Communication method and communication device

Abstract

The embodiments of the present disclosure relate to a method, an apparatus, and a computer-readable medium for communication. According to the embodiments of the present disclosure, a terminal device receives downlink information for triggering a report from a network device. The terminal device determines whether an estimation failure occurs in a data processing model. The terminal device transmits a report to the network device. The report indicates whether an estimation failure occurs in the data processing model and / or whether information in the report is generated based on the data processing model. In this way, the network device can be informed of the estimation failure and the accuracy of information transmitted from the terminal device can be improved.

Description

[Technical field]

[0001] TECHNICAL FIELD Embodiments of the present disclosure relate generally to the field of telecommunications, and more particularly to methods, apparatus and computer-readable media for communications. [Background technology]

[0002] Several techniques have been proposed to improve communication performance. For example, communication devices can utilize artificial intelligence / machine learning (AI / ML) models to improve communication quality. AI / ML models can be applied to various scenarios to achieve better performance. Summary of the Invention [Problem to be solved by the invention]

[0003] Generally, the exemplary embodiments of the present disclosure provide a solution for communication. [Means for solving the problem]

[0004] In a first aspect, a communication method is provided, the communication method including: receiving, in a terminal device, downlink information for triggering a report from a network device; determining, in the terminal device, whether an estimation failure occurs in a data processing model; and sending a report to the network device. The report at least indicates whether an estimation failure occurs in the data processing model.

[0005] In a second aspect, a communication method is provided, the communication method including: in a network device, sending downlink information for triggering a report to a terminal device, and receiving a report from the terminal device, the report indicating at least whether an estimation failure occurs in a data processing model.

[0006] In a third aspect, a terminal device is provided. The terminal device includes a processor unit and a memory coupled to the processor unit and having instructions stored therein. The instructions, when executed by the processor unit, cause the terminal device to perform operations. The operations include receiving downlink information for triggering a report from a network device, determining in the terminal device whether an estimation failure has occurred in the data processing model, and sending a report to the network device. The report at least indicates whether an estimation failure has occurred in the data processing model.

[0007] In a fourth aspect, a network device is provided. The network device includes a processor unit and a memory coupled to the processor unit and having instructions stored therein. The instructions, when executed by the processor unit, cause the network device to perform operations. The operations include transmitting downlink information to a terminal device for triggering a report and receiving a report from the terminal device. The report indicates at least whether an estimation failure has occurred in the data processing model.

[0008] In a fifth aspect, there is provided a computer readable medium having stored thereon instructions which, when executed on at least one processor, cause the at least one processor to perform a method according to the first or second aspect.

[0009] Other features of the present disclosure will become readily apparent 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 from the following detailed description of some exemplary embodiments of the present disclosure in the accompanying drawings.

[0011] [Figure 1] FIG. 1 is a schematic diagram of a communication environment in which embodiments of the present disclosure may be implemented.

[0012] [Diagram 2] 1 illustrates a signaling flow of communication according to some embodiments of the present disclosure.

[0013] [Figure 3A] 1A and 1B each show a schematic diagram of AI / ML-based beam management in accordance with some embodiments of the present disclosure. [Figure 3B] 1A and 1B each show a schematic diagram of AI / ML-based beam management in accordance with some embodiments of the present disclosure. [Figure 3C] 1A and 1B each show a schematic diagram of AI / ML-based beam management in accordance with some embodiments of the present disclosure. [Figure 3D] 1A and 1B each show a schematic diagram of AI / ML-based beam management in accordance with some embodiments of the present disclosure. [Figure 3E] 1A and 1B each show a schematic diagram of AI / ML-based beam management in accordance with some embodiments of the present disclosure.

[0014] [Figure 4A] 1A and 1B each illustrate a schematic diagram of AI / ML-based channel state information (CSI) feedback according to some embodiments of the present disclosure. [Figure 4B] 1A and 1B each illustrate a schematic diagram of AI / ML-based channel state information (CSI) feedback according to some embodiments of the present disclosure.

[0015] [Diagram 5] 1 illustrates a schematic diagram of an AI / ML-based demodulation reference signal (DMRS) according to some embodiments of the present disclosure.

[0016] [Figure 6] 1 illustrates a schematic diagram of AI / ML-based demodulation CSI-RS in accordance with some embodiments of the present disclosure.

[0017] [Figure 7] 1 is a flow chart of an exemplary method according to an embodiment of the present disclosure.

[0018] [Figure 8] 1 is a flow chart of an exemplary method according to an embodiment of the present disclosure.

[0019] [Figure 9] FIG. 1 is a schematic block diagram of an apparatus suitable for practicing embodiments of the present disclosure.

[0020] Throughout the drawings, the same or similar reference numbers represent the same or similar elements. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] The principles of the present disclosure will be described with reference to some exemplary embodiments. It should be understood that these embodiments are merely described for illustrative purposes to aid those skilled in the art in understanding and implementing the present disclosure, and do not imply any limitations on the scope of the present disclosure. The present disclosure described herein can be implemented in a variety of ways other than those described below.

[0022] In the following description and claims, unless defined otherwise, all technical and scientific terms used have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0023] In this specification, 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, cell 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, vehicle-mounted devices for V2X communication (where X means pedestrian, vehicle or infrastructure / network), devices for Integrated Access and Backhaul (IAB), spacecraft or aircraft in Non-Terrestrial Networks (NTN) including High Altitude Platforms (HAP) and satellites, including Unmanned Aerial Systems (UAS), and Extended Reality (XR) including different types of reality such as Augmented Reality (AR), Mixed Reality (MR), and Virtual Reality (VR). Examples of such devices include, but are not limited to, a Reality (UE) device, an unmanned aerial vehicle (UAV) that does not require a human pilot, commonly known as a drone, a device on a high speed train (HST), an imaging device such as a digital camera, a sensor, a gaming device, a music storage and playback device, or an Internet device that allows wireless or wired Internet access and browsing. A "terminal device" may also 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 communication, and IoT applications. Also, one or more subscriber identity modules (SIMs) may be incorporated, known as multi-SIM. The term "terminal device" may be used interchangeably with UE, mobile station, subscriber equipment, mobile terminal, user terminal, or wireless device. In the following description, the terms "terminal device", "communication device", "terminal", "user terminal", and "UE" may be used interchangeably.

[0024] A terminal device or a network device may have an artificial intelligence (AI) or machine learning function, which generally includes a model that can be used to learn from a large amount of data collected for a specific function and predict some information.

[0025] The terminal device or network device may function in multiple frequency ranges, e.g., FR1 (410 MHz-7125 MHz), FR2 (24.25 GHz-71 GHz), higher than 100 GHz, Terahertz (THz), etc. Furthermore, it can function in licensed / unlicensed / shared spectrum. The terminal device may have multiple connections with the network device in a multi-radio dual connectivity (MR-DC) application scenario. The terminal device or network device can function in full duplex, flexible duplex, and cross division duplex modes.

[0026] The term "network device" refers to a device capable of providing or hosting a cell or coverage through which terminal devices can communicate. Examples of network devices include, but are not limited to, a Node B (NodeB or NB), an Evolved Node B (eNodeB or eNB), a next generation Node B (gNB), a transmit / receive point (TRP), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS), etc.

[0027] In one embodiment, the terminal device may be connected to a first network device and a second network device. One of the first network device and the second network device may be a master node, and the other may be a secondary node. The first network device and the second network device may use different radio access technologies (RATs). In one embodiment, the first network device may be a first RAT device, and the second network device may be a second RAT device. In one embodiment, the first RAT device is an eNB, and the second RAT device is a gNB. Information related to the different RATs may be transmitted to the terminal device from at least one of the first network device and the second network device. In one embodiment, the first information may be transmitted from the first network device to the terminal device, and the second information may be transmitted from the second network device directly to the terminal device or via the first network device. In one embodiment, information related to the configuration of the terminal device set by the second network device may be transmitted from the second network device via the first network device. Information related to the reconfiguration of the terminal device set by the second network device may be transmitted from the second network device directly to the terminal device or via the first network device.

[0028] Communications discussed herein may conform to any suitable standard, including, but not limited to, New Radio Access (NR), Long Term Evolution (LTE), LTE Evolution (LTE-Evolution), LTE Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), cdma2000, Global System for Mobile Communications (GSM), and the like. Furthermore, communications may be performed according to any currently known or future developed generation of communications protocols. Examples of communications protocols include, but are not limited to, first generation (1G), second generation (2G), 2.5G, 2.85G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G), and sixth generation (6G) communications protocols. The techniques described herein may be used for the above wireless networks and radio technologies as well as other wireless networks and radio technologies. The embodiments of the present disclosure may be performed according to any generation of communication protocols now known or 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.

[0029] As used herein, the term "circuitry" may refer to hardware circuits and / or combinations of hardware circuits and software. For example, a circuit may be a combination of analog and / or digital hardware circuits and software / firmware. As a further example, a circuit may be any portion of a hardware processor with software, such as a digital signal processor, software, and memory that work together to perform various functions on a device, such as a terminal device or a network device. In yet another example, a circuit may be a hardware circuit and / or processor, such as a microprocessor or a portion of a microprocessor, that requires software / firmware for operation, but the software may not be present when not required for operation. As used herein, the term circuitry also encompasses merely a hardware circuit or processor, or a portion of a hardware circuit or processor, and its (or their) accompanying software and / or firmware implementations.

[0030] As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. The term "comprises" and variations thereof are intended to be open ended, meaning "including, but not limited to." The term "based on" is intended to mean "based at least in part on." The terms "one embodiment" and "one embodiment" are intended to mean "at least one embodiment." The term "another embodiment" is intended to mean "at least one other embodiment." Terms such as "first," "second," and the like may refer to different objects or the same object. The following content may include other definitions, both explicit and implicit.

[0031] In some instances, values, procedures, or devices are referred to as "optimum," "lowest," "highest," "minimum," "maximum," etc. It is understood that such descriptions are intended to indicate choices among multiple functional alternatives that may be used, and that such choices are not necessarily better, smaller, higher, or more preferred than other choices.

[0032] As described above, the AI / ML model can be applied to various scenarios to achieve better performance. In some embodiments, the AI / ML model can be implemented on the network device side. Alternatively, the AI / ML model can be implemented on the terminal device side. In other embodiments, the AI / ML model can be implemented on both the network device and the terminal device.

[0033] For example, the terminal device can perform beam management in an AI / ML model. In this case, the terminal device can measure a portion of the candidate beam pairs and estimate the quality of all candidate beam pairs using AI or ML. Massive MIMO (mMIMO) and beamforming are widely used in the communications industry. The terms "beamforming" and "mMIMO" are sometimes used interchangeably. In general, beamforming uses multiple antennas to control the direction of the wavefront by appropriately weighting the magnitude and phase of the signal of each antenna in an array of multiple antennas. In the most general definition, mMIMO is a system in which the number of antennas exceeds the number of users. In 5G, coverage is beam-based rather than cell-based. There is no cell-level reference channel against which the coverage of a cell can be measured. Instead, each cell has one or more synchronization signal block beams (SSB). SSB beams are static or semi-static and always point in the same direction. The SSB beams form a grid of beams that cover the entire cell. The user equipment (UE) searches for and measures the beams and maintains a set of candidate beams. The candidate set of beams may include beams from multiple cells. With 5G mmWave, which allows for directional communication with more antenna elements and provides additional beamforming gain, efficient beam management becomes crucial, where the UE and gNB periodically identify the best beam on which to operate at a given time.

[0034] Furthermore, the terminal device can perform CSI feedback based on the AI / ML model. In this situation, the original CSI information can be compressed by an AI encoder located in the terminal device and restored by an AI decoder located in the network device. The AI / ML model can also be used to reduce reference signal (RS) overhead. For example, the terminal device can use new RS patterns, such as low density DMRS, fewer CSI-RS ports, etc.

[0035] However, inference failures may occur in AI / ML models. As used herein, the term "inference failure" may refer to a situation in which an AI / ML model cannot operate normally to obtain an inference result. Therefore, it is important to inform the network device of the inference failure.

[0036] In an embodiment, a solution for improving an AI / ML model is proposed. According to an embodiment of the present disclosure, a terminal device receives downlink information for triggering a report from a network device. The terminal device determines whether an estimation failure occurs in a data processing model. The terminal device sends a report to the network device. The report indicates whether an estimation failure occurs in the data processing model and / or whether the information in the report is generated based on the data processing model. In this way, the network device can be informed about the estimation failure, and the accuracy of the information sent from the terminal device can be improved.

[0037] 1 shows a schematic diagram of a communication system in which embodiments of the present disclosure can be implemented. The communication system 100, which is part of a communication network, includes terminal devices 110-1, 110-2, ..., 110-N, which may be collectively referred to as "terminal devices 110." The number N may be any suitable integer. The terminal devices 110 may communicate with each other.

[0038] The communication system 100 further includes a network device. In the communication system 100, the network device 120 and the terminal device 110 can communicate data and control information with each other. The number of terminal devices shown in FIG. 1 is provided for illustrative purposes and is not intended to imply any limitation.

[0039] Communications in the communication system 100 may be implemented according to any suitable communication protocol, including, but not limited to, cellular communication protocols such as first generation (1G), second generation (2G), third generation (3G), fourth generation (4G), and fifth generation (5G), wireless local network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocols now known or developed in the future. Furthermore, communications may utilize any suitable wireless communication technology, including, but not limited to, code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), frequency division duplex (FDD), time division duplex (TDD), multiple-input multiple-output (MIMO), orthogonal frequency division multiple access (OFDMA), and / or any other technology now known or developed in the future.

[0040] The embodiments of the present disclosure may be applied to any suitable scenario. For example, the embodiments of the present disclosure may be implemented in a low-capability NR device. Alternatively, the embodiments of the present disclosure may be implemented in any of the following: New Radio (NR) multiple-input and multiple-output (MIMO), NR Sidelink Enhancements, NR systems at frequencies above 52.6 GHz, NR operation extension to 71 GHz, narrow band-Internet of Things (NB-IoT) / enhanced Machine Type Communication (eMTC) in non-terrestrial networks (NTN), NTN, UE power saving enhancements, NR coverage extension, NB-IoT and LTE-MTC, Integrated Access and Backhaul (IAB), NR multicast and broadcast services, or enhanced multi-radio dual connectivity.

[0041] As used herein, the term "slot" refers to a dynamic scheduling unit. A slot contains a predetermined number of symbols. The term "downlink (DL) subslot" may refer to a virtual subslot built on an uplink (UL) subslot. A DL subslot may contain fewer symbols than a DL slot. A slot may refer to a regular slot containing a predetermined number of symbols, or a subslot containing fewer than a predetermined number of symbols.

[0042] In the following, the embodiments of the present disclosure will be described in detail. Please refer to FIG. 2 first. FIG. 2 illustrates a signaling chart showing a process 200 between a terminal device and a network device according to some exemplary embodiments of the present disclosure. For discussion purposes only, the process 200 will be described with reference to FIG. 1. The process 200 may involve the terminal device 110-1 and the network device 120 of FIG. 1. In some embodiments, the process 200 may be applied to AI / ML-based beam management. Alternatively, the process 200 may be applied to AI / ML-based CSI feedback. In other embodiments, the process 200 may be applied to AI / ML-based DMRS. In some embodiments, the process 200 may be applied to AI / ML-based CSI-RS.

[0043] In some embodiments, terminal device 110-1 may report one or more capabilities of terminal device 110-1 to network device 120 (2010). The one or more capabilities at least indicate that terminal device 110-1 supports a data processing model. The data processing model may be an AI / ML model. As used herein, the term "AI / ML model" may refer to a program or algorithm that utilizes a data set that allows for the recognition of certain patterns, which can then be used to reach a conclusion or make a prediction when provided with sufficient information. In general, an AI / ML model may be a mathematical algorithm that "learns" using data and input from a human expert to replicate the decisions the expert would make when provided with the same information.

[0044] In some embodiments, the capabilities may indicate a capability to support AI / ML. In some embodiments, the capabilities may indicate a capability to support beam management based on AI / ML. Alternatively, or in addition, the capabilities may indicate a capability to support CSI feedback based on AI / ML. Furthermore, the capabilities may indicate that the terminal device 110-1 supports a capability to support DMRS based on AI / ML. In some other embodiments, the capabilities may indicate that the terminal device 110-1 supports a capability to support CSI-RS based on AI / ML.

[0045] The network device 120 transmits (2020) downlink information for triggering the report. In some embodiments, the report may be a periodic CSI report configurable by RRC signaling. Alternatively, the report may be a semi-persistent CSI report. In this case, such CSI report may be activated by a media access control element (MAC CE) from the network device 120. In other embodiments, the report may be an aperiodic CSI report or a SP-CSI report. In this case, the CSI report may be triggered by a downlink control information (DCI) from the network device 120. In some embodiments, the downlink information may indicate that the report includes an estimation failure indicator (IFI). In some embodiments, the downlink information may indicate a first time offset associated with the transmission of the report. Alternatively, or in addition, the downlink information may indicate a second time offset associated with the transmission of the report. In other embodiments, the second time offset may be transmitted in other downlink information. The second time offset is greater than the first time offset.

[0046] In some embodiments, the network device 120 may transmit the report configuration. For example, the report configuration may be transmitted via a higher layer configuration of CSI-ReportConfig. The report configuration may indicate that the CSI report is associated with one or more CSI-RS or SSB resource sets. In some embodiments, the CSI-RS resource set may be periodic. Alternatively, the CSI-RS resource set may be semi-persistent. In other embodiments, the CSI-RS resource set may be aperiodic. In some embodiments, each CSI-RS resource in the CSI-RS resource set may correspond to a beam.

[0047] The terminal device 110-1 determines whether an estimation failure has occurred in the data processing model (2030). For example, when the terminal device 110-1 performs estimation based on normal AI / ML, the terminal device 110-1 can determine whether the processing in the AI / ML mode has been interrupted. The processing in the AI / ML mode may be interrupted due to one of memory overflow, CPU overload / overheat, or timeout. If the processing in the AI / ML mode has been interrupted, the terminal device 110-1 can determine that an estimation failure has occurred in the data processing model.

[0048] The terminal device 110-1 transmits a report to the network device 120 (2040). The report at least indicates whether an estimation failure occurs in the data processing model. For example, if the report includes CSI information and further indicates that an estimation failure occurs in the data processing model, this means that the CSI information is not acquired based on the data processing model. Alternatively, if the report includes CSI information and further indicates that an estimation failure does not occur in the data processing model, this means that the CSI information is acquired based on the data processing model. In some embodiments, if an estimation failure occurs, the CSI field in the report can be set to a predefined bit value. For example, the predefined bit value can be all 0. Alternatively, the predefined bit value can be all 1. In this way, the network device 120 can know whether an estimation failure occurs. Alternatively, a part of the CSI field can be set to a predefined value. For example, the bits of the reference signal received power (RSRP) can be set to a predefined value, and the bits of the CSI-RS resource indicator (CRI) field do not need to be set to a predefined value. In this way, the network device can be notified of the occurrence of estimation failure and the optimal beam.

[0049] In some embodiments, as described above, the downlink information may indicate that the report includes an IFI. In this case, the report may include an IFF and a CSI corresponding to the IFI. In some embodiments, the report may include a single part indicating the IFI and the CSI. Alternatively, the report may include a first part and a second part. In this situation, the first part may include an estimation failure indicator, and the second part may include a CSI corresponding to the estimation failure indicator. In some other embodiments, the first part may include at least one of an IFI, a Rank Indication (RI), a CSI Reference Signal (CSI-RS) Resource Indicator (CRI), a Channel Quality Indicator (CQI), or an indication of the number of non-zero wideband amplitude coefficients per layer of the Type 2 CSI, and the second part may include a Precoding Matrix Indicator (PMI). Alternatively, the report may include a first part, a second part, and a third part. In this case, the first part may include an IFI, the second part may include at least one of an RI, a CRI, a CQI, or an indication, and the third part may include a PMI.

[0050] In some other embodiments, the terminal device 110-1 may be configured with a first time offset and a second time offset as described above. In this case, if no estimation failure occurs in the data processing model, the terminal device 110-1 may transmit a report to the network device 120 according to the first time offset. In this case, the report may indicate a set of beams based on the data processing model, and the terminal device 110-1 may ignore the second time offset. Alternatively, if an estimation failure occurs in the data processing model, the terminal device 110-1 may transmit a report to the network device 120 according to the second time offset. In this case, the report may indicate a set of beams not based on the data processing model, and the terminal device 110-1 may ignore the first time offset. In some other embodiments, if an estimation failure occurs in the data processing model, the terminal device 110-1 may transmit an IFI according to the first time offset and then transmit a report to the network device 120. In this case, the report may indicate a set of beams not based on the data processing model. In this way, the network device 120 can know the estimation failure and the actual optimal beam information as soon as possible.

[0051] In some embodiments, terminal device 110-1 may be configured with an enablement parameter. The enablement parameter may enable CSI feedback based on a data processing model. Terminal device 110-1 may receive a configuration indicating a type of codebook. In this case, when an estimation failure occurs in the data processing model, terminal device 110-1 may send a report based on the codebook.

[0052] Alternatively, terminal device 110-1 may determine the type of codebook, in which case the report may include a bit field to indicate the type of codebook.

[0053] In some embodiments, if an estimation failure occurs in the data processing model, the report may include a negative acknowledgement (NACK) for all Hybrid Automatic Repeat Request-Acknowledgement (HARQ-ACK) information bits. In other words, the report may indicate HARQ information. Alternatively, if an estimation failure occurs in the data processing model, the report may include HARQ-ACK information bits, and the uplink channel on which the report is transmitted may include an IFI field. In some embodiments, the uplink channel may be a physical uplink control channel.

[0054] In another embodiment, if an estimation failure occurs in the data processing model, the terminal device 110-1 may scramble the uplink channel with an AI or ML specific scrambling sequence associated with the estimation failure. In this case, a report may be transmitted on the uplink channel. In some embodiments, the uplink channel may refer to a PUCCH. Alternatively, the uplink channel may refer to a PUSCH. In other words, the terminal device 110-1 may scramble a PUSCH / PUCCH carrying CSI or HRRQ information using an AI / ML specific scrambling sequence. The scrambled PUSCH / PUCCH may be used to indicate that an estimation failure has occurred in the terminal device 110-1.

[0055] In some embodiments, the scrambling sequence may be generated based on a Radio Network Temporary Identity (RNTI) of the AL or ML. For example, a new RNTI for the AI / ML, such as an AI-RNTI, may be introduced. Specifically, when scrambling a PUCCH or PUSCH carrying CSI or HRRQ information, the terminal device 110-1 first generates a scrambling sequence c according to the value of the RNTI. init If an estimation failure occurs, the terminal device 110-1 may calculate the scrambling sequence cinit may be calculated.

[0056] Alternatively, the scrambling sequence may be an AI / ML-specific pseudo-random sequence. For example, the terminal device 110-1 may use a new DMRS sequence corresponding to a PUSCH / PUCCH carrying CSI or HRRQ information to indicate an estimation failure. Specifically, the new DMRS sequence may be AI / ML-specific, and the new DMRS sequence may be an AI / ML-specific pseudo-random sequence c init Further, c initは ,AI / ML-specific scrambling ID (e.g., TIFF2025504319000002.tif1111 or TIFF2025504319000003.tif1211, which is set by a higher layer setting of scramblingID0 or scramblingID0.

[0057] In another embodiment, the scrambling sequence may be an AI / ML-specific mask. For example, if an estimation failure occurs in the data processing model, the terminal device 110-1 may add a cyclic redundancy check (CRC) having a mask (e.g., an AI / ML-specific mask) to the transport block (i.e., raw data or CSI of the PUSCH).

[0058] Exemplary embodiments will be described in detail with reference to Figures 3A-6. It should be noted that the exemplary embodiments described below can be implemented separately or together.

[0059] 3A-3E each illustrate a process 300 for AI / ML-based beam management.

[0060] The terminal device 110-1 may report the ability to support an AI / ML-based BM (3010). Thereafter, the network device 120 may set activation parameters to enable the functions of the AI-ML-based BM by RRC signaling (3020). The network device 120 can transmit DCI for triggering the CSI report of the BM (3030). The reported amount related to the CSI report can be set to "CRI-RSRP" (or other amounts, e.g., Synchronization Signal / Physical Broadcast Channel (SS / PBCH) Resource Block Indicator (SSBRI)-RSRP). The CSI-RS report can be associated with a CSI resource set including N CSI-RS resources, and each CSI-RS resource can correspond to a beam (direction). The network device 120 can transmit a set of reference signals to the terminal device 110-1 (3040).

[0061] The terminal device 110-1 can estimate the beam quality (e.g., L1-RSRP) of all N candidate beams according to M beams (M < N, M = N / a, a ∈ [1, N]) out of the N candidate beams by using AI prediction. Next, the terminal device 110-1 determines K optimal beams (i.e., having the maximum L1-RSRP), and after a set time offset (set by the upper layer setting of reportSlotOffset), the terminal device 110-1 can report the K (set by the existing upper layer setting nrofReportedRS, e.g., K = 1, 2, or 4) optimal beams to the network device 120. Specifically, the terminal device 110-1 can report the K CRIs and L1-RSRP corresponding to the K optimal beams.

[0062] The terminal device 110-1 may transmit a CSI report to the network device 120 (3050). When an estimation failure occurs in the data processing model, the beam qualities of all the N candidate beams cannot be estimated. In this case, a predefined bit value (or state) may be introduced as an indicator in the CSI field. The indicator may be used to indicate that an estimation failure has occurred in the terminal device 110-1. For example, the entire CSI field including all CRI fields and all RSRP fields in the CSI report may be set to all "0" or all "1". In this way, the network device may know whether an estimation failure has occurred. Alternatively, a partial CSI field in the CSI report may be set to all "0" or all "1". For example, only all RSRP fields in the CSI report may be set to all "0" or all "1". Furthermore, K CRIs corresponding to K optimal beams among the M candidate beams may be indicated in the CRI field. In this way, if a estimation failure occurs, the network device can know both the occurrence of the estimation failure and the (IDs) of the K optimal beams (determined from the M candidate beams).

[0063] In some embodiments, a new bit field may be introduced as an estimation failure indicator (IFI). Specifically, a new bit field may be introduced in the CSI field. Furthermore, the IFI field may include one bit, which indicates whether an estimation failure occurs. In other words, this means whether the corresponding CSI (e.g., CRI-RSRP, SSBRI-RSRP, CRI-signal-to-interference-and-noise-ratio (SINR), SSBRI-SINR) can be obtained based on the AI ​​prediction (i.e., data processing model). The term "corresponding CSI" may refer to the CSI in the PUCCH / PUSCH resource where the IFI is located, or the CSI in the same report as the IFI.

[0064] In some embodiments, the IFI may be introduced into the CSI report as a report quantity. Referring to FIG. 3B, the network device 120 may transmit a DCI for triggering a CSI report of the BM (3031). The report quantity associated with the CSI report (configured in the upper layer configuration of reportQuantity) may be set to "IFI-CRI-RSRP". The IFI may occupy a 1-bit field. In this case, the terminal device 110-1 may transmit a PUCCH / PUSCH including an IFI field to the network device 120 (3051). If an estimation failure occurs, the terminal device 110-1 may report "0" in the IFI field, which also means that the CRI and L1-RSRP corresponding to the IFI are not based on the AI ​​prediction (i.e., data processing model). If an estimation failure does not occur, the terminal device 110-1 may report "1" in the IFI field, which also means that the CRI and L1-RSRP corresponding to the IFI are based on the AI ​​prediction (i.e., data processing model). In other embodiments, the IFI may include more than one bit. In this case, the terminal device may also report the index of the data processing model of the estimation failure to the network device.

[0065] In some embodiments, the IFI and the CRI-RSRP may be included in the same part. Alternatively, the IFI and the CRI-RSRP may not be included in the same part. For example, if the reporting amount is set to "IFI-CRI-RSRP", the CSI report may include a single part. Alternatively, the CSI report may include two parts, a first part and a second part. In this case, the first part may include the IFI and the second part may include the CRI-RSRP. The first part and the second part refer to part 1 and part 2, respectively, i.e., part 1 and part 2 in the Type 1 or Type 2 CSI feedback. In this way, the network device can know whether an estimation failure has occurred and whether the reported K optimal beams are based on AI prediction.

[0066] In some other embodiments, one CSI report can be associated with two time offsets, which are used for AI-based beam reporting and legacy (or default, alternative) beam reporting, respectively. Specifically, the terminal device 110-1 can receive a DCI in which a CSI report for the BM is scheduled. The DCI can indicate two time offsets (e.g., t1 and t2) at the same time. That is, the CSI report is associated with two time offsets, t1 and t2. The value of t1 can be set according to the time required to measure M candidate beams and the delay of the AI ​​process (which is relatively small). The value of t2 can be set according to the time required to measure all N candidate beams. Thus, the value of t2 is larger than the value of t1. In some embodiments, the two time offsets can be indicated in two separate fields of the DCI. And they are selected from the same time offset list (e.g., reportSlotOffsetList) or two separate time offset lists (e.g., reportSlotOffsetList and reportSlotOffsetListForAI) configured by the RRC. Alternatively, one time offset may be indicated in the DCI and the other time offset may be associated with a time offset or a time offset list including the time offset. For example, the other time offset may be set in a CSI trigger state (e.g., CSI-AperiodicTriggerState) or a CSI report (CSI-ReportConfig).

[0067] Referring to FIG. 3C to FIG. 3E, the terminal device 110-1 can be configured with a time slot 310 and a time slot 320. It is assumed that the scheduling DCI can be placed in slot n. As shown in FIG. 3C, if an estimation failure does not occur, the terminal device 110-1 can transmit an AI-based beam report in a PUSCH of slot n+K2 (3052). K2 can refer to the slot interval between the PUSCH carrying the CSI and the scheduling DCI. In this case, the value of K2 can be determined according to the minimum time offset 310 (and other indicated time offsets, if present, e.g., time offsets associated with other CSI reports, time offsets of the TDRA field of the scheduling DCI), and the maximum time offset 320 can be ignored. In this way, the network device can know that no estimation failure has occurred in the terminal device 110-1, and can know K optimal beams based on the AI ​​prediction. Alternatively, as shown in FIG. 3D, if an estimation failure occurs, the terminal device 110-1 can transmit a legacy beam report in a PUSCH of slot n+K2 (3053). In this case, the value of K2 can be determined according to the maximum time offset 320 (and other indicated time offsets, if present), and the minimum time offset 310 can be ignored. In this way, the network device can know that an estimation failure has occurred in the terminal device, and can know the optimal beam based on legacy beam measurements, i.e., measurements of all N candidate beams.

[0068] Alternatively, the content of the AI-based beam report at t1 may include at least IFI information (e.g., a predefined bit value in the CRI-RSRP field or the RSRP field), and the content of the legacy beam report at t2 may include beam information (e.g., CRI-RSRP). Referring to FIG. 3E, the terminal device 110-1 may transmit a PUCCH 1 including at least IFI information to the network device 120 (3054). Then, the terminal device 110-1 may transmit a PUCCH 2 including beam information to the network device 120 (3055). In this way, when an estimation failure occurs, the network device can not only know the estimation failure in time, but also know the actual optimal beam information as soon as possible, because the terminal device does not need to wait for another CSI report to be triggered by the network device.

[0069] 4A-4B respectively show a process 400 of AI / ML-based CSI feedback. The terminal device 110-1 may report a capability of supporting AI / ML-based CSI feedback (4010). The network device 120 may then configure an enablement parameter to enable the function of AI-ML-based CSI feedback by RRC signaling (i.e., higher layer configuration) (4020). The network device 120 may transmit a DCI to trigger a CSI report for CSI acquisition (4030). A report quantity (i.e., report content) associated with the CSI report may be set to "CRI-RI-PMI-CQI" (or other quantity such as compressed CSI). The CSI-RS report may be associated with a CSI resource set including N CSI-RS resources, and each CSI-RS resource may correspond to a beam (direction).

[0070] The network device 120 may transmit the reference signal set to the terminal device 110-1 (4040). The terminal device 110-1 may calculate a compressed CSI (i.e., a bitstream) according to the CSI-RS resource associated with the CSI report by using an AI encoder. After a configured time offset (set by higher layer configuration of reportSlotOffset), the terminal device 110-1 may transmit the compressed bitstream of the CSI field of the PUSCH to the network device 120.

[0071] In some embodiments, a new bit field may be introduced as the IFI. Specifically, a new bit field may be introduced in the CSI field. Furthermore, the IFI field may include one bit, which indicates whether an estimation failure occurs. In other words, this means whether the corresponding CSI (e.g., CRI, rank indication (RI), precoding matrix indicator (PMI), channel quality indicator (CQI), compressed CSI) is obtained based on AI prediction. The term "corresponding CSI" may refer to the CSI in the PUCCH / PUSCH resource where the IFI is located, or the CSI in the same report as the IFI. In this case, referring to FIG. 4A, the terminal device 110-1 may transmit a PUCCH including the IFI to the network device 120 (4050). If an estimation failure occurs, the terminal device 110-1 may report "0" in the IFI field, which also means that the CRI, RI, CQI and / or PMI corresponding to the IFI are not based on the AI ​​encoder. If no estimation failure occurs, the terminal device 110-1 may report "1" in the IFI field, which also means that the CRI, RI, CQI and / or PMI corresponding to the IFI are based on the AI ​​encoder. In other embodiments, the IFI may include more than one bit. In this case, the terminal device may also report the index of the data processing model of the estimation failure to the network device.

[0072] In some embodiments, the IFI and the CRI-RI-PMI-CQI may be included in the same part. Alternatively, the IFI and the CRI-RI-PMI-CQI may not be included in the same part. Specifically, for Type1, Type2, and Extended Type2, CSI feedback is possible in the PUCCH / PUSCH. In some embodiments, the CSI report includes two parts, Part 1 and Part 2. In this case, Part 1 may include at least one of the IFI, RI, CRI, CQI, and an indication of the number of non-zero wideband amplitude coefficients per layer of the Type2 CSI. Part 2 may include the PMI. Alternatively, the CSI report may include three parts, Part 1, Part 2, and Part 3. In this case, Part 1 may include the IFI. Part 2 and Part 3 refer to Part 1 and Part 2, respectively. In this way, the network device can know whether an estimation failure has occurred and whether the reported CSI is based on the AI ​​encoder.

[0073] In some other embodiments, when the terminal device 110-1 is provided with an enable parameter enabling AI / ML-based CSI feedback, the terminal device 110-1 expects the type of codebook to be configured. With reference to FIG. 4B, when the terminal device 110-1 is configured with an enable parameter enabling AI / ML-based CSI feedback, the network device 120 may also configure the type of codebook (4021). For example, the network device 120 may transmit the codebook configuration (e.g., via a higher layer configuration). In this case, when an estimation failure occurs, the terminal device 110-1 may transmit a PUSCH based on the configured codebook (4051). Alternatively, the terminal device 110-1 may select the type of codebook. In this case, a new bit field may be introduced to indicate the selected codebook to the network device 120. For example, part 1 of the PUSCH may include a new bit field to indicate the type of the codebook (of part 2). In this way, in addition to the occurrence of an estimation failure and the AI ​​encoder based reported PUSCH, the network device also knows which codebook the terminal device used to calculate the reported PUSCH.

[0074] FIG. 5 shows a process 500 of AI / ML-based DMRS. The terminal device 110-1 may report the capability of supporting AI / ML-based DMRS (5010). Then, the network device 120 may set an enablement parameter to enable the function of AI-ML-based DMRS by RRC signaling (5020). The network device 120 may transmit a PDCCH with sparse DMRS (5030). The DMRS can be used to demodulate the PDCCH. Specifically, the terminal device 110-1 can estimate the channel in all resources by using the channel response in the DMRS resource by using the AI ​​DMRS. Then, the network device 120 can schedule a PDSCH with sparse DMRS (5040). According to the same AI DMRS, the terminal device 110-1 may also demodulate the scheduled PDSCH. Finally, the terminal device 110-1 may determine whether to report a HARQ-ACK or a HARQ-NACK depending on whether the received PDSCH is correct (eg, using a CRC check).

[0075] When an estimation failure occurs, the terminal device 110-1 can inform the network device 120 of the occurrence of the estimation failure in an implicit manner. For example, when an estimation failure occurs, the terminal device 110-1 may generate a NACK for all HARQ-ACK information bits in the PUCCH, regardless of whether other PDSCHs are correctly decoded or not. The terminal device 110-1 can transmit a PUCCH including a NACK to the network device 120 (5050). In this way, when a PUCCH in which all HARQ information bits are NACK is received, the network device can know that an estimation failure has occurred in the terminal device. Alternatively, the terminal device 110-1 can inform the network device 120 of the occurrence of the estimation failure in an explicit manner. For example, a new bit field can be introduced as an IFI of the PUCCH. Specifically, the IFI field can include one bit, which indicates whether an estimation failure has occurred or not. In this case, the terminal device 110-1 can transmit a PUCCH including an IFI field to the network device 120 (5050). The HARQ-ACK information bit of the PUCCH can indicate whether the corresponding PDSCH has been correctly decoded, in this way the network device can know whether an estimation failure has occurred, and the HARQ feedback of other PDSCHs will not be affected.

[0076] FIG. 6 shows a process of AI / ML-based CSI-RS. The terminal device 110-1 may report the capability of supporting AI / ML-based CSI-RS (6010). Then, the network device 120 may set an enablement parameter to enable the function of AI-ML-based CSI-RS by RRC signaling (6020). Assume that the network device 120 wants to know DL CSI corresponding to 32 antenna ports. The network device 120 may transmit a DCI for triggering a CSI report of the CSI-RS (6030). The network device 120 may transmit the CSI-RS of 16 ports (6040). After receiving the CSI-RS, the terminal device may estimate the channel in the resource corresponding to the CSI-RS of 32 ports based on the channel in the resource corresponding to the CSI-RS of 16 ports by using the AI ​​CSI-RS. Then, the terminal device may report the CSI corresponding to the 32 antenna ports to the network device 120 after a set time offset.

[0077] In some embodiments, a new bit field may be introduced as an estimation failure indicator (IFI). Specifically, a new bit field may be introduced in the CSI field. Furthermore, the IFI field may include one bit, which indicates whether an estimation failure occurs. In other words, this means whether the corresponding CSI (e.g., CRI, LI, RI, PMI, CQI, i1) is obtained based on the AI ​​CSI-RS. The term "corresponding CSI" may refer to the CSI in the PUCCH / PUSCH resource where the IFI is located, or the CSI in the same report as the IFI.

[0078] In some embodiments, the IFI can be introduced into the CSI as a report quantity. The report quantity associated with the CSI report (configured in the higher layer configuration of reportQuantity) can be set to "IFI-CRI-RI-PMI-CQI". The IFI can occupy a 1-bit field. In this case, the terminal device 110-1 can transmit a PUCCH / PUSCH including the IFI field to the network device 120 (6050). If an estimation failure occurs, the terminal device 110-1 may report "0" in the IFI field, which also means that the CRI, RI, CQI and PMI corresponding to the IFI are not based on the AI ​​CSI-RS, i.e., the reported CRI, RI, CQI and PMI are determined according to the 16 ports of the CSI-RS. If no estimation failure occurs, the terminal device 110-1 may report "1" in the IFI field, which also means that the CRI, RI, CQI and PMI corresponding to the IFI are based on the AI ​​encoder, i.e., the reported CRI, RI, CQI and PMI are determined according to the 32 ports of the CSI-RS. In other embodiments, the IFI may also include more than one bit. In this case, the terminal device 110-1 may also report the index of the data processing model of the estimation failure to the network device 120. In this way, the network device can know whether an estimation failure occurs and whether the reported CSI is based on the AI ​​encoder.

[0079] 7 illustrates a flowchart of an exemplary method 700 according to an embodiment of the present disclosure. The method 700 may be implemented in any suitable device. For illustrative purposes only, the method 700 may be implemented in the terminal device 110-1 shown in FIG. 1.

[0080] In some embodiments, the terminal device 110-1 may report one or more capabilities of the terminal device 110-1 to the network device 120. The one or more capabilities at least indicate that the terminal device 110-1 supports a data processing model. The data processing model may be an AI / ML model. As used herein, the term "AI / ML model" may refer to a program or algorithm that utilizes a data set that allows for the recognition of certain patterns, which can then be used to reach a conclusion or make a prediction when provided with sufficient information. In general, an AI / ML model may be a mathematical algorithm that "learns" using data and input from a human expert to reproduce the decisions that the expert would make when provided with the same information.

[0081] In some embodiments, the capabilities may indicate a capability to support AI / ML. In some embodiments, the capabilities may indicate a capability to support beam management based on AI / ML. Alternatively, or in addition, the capabilities may indicate a capability to support CSI feedback based on AI / ML. Furthermore, the capabilities may indicate that the terminal device 110-1 supports a capability to support DMRS based on AI / ML. In some other embodiments, the capabilities may indicate that the terminal device 110-1 supports a capability to support CSI-RS based on AI / ML.

[0082] In block 710, the terminal device 110-1 receives downlink information from the network device 120 for triggering a report. In some embodiments, the report may be a periodic CSI report configurable by RRC signaling. Alternatively, the report may be a semi-persistent CSI report. In this case, such a CSI report may be activated by a MAC CE from the network device 120. In other embodiments, the report may be an aperiodic CSI report or an SP-CSI report. In this case, the CSI report may be triggered by a DCI from the network device 120. In some embodiments, the downlink information may indicate that the report includes an IFI. In some embodiments, the downlink information may indicate a first time offset associated with the transmission of the report. Alternatively, or in addition, the downlink information may indicate a second time offset associated with the transmission of the report. In other embodiments, the second time offset may be transmitted in other downlink information. The second time offset is greater than the first time offset.

[0083] In some embodiments, the terminal device 110-1 may receive a report configuration. For example, the report configuration may be sent via a higher layer configuration of CSI-ReportConfig. The report configuration may indicate that the CSI report is associated with one or more CSI-RS or SSB resource sets. In some embodiments, the CSI-RS resource set may be periodic. Alternatively, the CSI-RS resource set may be semi-persistent. In other embodiments, the CSI-RS resource set may be aperiodic. In some embodiments, each CSI-RS resource in the CSI-RS resource set may correspond to a beam.

[0084] In block 720, the terminal device 110-1 determines whether an estimation failure occurs in the data processing model. For example, when the terminal device 110-1 performs estimation based on normal AI / ML, the terminal device 110-1 can determine whether the processing in the AI / ML mode is interrupted. The processing in the AI / ML mode may be interrupted due to one of memory overflow, CPU overload / overheat, or timeout. If the processing in the AI / ML mode is interrupted, the terminal device 110-1 can determine that an estimation failure occurs in the data processing model.

[0085] In block 730, the terminal device 110-1 transmits a report to the network device 120. The report at least indicates whether an estimation failure has occurred in the data processing model. For example, if the report includes CSI information and the report indicates that an estimation failure has occurred in the data processing model, this means that the CSI information has not been acquired based on the data processing model. Alternatively, if the report includes CSI information and the report indicates that an estimation failure has not occurred in the data processing model, this means that the CSI information has been acquired based on the data processing model. In some embodiments, if an estimation failure has occurred, the CSI field in the report can be set to a predefined bit value. For example, the predefined bit value can be all 0s. Alternatively, the predefined bit value can be all 1s. In this way, the network device 120 can know whether an estimation failure has occurred. Alternatively, a part of the CSI field can be set to a predefined value. For example, the bit of the RSRP can be set to a predefined value, and the bit of the CRI field does not need to be set to a predefined value. In this way, the network device can know the occurrence of an estimation failure and the optimal beam.

[0086] In some embodiments, as described above, the downlink information may indicate that the report includes an IFI. In this case, the report may include an IFF and a CSI corresponding to the IFI. In some embodiments, the report may include a single part indicating the IFI and the CSI. Alternatively, the report may include a first part and a second part. In this situation, the first part may include an estimation failure indicator and the second part may include a CSI corresponding to the estimation failure indicator. In some other embodiments, the first part may include at least one of an IFI, an RI, a CSI-RS, a CRI, a CQI, or an indication of the number of non-zero wideband amplitude coefficients per layer of the Type2 CSI, and the second part may include a PMI. Alternatively, the report may include a first part, a second part, and a third part. In this case, the first part may include an IFI, the second part may include at least one of an RI, a CRI, a CQI, or an indication, and the third part may include a PMI.

[0087] In some other embodiments, the terminal device 110-1 may be configured with a first time offset and a second time offset as described above. In this case, if no estimation failure occurs in the data processing model, the terminal device 110-1 may transmit a report to the network device 120 according to the first time offset. The report may indicate a set of beams based on the data processing model, and the terminal device 110-1 may ignore the second time offset. Alternatively, if an estimation failure occurs in the data processing model, the terminal device 110-1 may transmit a report to the network device 120 according to the second time offset. In this case, the report may indicate a set of beams not based on the data processing model, and the terminal device 110-1 may ignore the first time offset. In some other embodiments, if an estimation failure occurs in the data processing model, the terminal device 110-1 may transmit an IFI according to the first time offset and then transmit a report to the network device 120. In this case, the report may indicate a set of beams not based on the data processing model. In this way, the network device 120 can know the estimation failure and the actual optimal beam information as soon as possible.

[0088] In some embodiments, terminal device 110-1 may be configured with an enablement parameter. The enablement parameter may enable CSI feedback based on a data processing model. Terminal device 110-1 may receive a configuration indicating a type of codebook. In this case, when an estimation failure occurs in the data processing model, terminal device 110-1 may send a report based on the codebook.

[0089] Alternatively, terminal device 110-1 may determine the type of codebook, in which case the report may include a bit field to indicate the type of codebook.

[0090] In some embodiments, if an estimation failure occurs in the data processing model, the report may include a NACK for all HARQ-ACK information bits. In other words, the report may indicate HARQ information. Alternatively, if an estimation failure occurs in the data processing model, the report may include an IFI and HARQ-ACK information bits, and the uplink channel on which the report is transmitted may include an IFI field. In some embodiments, the uplink channel may be a physical uplink control channel.

[0091] In another embodiment, if an estimation failure occurs in the data processing model, the terminal device 110-1 may scramble the uplink channel with an AI or ML specific scrambling sequence associated with the estimation failure. In this case, a report may be transmitted on the uplink channel. In some embodiments, the uplink channel may refer to a PUCCH. Alternatively, the uplink channel may refer to a PUSCH. In other words, the terminal device 110-1 may scramble a PUSCH / PUCCH carrying CSI or HRRQ information using an AI / ML specific scrambling sequence. The scrambled PUSCH / PUCCH may be used to indicate that an estimation failure has occurred in the terminal device 110-1.

[0092] In some embodiments, the scrambling sequence may be generated based on the RNTI of the AL or ML. For example, a new RNTI for AI / ML, such as an AI-RNTI, may be introduced. Specifically, when scrambling a PUCCH or PUSCH carrying CSI or HRRQ information, the terminal device 110-1 first generates a scrambling sequence c according to the value of the RNTI. init If an estimation failure occurs, the terminal device 110-1 may calculate the scrambling sequence c init may be calculated.

[0093] Alternatively, the scrambling sequence may be an AI / ML-specific pseudo-random sequence. For example, the terminal device 110-1 may use a new DMRS sequence corresponding to a PUSCH / PUCCH carrying CSI or HRRQ information to indicate an estimation failure. Specifically, the new DMRS sequence may be AI / ML-specific, and the new DMRS sequence may be an AI / ML-specific pseudo-random sequence c init Further, c initは ,AI / ML-specific scrambling ID (e.g., TIFF2025504319000004.tif99 or TIFF2025504319000005.tif99, which is set by a higher layer setting of scramblingID0 or scramblingID0.

[0094] In another embodiment, the scrambling sequence may be an AI / ML-specific mask. For example, if an estimation failure occurs in the data processing model, the terminal device 110-1 may add a CRC having a mask (e.g., an AI / ML-specific mask) to the transport block (i.e., raw data or CSI of the PUSCH).

[0095] 8 illustrates a flowchart of an exemplary method 800 according to an embodiment of the present disclosure. The method 800 may be implemented in any suitable device. For illustrative purposes only, the method 800 may be implemented in the network device 120 shown in FIG.

[0096] In some embodiments, the network device 120 may receive a report from the terminal device 110-1 indicating one or more capabilities of the terminal device 110-1. The one or more capabilities at least indicate that the terminal device 110-1 supports a data processing model. The data processing model may be an AI / ML model. As used herein, the term "AI / ML model" may refer to a program or algorithm that utilizes a data set that allows for the recognition of certain patterns, which can then be used to reach a conclusion or make a prediction when provided with sufficient information. In general, an AI / ML model may be a mathematical algorithm that "learns" using data and input from a human expert to reproduce the decisions that the expert would make when provided with the same information.

[0097] In some embodiments, the capabilities may indicate a capability to support AI / ML. In some embodiments, the capabilities may indicate a capability to support beam management based on AI / ML. Alternatively, or in addition, the capabilities may indicate a capability to support CSI feedback based on AI / ML. Furthermore, the capabilities may indicate that the terminal device 110-1 supports a capability to support DMRS based on AI / ML. In some other embodiments, the capabilities may indicate that the terminal device 110-1 supports a capability to support CSI-RS based on AI / ML.

[0098] At block 810, the network device 120 transmits downlink information for triggering the report. In some embodiments, the report may be a periodic CSI report configurable by RRC signaling. Alternatively, the report may be a semi-persistent CSI report. In this case, such CSI reporting may be activated by a MAC CE from the network device 120. In other embodiments, the report may be an aperiodic CSI report or an SP-CSI report. In this case, the CSI reporting may be triggered by a DCI from the network device 120. In some embodiments, the downlink information may indicate that the report includes an IFI. In some embodiments, the downlink information may indicate a first time offset associated with the transmission of the report. Alternatively or additionally, the downlink information may indicate a second time offset associated with the transmission of the report. In other embodiments, the second time offset may be transmitted in other downlink information. The second time offset is greater than the first time offset.

[0099] In some embodiments, the network device 120 may transmit the report configuration. For example, the report configuration may be transmitted via a higher layer configuration of CSI-ReportConfig. The report configuration may indicate that the CSI report is associated with one or more CSI-RS or SSB resource sets. In some embodiments, the CSI-RS resource set may be periodic. Alternatively, the CSI-RS resource set may be semi-persistent. In other embodiments, the CSI-RS resource set may be aperiodic. In some embodiments, each CSI-RS resource in the CSI-RS resource set may correspond to a beam.

[0100] In block 820, the network device 120 receives a report from the terminal device 110-1. The report at least indicates whether an estimation failure has occurred in the data processing model. For example, if the report includes CSI information and the report indicates that an estimation failure has occurred in the data processing model, this means that the CSI information has not been acquired based on the data processing model. Alternatively, if the report includes CSI information and the report indicates that an estimation failure has not occurred in the data processing model, this means that the CSI information has been acquired based on the data processing model. In some embodiments, if an estimation failure has occurred, the CSI field in the report can be set to a predefined bit value. For example, the predefined bit value can be all 0s. Alternatively, the predefined bit value can be all 1s. In this way, the network device 120 can know whether an estimation failure has occurred. Alternatively, a part of the CSI field can be set to a predefined value. For example, the bit of the RSRP can be set to a predefined value, and the bit of the CRI field does not need to be set to a predefined value. In this way, the network device can know the occurrence of an estimation failure and the optimal beam.

[0101] In some embodiments, as described above, the downlink information may indicate that the report includes an IFI. In this case, the report may include an IFF and a CSI corresponding to the IFI. In some embodiments, the report may include a single part indicating the IFI and the CSI. Alternatively, the report may include a first part and a second part. In this situation, the first part may include an estimation failure indicator and the second part may include a CSI corresponding to the estimation failure indicator. In some other embodiments, the first part may include at least one of an IFI, an RI, a CRI, a CQI, or an indication of the number of non-zero wideband amplitude coefficients per layer of the Type2 CSI, and the second part may include a PMI. Alternatively, the report may include a first part, a second part, and a third part. In this case, the first part may include an IFI, the second part may include at least one of an RI, a CRI, a CQI, or an indication, and the third part may include a PMI.

[0102] In some other embodiments, as described above, the terminal device 110-1 may be configured with a first time offset and a second time offset. In this case, if no estimation failure occurs in the data processing model, the network device 120 may receive a report according to the first time offset. The report may indicate a set of beams based on the data processing model. Alternatively, if an estimation failure occurs in the data processing model, the network device 120 may receive a report according to the second time offset. In this case, the report may indicate a set of beams not based on the data processing model. In some other embodiments, if an estimation failure occurs in the data processing model, the network device 120 may receive an IFI according to the first time offset and then receive a report. In this case, the report may indicate a set of beams not based on the data processing model. In this way, the network device 120 may know the estimation failure and the actual optimal beam information as soon as possible.

[0103] In some embodiments, the terminal device 110-1 may be configured with an enablement parameter. The enablement parameter may enable CSI feedback based on a data processing model. The network device 110-1 may send a configuration indicating a type of codebook. In this case, when an estimation failure occurs in the data processing model, the terminal device 110-1 may send a report based on the codebook.

[0104] Alternatively, terminal device 110-1 may determine the type of codebook, in which case the report may include a bit field to indicate the type of codebook.

[0105] In some embodiments, if an estimation failure occurs in the data processing model, the report may include a NACK for all HARQ-ACK information bits, or if an estimation failure occurs in the data processing model, the report may include an IFI and the HARQ-ACK information bits.

[0106] In another embodiment, if an estimation failure occurs in the data processing model, the uplink channel may be scrambled with an AI or ML specific scrambling sequence associated with the estimation failure. In this case, a report may be transmitted on the uplink channel. In some embodiments, the uplink channel may refer to a PUCCH. Alternatively, the uplink channel may refer to a PUSCH. In other words, the terminal device 110-1 may scramble a PUSCH / PUCCH carrying CSI or HRRQ information using an AI / ML specific scrambling sequence. The scrambled PUSCH / PUCCH may be used to indicate that an estimation failure has occurred in the terminal device 110-1. In this case, the network device 120 may determine that an estimation failure has occurred in the terminal device 110-1 based on the scrambled PUSCH / PUCCH.

[0107] In some embodiments, the terminal device includes circuitry configured to receive downlink information for triggering a report from the network device, determine whether an estimation failure occurs in the data processing model, and send a report to the network device, the report indicating at least whether an estimation failure occurs in the data processing model.

[0108] In some embodiments, the terminal device includes circuitry configured to transmit a report to the network device in response to a determination of an occurrence of an estimation failure, whereby a channel state information (CSI) field in the report is set to a predefined bit value or a portion of the CSI field is set to a predefined bit value.

[0109] In some embodiments, the report includes at least one of an estimation failure indicator or a CSI corresponding to the estimation failure indicator, where the estimation failure indicator indicates whether an estimation failure occurred in the data processing model.

[0110] In some embodiments, the downlink information indicates whether the report includes an estimation failure indicator.

[0111] In some embodiments, the report includes a single portion, the single portion including at least one of the estimated failure indicator and the CSI corresponding to the estimated failure indicator.

[0112] In some embodiments, the report includes a first portion and a second portion, the first portion including the estimated failure indicator and the second portion including the CSI corresponding to the estimated failure indicator.

[0113] In some embodiments, the report includes a first portion and a second portion, the first portion including at least one of an estimation failure indicator, a rank indication (RI), a CSI reference signal (CSI-RS) resource indicator (CRI), a channel quality indicator (CQI), or an indication of a number of non-zero wideband amplitude coefficients per layer of Type-2 CSI, and the second portion including a precoding matrix indicator (PMI).

[0114] In some embodiments, the report includes a first portion, a second portion, and a third portion, where the first portion includes an estimated failure indicator, the second portion includes at least one of an RI, a CRI, a CQI, or an indication, and the third portion includes a PMI.

[0115] In some embodiments, the terminal device includes circuitry configured to receive from the network device a setting indicating a type of codebook in accordance with a determination that an enablement parameter enabling CSI feedback based on a data processing model is configured in the terminal device. In some embodiments, the terminal device includes circuitry configured to transmit a report to the network device by transmitting a report including CSI based on the codebook in accordance with a determination that an estimation failure has occurred.

[0116] In some embodiments, the terminal device includes circuitry configured to determine a type of the codebook, hi some embodiments, the terminal device includes circuitry configured to send a report to the network device by sending a report to the network device that includes a bit field indicating a type of the codebook.

[0117] In some embodiments, the downlink information indicates a first time offset and a second time offset that is greater than the first time offset, or the downlink information indicates the first time offset and further downlink information indicates the second time offset.

[0118] In some embodiments, the terminal device includes circuitry configured to transmit a report to the network device in accordance with a determination that no estimation failure occurs in the data processing model by transmitting a report to the network device in accordance with a first time offset, the report indicating a set of beams based on the data processing model, the second time offset being omitted.

[0119] In some embodiments, the terminal device includes circuitry configured to transmit a report to the network device according to a determination of an occurrence of an estimation failure by transmitting the report to the network device according to a second time offset, the report indicating a set of beams not based on the data processing model, and the first time offset being omitted.

[0120] In some embodiments, the terminal device includes circuitry configured to transmit a report to the network device by transmitting a channel state information (CSI) field or an estimation failure indicator in the report according to a first time offset in accordance with a determination of an occurrence of an estimation failure, and transmitting a report to the network device indicating a set of beams not based on the data processing model according to a second time offset, wherein the channel state information (CSI) field is set to a predefined bit value or a portion of the CSI field is set to a predefined bit value.

[0121] In some embodiments, the terminal device includes circuitry configured to send a report to the network device by sending a report including a negative acknowledgment (NACK) for all Hybrid Automatic Repeat Request-Acknowledgement (HARQ-ACK) information bits in accordance with a determination of an occurrence of an estimation failure.

[0122] In some embodiments, the terminal device includes circuitry configured to, in accordance with a determination of an occurrence of an estimation failure, transmit a report to the network device by transmitting a report including a HARQ-ACK information bit on an uplink channel, the uplink channel including an estimation failure indicator.

[0123] In some embodiments, the terminal device includes circuitry configured to, pursuant to a determination of an occurrence of an estimation failure, scramble an uplink channel on which the report is transmitted with an artificial intelligence (AI) or machine learning (ML) specific scrambling sequence associated with the estimation failure.

[0124] In some embodiments, the scrambling sequence is generated based on an AL or ML Radio Network Temporary Identity (RNTI), or the scrambling sequence is an AI or ML specific pseudo-random sequence, or the scrambling sequence is an AI or ML specific Cyclic Redundancy Check (CRC) mask.

[0125] In some embodiments, the network device includes circuitry configured to transmit downlink information to the terminal device for triggering a report at the network device and to receive a report from the terminal device, the report indicating at least whether an estimation failure occurred in the data processing model.

[0126] In some embodiments, the network device includes circuitry configured to receive a report from the terminal device in accordance with a determination of an occurrence of an estimation failure, whereby a channel state information (CSI) field in the report is set to a predefined bit value or a portion of the CSI field is set to a predefined bit value.

[0127] In some embodiments, the report includes an estimation failure indicator and a CSI corresponding to the estimation failure indicator, where the estimation failure indicator indicates whether an estimation failure occurred in the data processing model.

[0128] In some embodiments, the downlink information indicates that the report includes an estimation failure indicator.

[0129] In some embodiments, the report includes a single portion indicating the estimated failure indicator and the CSI.

[0130] In some embodiments, the report includes a first portion and a second portion, the first portion including the estimated failure indicator and the second portion including the CSI corresponding to the estimated failure indicator.

[0131] In some embodiments, the report includes a first part and a second part, where the first part includes at least one of an estimation failure indicator, a rank indication (RI), a CSI reference signal (CSI-RS) resource indicator (CRI), a channel quality indicator (CQI), or an indication of a number of non-zero wideband amplitude coefficients per layer of Type 2 CSI, and the second part includes a precoding matrix indicator (PMI). Or, the report includes a first part, a second part, and a third part, where the first part includes an estimation failure indicator, the second part includes at least one of an RI, a CRI, a CQI, or an indication, and the third part includes a PMI.

[0132] In some embodiments, the network device includes circuitry configured to: send a configuration to the terminal device indicating a type of codebook in accordance with a determination that an enablement parameter enabling CSI feedback based on a data processing model is set in the terminal device. In some embodiments, the network device includes circuitry configured to receive a report from the terminal device in accordance with a determination that an estimation failure has occurred by receiving a report including CSI feedback based on the codebook.

[0133] In some embodiments, the network device includes circuitry configured to receive the report from the terminal device by receiving a report from the terminal device that includes a bit field indicating a type of codebook.

[0134] In some embodiments, the downlink information indicates a first time offset and a second time offset that is greater than the first time offset, or the downlink information indicates the first time offset and further downlink information indicates the second time offset.

[0135] In some embodiments, the network device includes circuitry configured to receive a report from the terminal device according to a determination that no estimation failure occurs in the data processing model, by receiving a report from the terminal device according to a first time offset, the report indicating a set of beams based on the data processing model, the second time offset being ignored.

[0136] In some embodiments, the network device includes circuitry configured to receive a report from the terminal device according to a determination of an occurrence of an estimation failure, by receiving a report from the terminal device according to a second time offset, the report indicating a set of beams not based on the data processing model, the second time offset being ignored.

[0137] In some embodiments, the network device includes circuitry configured to receive a report from the terminal device according to a determination of an occurrence of an estimation failure by receiving an estimation failure indicator according to a first time offset and by receiving a report from the terminal device according to a second time offset, the report indicating a set of beams not based on the data processing model.

[0138] In some embodiments, the network device includes circuitry configured to receive a report from the terminal device, pursuant to a determination of an occurrence of an estimation failure, by receiving a report including a negative acknowledgment (NACK) for all Hybrid Automatic Repeat Request-Acknowledgement (HARQ-ACK) information bits.

[0139] In some embodiments, the network device includes circuitry configured to receive, pursuant to a determination of an occurrence of an estimation failure, a report from the terminal device by receiving, on an uplink channel, a report including a HARQ-ACK information bit, the uplink channel including an estimation failure indicator.

[0140] In some embodiments, the network device includes circuitry configured to receive a report from the terminal device by receiving a report on an uplink channel in accordance with a determination of an occurrence of an estimation failure, the uplink channel being scrambled with an artificial intelligence (AI) or machine learning (ML) specific scrambling sequence associated with the estimation failure.

[0141] In some embodiments, the scrambling sequence is generated based on the AL or ML Radio Network Temporary Identity (RNTI), or the scrambling sequence is an AI / ML specific pseudo-random sequence, or the scrambling sequence is an AI / ML specific mask.

[0142] 9 is a schematic block diagram of an apparatus 900 suitable for implementing an embodiment of the present disclosure. The apparatus 900 may be considered as a further exemplary implementation of the terminal apparatus 110 shown in FIG. 1. Thus, the apparatus 900 may be implemented in, or at least as a part of, the terminal apparatus 110. Alternatively, the apparatus 900 may be considered as a further exemplary implementation of the network apparatus 120 shown in FIG. 1. Thus, the apparatus 900 may be implemented in, or at least as a part of, the network apparatus 120.

[0143] As shown, the apparatus 900 includes a processor 910, a memory 920 coupled to the processor 910, a suitable transmitter (TX) and receiver (RX) 940 coupled to the processor 910, and a communication interface coupled to the TX / RX 940. The memory 920 stores at least a portion of a program 930. The TX / RX 940 is for bidirectional communication. The TX / RX 940 has at least one antenna to facilitate communication, although in practice the access nodes discussed herein may have multiple antennas. The communication interface may represent any interface required 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 an Uu interface for communication between an eNB and a terminal device.

[0144] The program 930 may be considered to include program instructions that, when executed by an associated processor 910, enable the device 900 to operate in accordance with embodiments of the present disclosure, as discussed herein with reference to Figures 2-8. The embodiments of the present disclosure may be implemented by computer software, hardware, or a combination of software and hardware executable by the processor 910 of the device 900. The processor 910 may be configured to implement various embodiments of the present disclosure. The combination of the processor 910 and the memory 920 may also constitute a processing means 950 suitable for implementing various embodiments of the present disclosure.

[0145] The memory 920 may be of any type suitable for the local technology network and may be implemented by any suitable data storage technology, including, but not limited to, computer-readable non-transitory storage media, semiconductor-based storage devices, magnetic storage devices and systems, optical storage devices and systems, fixed and removable memories, etc. Although only one memory 920 is shown in the device 900, multiple physically distinct memory modules may be installed in the device 900. The processor 910 may be of any type suitable for the local technology network and may include, but is not limited to, one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), and processors based on multi-core processor configurations. The device 900 may have multiple processors, for example application specific integrated circuit chips time-slaved to a clock synchronous with a master processor.

[0146] In general, various embodiments of the present disclosure may be implemented by hardware or special purpose circuits, software, logic, or any combination thereof. Some aspects may be implemented by hardware, and other aspects may be implemented by firmware or software that may be executed by a controller, microprocessor, or other computing device. Various aspects of the embodiments of the present disclosure have been shown and described as block diagrams, flow charts, or illustrated by some other pictorial representation, and it will be understood that the blocks, apparatus, systems, techniques, or methods described herein may be implemented by, for example, but not limited to, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing device, or combinations thereof.

[0147] The present disclosure further provides at least one computer program product tangibly stored in a computer readable non-transitory storage medium. The computer program product includes computer executable instructions, such as instructions included in program modules. The instructions execute on a target real or virtual processor device to perform, for example, the processes or methods described above with reference to Figures 2-8. Typically, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In various embodiments, the functionality of the program modules may be combined or split among program modules as desired. The machine readable instructions of the program modules may be executed in local or distributed devices. In distributed devices, the program modules may be located in both local and remote storage media.

[0148] The program codes for carrying out the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer or other programmable data processing apparatus, and when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are performed. The program codes may run entirely on the machine, partially on the machine, as a separate software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] The above program code may be embodied on a machine-readable medium, which may be any tangible medium that contains or stores a program for use by or in conjunction 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, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Even more specific examples of machine-readable storage media include one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable-programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0150] It should be understood that although operations have been described in a particular order, it is not required that such operations be performed in the particular order or sequence shown, or that all of the operations shown be performed, in order to achieve desired results. In some situations, multitasking and parallel processing may be advantageous. Similarly, although the above discussion includes some specific implementation details, these should not be construed as limitations on the scope of the disclosure, but rather as descriptions of features that may be specific to certain embodiments. Some features that are described in the context of individual embodiments may be implemented in combination in an embodiment. Conversely, various features that are described in the context of an embodiment may be implemented in multiple embodiments separately or in any suitable subcombination.

[0151] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it is to be understood that the present disclosure, as defined by the appended claims, is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

[0152] In this specification, 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, cell 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, vehicle-mounted devices for V2X communication (where X means pedestrian, vehicle or infrastructure / network), devices for Integrated Access and Backhaul (IAB), spacecraft or aircraft in Non-Terrestrial Networks (NTN) including High Altitude Platforms (HAP) and satellites, including Unmanned Aerial Systems (UAS), and Extended Reality (XR) including different types of reality such as Augmented Reality (AR), Mixed Reality (MR), and Virtual Reality (VR). Examples of such devices include, but are not limited to, Reality (UE) devices, unmanned aerial vehicles (UAVs) that do not require a human pilot, commonly known as drones, devices on high speed trains (HST), imaging devices such as digital cameras, sensors, gaming devices, music storage and playback devices, or Internet devices that allow wireless or wired Internet access and browsing. A "terminal device" may also 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 communication, and Iota applications. It may also incorporate one or more subscriber identity modules (SIMs), known as multi-SIM. The term "terminal device" may be used interchangeably with UE, mobile station, subscriber equipment, mobile terminal, user terminal, or wireless device.

[0153] The term "network device" refers to a device capable of providing or hosting a cell or coverage through which terminal devices can communicate. Examples of network devices include, but are not limited to, a Node B (Node or NB), an Evolved Node (anode or eNB), a next generation node (gNB), a transmit / receive point (TRP), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), an IAB node, a low power node such as a femto node, a pico node, a reconfigurable intelligent surface (RIS), etc.

[0154] A terminal device or a network device may have an artificial intelligence (AI) or machine learning function, which generally includes a model that can be used to learn from a large amount of data collected for a specific function and predict some information.

[0155] The terminal device or network device may function in multiple frequency ranges, e.g., FR1 (410 MHz-7125 MHz), FR2 (24.25 GHz-71 GHz), higher than 100 GHz, Terahertz (THz), etc. Furthermore, it can function in licensed / unlicensed / shared spectrum. The terminal device may have multiple connections with the network device in a multi-radio dual connectivity (MR-DC) application scenario. The terminal device or network device can function in full duplex, flexible duplex, and cross division duplex modes.

[0156] Embodiments of the present disclosure may be implemented in test equipment, such as, for example, a signal generator, a signal analyzer, a spectrum analyzer, a network analyzer, a test terminal equipment, a test network equipment, a channel emulator, and the like.

[0157] Embodiments of the present disclosure may be performed in accordance with any generation of communication protocols now known or developed in the future, including, but 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.

Claims

1. receiving, at the terminal device, downlink information for triggering a report from a network device; determining, in the terminal device, whether an estimation failure has occurred in a data processing model; transmitting said report to said network device; Including, The report indicates at least whether the estimation failure occurred in the data processing model. Communication methods.

2. Transmitting the report to the network device includes: transmitting said report to said network device in response to said determination of an occurrence of said estimation failure; A channel state information (CSI) field in the report is set to a predefined bit value, or a portion of the CSI field is set to the predefined bit value; The method of claim 1.

3. the report includes at least one of an estimation failure indicator or CSI corresponding to the estimation failure indicator; the estimation failure indicator indicating whether the estimation failure occurred in the data processing model; The method of claim 1.

4. the downlink information indicating whether the report includes the estimation failure indicator. The method according to claim 3.

5. the report includes a single part; the single portion includes at least one of the estimation failure indicator and the CSI corresponding to the estimation failure indicator. The method according to claim 3.

6. the report includes a first portion and a second portion; the first portion includes the estimation failure indicator; the second portion includes the CSI corresponding to the estimated failure indicator. The method according to claim 3.

7. the report includes a first portion and a second portion; the first portion includes at least one of the estimation failure indicator, a rank indication (RI), a CSI reference signal (CSI-RS) resource indicator (CRI), a channel quality indicator (CQI), or an indication of a number of non-zero wideband amplitude coefficients per layer of Type 2 CSI; The second part includes a precoding matrix indicator (PMI). The method according to claim 3.

8. the report includes a first portion, a second portion, and a third portion; the first portion includes the estimation failure indicator; the second part includes at least one of a RI, a CRI, a CQI, or an indication; The third portion includes PMI. The method according to claim 3.

9. receiving, in accordance with a determination that an enabling parameter enabling CSI feedback based on the data processing model is configured in the terminal device, a setting indicating a type of a codebook from the network device; Transmitting the report to the network device includes: transmitting the report including the CSI based on the codebook in response to a determination of an occurrence of the estimation failure. The method according to claim 3.

10. determining a type of codebook; Transmitting the report to the network device includes: transmitting the report to the network device, the report including a bit field indicating the type of the codebook. The method according to claim 3.

11. the downlink information indicates a first time offset and a second time offset that is greater than the first time offset; or the downlink information indicates the first time offset, and further downlink information indicates the second time offset. The method of claim 1.

12. Transmitting the report to the network device includes: transmitting the report to the network device according to the first time offset in response to a determination that the estimation failure has not occurred in the data processing model; the report indicates a set of beams based on the data processing model; The second time offset is omitted. The method of claim 11.

13. Transmitting the report to the network device includes: transmitting the report to the network device according to the second time offset in response to a determination of the occurrence of the estimation failure; the report indicates a set of beams not based on the data processing model; The first time offset is omitted. The method of claim 11.

14. Transmitting the report to the network device includes: transmitting a channel state information (CSI) field or an estimation failure indicator in the report according to the first time offset in response to the determination of the occurrence of the estimation failure; transmitting the report to the network device according to the second time offset; Including, The channel state information (CSI) field is set to a predefined bit value or a portion of the CSI field is set to the predefined bit value; the report indicates a set of beams not based on the data processing model; The method of claim 11.

15. Transmitting the report to the network device includes: transmitting the report including a negative acknowledgement (NACK) for all Hybrid Automatic Repeat Request-Acknowledgement (HARQ-ACK) information bits in response to the determination of the occurrence of the estimation failure. The method of claim 1.

16. Transmitting the report to the network device includes: transmitting, in response to the determination of the occurrence of the estimation failure, the report including a HARQ-ACK information bit on an uplink channel; the uplink channel includes an estimation failure indicator. The method of claim 1.

17. and scrambling an uplink channel over which the report is transmitted with an artificial intelligence (AI) or machine learning (ML) specific scrambling sequence associated with the estimation failure in accordance with determining that the estimation failure has occurred. The method of claim 1.

18. The scrambling sequence is generated based on a Radio Network Temporary Identity (RNTI) of the AL or ML; or The scrambling sequence is an AI or ML specific pseudorandom sequence, or The scrambling sequence is an AI or ML specific cyclic redundancy check (CRC) mask.

20. The method of claim 17.

19. In the network device, transmitting downlink information for triggering a report to the terminal device; receiving the report from the terminal device; Including, The report at least indicates whether an estimation failure occurred in the data processing model. Communication methods.

20. Receiving the report from the terminal device receiving the report from the terminal device in accordance with a determination of an occurrence of the estimation failure; A channel state information (CSI) field in the report is set to a predefined bit value, or a portion of the CSI field is set to the predefined bit value; 20. The method of claim 19.

21. the report includes an estimation failure indicator and a CSI corresponding to the estimation failure indicator; the estimation failure indicator indicating whether the estimation failure occurred in the data processing model; 20. The method of claim 19.

22. the downlink information indicates that the report includes an estimation failure indicator.

22. The method of claim 21.

23. the report includes a single portion indicating the estimated failure indicator and the CSI.

22. The method of claim 21.

24. the report includes a first portion and a second portion; the first portion includes the estimation failure indicator; the second portion includes the CSI corresponding to the estimated failure indicator.

22. The method of claim 21.

25. the report includes a first part and a second part, the first part including at least one of the estimation failure indicator, a rank indication (RI), a CSI reference signal (CSI-RS) resource indicator (CRI), a channel quality indicator (CQI), or an indication of a number of non-zero wideband amplitude coefficients per layer of Type 2 CSI, and the second part including a precoding matrix indicator (PMI); or the report comprises a first part, a second part, and a third part, the first part comprising the estimated failure indicator, the second part comprising at least one of the RI, the CRI, the CQI, or the indication, and the third part comprising the PMI.

22. The method of claim 21.

26. and transmitting a setting to the terminal device indicating a type of a codebook according to a determination that an enablement parameter enabling CSI feedback based on the data processing model is set in the terminal device; Receiving the report from the terminal device receiving the report including the CSI feedback based on the codebook in accordance with a determination of the occurrence of the estimation failure.

22. The method of claim 21.

27. Receiving the report from the terminal device receiving the report from the terminal device, the report including a bit field indicating the type of the codebook; 22. The method of claim 21.

28. the downlink information indicates a first time offset and a second time offset that is greater than the first time offset; or the downlink information indicates the first time offset, and further downlink information indicates the second time offset.

20. The method of claim 19.

29. Receiving the report from the terminal device receiving the report from the terminal device according to the first time offset in response to a determination that the estimation failure has not occurred in the data processing model; the report indicates a set of beams based on the data processing model; The second time offset is ignored.

30. The method of claim 28.

30. Receiving the report from the terminal device receiving, from the terminal device, the report according to the second time offset in response to a determination of the occurrence of the estimation failure; the report indicates a set of beams not based on the data processing model; The second time offset is ignored.

30. The method of claim 28.

31. Receiving the report from the terminal device receiving an estimation failure indicator according to the first time offset in response to determining that an estimation failure has occurred; receiving the report from the terminal device according to the second time offset; Including, the report indicates a set of beams not based on the data processing model; 30. The method of claim 28.

32. Receiving the report from the terminal device receiving the report including a negative acknowledgement (NACK) for all Hybrid Automatic Repeat Request-Acknowledgement (HARQ-ACK) information bits in response to the determination of the occurrence of the estimation failure.

20. The method of claim 19.

33. Receiving the report from the terminal device receiving, in response to the determination of the occurrence of the estimation failure, the report on an uplink channel, the report including a HARQ-ACK information bit; the uplink channel includes an estimation failure indicator.

20. The method of claim 19.

34. Receiving the report from the terminal device receiving said report on an uplink channel in accordance with said determination of an occurrence of said estimation failure; The uplink channel is scrambled with an artificial intelligence (AI) or machine learning (ML) specific scrambling sequence associated with the estimation failure.

20. The method of claim 19.

35. The scrambling sequence is generated based on a Radio Network Temporary Identity (RNTI) of the AL or ML; or the scrambling sequence is an AI / ML specific pseudo-random sequence, or The scrambling sequence is an AI / ML specific mask.

35. The method of claim 34.

36. A processor; a memory coupled to the processor and having instructions stored therein; Equipped with The instructions, when executed by the processor, perform operations including the method of any one of claims 1 to 18. Terminal device.

37. A processor; a memory coupled to the processor and having instructions stored therein; Equipped with The instructions, when executed by the processor, perform operations including a method according to any one of claims 19 to 35. Network device.

38. A computer-readable medium having instructions stored thereon, comprising: The instructions, when executed on at least one processor, cause the at least one processor to perform a method according to any one of claims 1 to 18 or any one of claims 19 to 35. Computer-readable medium.

Images