device and a third duration during which the inference procedure is performed by the network device.

[0188] In some embodiments, the second duration and the third duration do not overlap with each other, or at least partially overlap.

[0189] In some embodiments, the information represents a first number associated with the collection procedure and a second number associated with the inference procedure, wherein the first number is the number of sequential CSI reports used as input data for the inference procedure, and the second number is the number of prediction results output in the inference procedure.

[0190] In some embodiments, the network device 120 includes a circuit which is configured to determine the settings based on the capabilities of one or more of the terminal devices, including the maximum duration of the collection procedure and the inference procedure permitted to be supported by the terminal device, the maximum duration of the collection procedure permitted to be supported by the terminal device, the maximum duration of the inference procedure permitted to be supported by the terminal device, the maximum value for a first number associated with the collection procedure permitted to be supported by the terminal device, or the maximum value for a second number associated with the inference procedure permitted to be supported by the terminal device.

[0191] In some embodiments, the settings are transmitted via at least one of wireless resource control signaling, media access control elements, or downlink control information.

[0192] In some embodiments, the network device 120 includes a circuit configured to transmit instructions to the terminal device for the first duration offset and the duration of the first duration.

[0193] In some embodiments, the instructions are transmitted via at least one of wireless resource control signaling, media access control elements, or downlink control information.

[0194] In some embodiments, the network device 120 includes a circuit configured to transmit to the terminal device via radio resource control signaling an instruction that the CSI report is set as the first type of CSI report, that the first type of CSI report is a discontinuous periodic type of CSI report, or that the CSI report is released from the first type of CSI report.

[0195] In some embodiments, the network device 120 includes a circuit configured to send an instruction to the terminal device via at least one of media access control elements or downlink control information that the CSI report is activated as the first type of CSI report or deactivated from the first type of CSI report, the first type of CSI report being a discontinuous periodic type CSI report.

[0196] In some embodiments, downlink control information is scrambled by discontinuous periodic CSI radio network transient identities.

[0197] In some embodiments, the network device 120 includes a circuit configured to send a control command to the terminal device indicating that the artificial intelligence or machine learning function has been enabled, and the collection procedure and the inference procedure are executed by the artificial intelligence or machine learning function.

[0198] Figure 11 is a schematic block diagram of a device 1100 suitable for implementing an embodiment of the present disclosure. The device 1100 can be considered as another exemplary embodiment of the terminal device 110 or network device 120 shown in Figure 1. Therefore, the device 1100 may be implemented in or as part of the terminal device 110 or network device 120.

[0199] As illustrated, the device 1100 comprises a processor 1110, a memory 1120 coupled to the processor 1110, appropriate transmitters (TX) and receivers (RX) 1140 coupled to the processor 1110, and a communication interface coupled to the TX / RX 1140. The memory 1110 stores at least a portion of the program 1130. The TX / RX 1140 is used for bidirectional communication. The TX / RX 1140 has at least one antenna to facilitate communication, although the access node referred to herein may actually have multiple antennas. The communication interface may represent any interface necessary for communication with other network elements, such as an X2 interface for bidirectional communication between eNBs, an S1 interface for communication between a mobility management entity (MME) / serving gateway (S-GW) and an eNB, an Un interface for communication between an eNB and a relay node (RN), or a Uu interface for communication between an eNB and a terminal device.

[0200] It is assumed that program 1130 includes program instructions that, when executed by the associated processor 1110, enable the device 1100 to operate according to embodiments of the present disclosure, as described herein with reference to Figures 2A to 6. Embodiments of the present disclosure may be implemented by computer software executable by the processor 1110 of the device 1100, by hardware, or by a combination of software and hardware. The processor 1110 may be configured to implement various embodiments of the present disclosure. Furthermore, a combination of the processor 1110 and memory 1120 may form processing means 1150 suitable for implementing various embodiments of the present disclosure.

[0201] Memory 1120 may be of any type suitable for a local technology network and may be implemented using any suitable data storage technology, such as non-temporary computer-readable storage media, semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. Although only one memory 1120 is shown in device 1100, several physically different memory modules may be present in device 1100. Processor 1110 may be of any type suitable for a local technology network and may include, as non-limiting examples, one or more of general-purpose computers, dedicated computers, microprocessors, digital signal processors (DSPs), and processors based on multicore processor architectures. Device 1100 may have multiple processors, for example, application-specific integrated circuit chips that are temporally dependent on a clock that synchronizes the main processor.

[0202] Overall, various embodiments of the Disclosure may be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some embodiments may be implemented in hardware, while others may be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. Although various embodiments of the Disclosure are illustrated and described using block diagrams, flowcharts, or any other pictorial representation, it should be understood that any blocks, devices, systems, techniques, or methods described herein may be implemented, in non-limiting examples, in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or any combination thereof.

[0203] This disclosure also provides at least one computer program product tangibly stored on a non-temporary computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions contained in a program module, which are executed within a device on a target real or virtual processor to perform the processes or methods described above with reference to Figures 2 to 5. Generally, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform a specific task or realize a specific abstract data type. In various embodiments, the functions of program modules may be combined or separated among program modules as needed. The machine-executable instructions of a program module may be executed within a local or distributed device. In a distributed device, program modules may reside in both local and remote storage media.

[0204] Program code for performing the methods of this disclosure may be written in any combination of one or more programming languages. These program codes are provided to a processor or controller of a general-purpose computer, a dedicated computer, or other programmable data processing device, and when executed by the processor or controller, the program code implements the functions / operations specified in the flowcharts and / or block diagrams. The program code may run entirely on a machine, partially on a machine, as an independent software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0205] The program code described above may be implemented on a machine-readable medium, which may be any tangible medium that can contain or store programs used by or associated with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the aforementioned mediums. More specific examples of machine-readable storage media may include electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0206] While the operations have been described in a specific order, it should not be understood that, in order to obtain the desired results, these operations must be performed in a specific order or sequential order, or that all illustrated operations must be performed. In some cases, multitasking and parallel processing may be advantageous. Similarly, while some specific implementation details are included in the above discussion, these should not be interpreted as limitations on the scope of this disclosure, but rather as descriptions of features that may be specific to a particular embodiment. Some features described in the context of individual embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may be implemented separately or in any suitable subcombination in multiple embodiments.

[0207] While this disclosure has been described in language specific to structural features and / or methodological behavior, it should be understood that the disclosure as defined in the attached claims is not necessarily limited to the specific features or behaviors described above. Rather, the specific features and behaviors described above are disclosed as exemplary forms of implementing the claims.

Claims

1. A collection procedure for a network device to collect one or more CSI reports collected from terminal devices, or An inference procedure for the network device for inferring one or more CSIs based on one or more collected CSI reports, The terminal device receives from the network device a setting for a Channel State Information (CSI) report that indicates at least one of the following: This includes transmitting the CSI report based on the aforementioned information, The CSI report includes at least one of the following: a periodic CSI report, a semi-permanent CSI report, and a first type of CSI report. method.

2. The aforementioned information is, A first duration including a second duration during which the collection procedure is performed by the network device and a third duration during which the inference procedure is performed by the network device. The second duration, or The third duration, The method according to claim 1, which shows at least one of the following.

3. Sending the CSI report based on the aforementioned information is: The terminal device shall not report the CSI report within the third duration, The method according to claim 2, including the method described in claim 2.

4. The information includes a first number associated with the collection procedure and a second number associated with the inference procedure, wherein the first number is the number of continuous CSI reports used as input data for the inference procedure, and the second number is the number of prediction results output in the inference procedure. The method according to claim 1.

5. Based on the first number and the second number, determine which CSI reports to drop. The method according to claim 4, further comprising:

6. Occupying the central processing unit of the terminal device during the second duration, or To release the central processing unit of the terminal device within the third duration, The method according to claim 2, further comprising:

7. With respect to the CSI report determined based on the first number and the second number, the central processing unit of the terminal device shall be released. The method according to claim 5, further comprising:

8. Omitting one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report within the third duration, or From the first symbol after the uplink channel carrying the latest CSI report to the last symbol before the CSI reference resource corresponding to the CSI report within the third duration, the terminal device shall not receive the CSI reference signal for channel measurement. The method according to claim 2, further comprising:

9. Omitting one or more CSI reference signal resources for channel measurement within the most recent CSI reference signal opportunity prior to the CSI reference resource corresponding to the CSI report determined based on the first number and the second number, or The terminal device shall not receive a CSI reference signal for channel measurement from the first symbol after the uplink channel carrying the latest CSI report to the last symbol before the CSI reference resource corresponding to the CSI report determined based on the first and second numbers. The method according to claim 5, further comprising:

10. The third duration is shorter than a threshold duration shorter than 1280 ms. The method according to claim 2.

11. The time interval between the CSI report and the latest CSI reference signal is shorter than 1280 ms, and the latest CSI reference signal is the latest CSI reference signal associated with the CSI report. The method according to claim 8 or 9.

12. To report the CSI report associated with the information in accordance with the determination that the CSI report associated with the information has conflicted with another CSI report not associated with the information, The method according to claim 1, further comprising:

13. The maximum duration of the collection procedure and the inference procedure permitted to be supported by the terminal device, The maximum duration of the collection procedure permitted to be supported by the terminal device, The maximum duration of the inference procedure permitted to be supported by the terminal device, The maximum value of the first number associated with the collection procedure permitted to be supported by the terminal device, or The maximum value for a second number associated with the inference procedure permitted to be supported by the terminal device, Reporting the capabilities of one or more of the terminal devices to the network device, including, The method according to claim 1, further comprising:

14. In network devices, A collection procedure for a network device based on one or more collected CSI reports for collecting one or more CSI reports collected from a terminal device, or Determining the settings for a Channel State Information (CSI) report that shows at least one of the inference procedures of the network device for inferring one or more CSIs based on one or more collected CSI reports, The above settings are transmitted to the terminal device, A method that includes this.

15. A terminal device equipped with a processor, The aforementioned processor, From the network device, A collection procedure for the network device for collecting one or more CSI reports collected from the terminal device, or The network device receives a Channel State Information (CSI) report configuration that includes at least information relating to at least one of the inference procedures for the network device to infer one or more CSIs based on one or more collected CSI reports, The system is configured to transmit the CSI report based on the aforementioned information, and the CSI report includes at least one of the following: a periodic CSI report, a semi-permanent CSI report, and a first type of CSI report. Terminal device.

Images