Apparatus and method for communication

Abstract

Embodiments of the present disclosure provide a solution for channel state information (CSI) reporting transmission. In the solution, a terminal device receives an indication from a network device for triggering a CSI report. The CSI report is configured for reporting a first type of CSI or is configured for model monitoring. The CSI report is associated with another CSI report. The other CSI report is configured for reporting a second type of CSI different from the first type or is configured for model monitoring. The terminal device performs transmission of the CSI report or omission of the transmission of the CSI report.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein relate generally to the field of communication technology, and more specifically to apparatus and methods for transmitting channel state information (CSI) reports. Background Technology

[0002] In some communication systems, the Channel Identity (CSI) of the communication channel between terminal equipment and network equipment is estimated at the receiving terminal equipment and reported to the network equipment. Using the CSI report, the network can control transmission based on the current channel conditions. As communication networks and services increase in size, complexity, and the number of users, operations within these networks can become increasingly complex.

[0003] To improve communication performance, the application of artificial intelligence (AI) / machine learning (ML) techniques to CSI estimation is proposed. For example, two-sided models can be used for CSI compression. In some cases, model monitoring can be performed for model-based CSI compression. For example, model monitoring can be based on CSI reports. Summary of the Invention

[0004] Typically, embodiments of this disclosure provide a solution for CSI report transmission.

[0005] In a first aspect, a terminal device is provided, comprising: a processor configured to cause the terminal device to: receive from a network device an instruction for triggering a CSI report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report being associated with another CSI report, and the other CSI report being configured to report a second type of CSI different from the first type or is configured for model monitoring; and to perform the transmission of the CSI report or an omission of the transmission of the CSI report.

[0006] In a second aspect, a terminal device is provided, comprising: a processor configured to cause the terminal device to: receive from a network device an instruction for triggering a CSI report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and transmit the CSI report to the network device.

[0007] In a third aspect, a network device is provided, comprising: a processor configured to cause the network device to: transmit to an end device an indication for triggering a CSI report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report being associated with another CSI report, and the other CSI report being configured to report a second type of CSI different from the first type or is configured for model monitoring; and receive the CSI report from the end device.

[0008] In a fourth aspect, a network device is provided, comprising: a processor configured to cause the network device to: transmit to an end device an indication for triggering a CSI report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and receive a CSI report from the end device.

[0009] In a fifth aspect, a communication method performed by a terminal device is provided. The method includes: receiving from a network device an instruction to trigger a CSI report, wherein the CSI report is configured to report a first type of CSI or configured for model monitoring, the CSI report being associated with another CSI report, and the other CSI report being configured to report a second type of CSI different from the first type or configured for model monitoring; and performing either the transmission of the CSI report or an omission of the transmission of the CSI report.

[0010] In a sixth aspect, a communication method performed by a terminal device is provided. The method includes: receiving from a network device an instruction to trigger a CSI report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and transmitting the CSI report to the network device.

[0011] In a seventh aspect, a communication method performed by a network device is provided. The method includes: transmitting to a terminal device an indication for triggering a CSI report, wherein the CSI report is configured to report a first type of CSI or configured for model monitoring, the CSI report being associated with another CSI report, and the other CSI report being configured to report a second type of CSI different from the first type or configured for model monitoring; and receiving the CSI report from the terminal device.

[0012] In an eighth aspect, a communication method performed by a network device is provided. The method includes: transmitting to a terminal device an indication for triggering a CSI report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and receiving the CSI report from the terminal device.

[0013] In a ninth aspect, a computer-readable medium is provided having instructions stored thereon that, when executed on at least one processor, cause at least one processor to perform the method according to the fifth, sixth, seventh, or eighth aspect.

[0014] Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0015] The above and other objects, features and advantages of this disclosure will become more apparent from the accompanying drawings, which describe some exemplary embodiments of this disclosure in more detail, wherein: Figure 1 An example communication environment in which example embodiments of this disclosure may be implemented is shown; Figure 2 The signaling stream of CSI report transmission according to some embodiments of this disclosure is shown; Figure 3 This illustrates the process used to determine the information in a CSI report; Figure 4 The process for monitoring network-side model performance is illustrated. Figure 5 Another signaling stream for CSI report transmission according to some embodiments of this disclosure is shown; Figure 6 A flowchart is shown illustrating a method implemented at a terminal device according to some example embodiments of the present disclosure; Figure 7 A flowchart is shown illustrating a method implemented at a terminal device according to some example embodiments of the present disclosure; Figure 8 A flowchart is shown illustrating a method implemented at a terminal device according to some example embodiments of the present disclosure; Figure 9 Flowcharts illustrating methods implemented at a network device according to some example embodiments of the present disclosure are shown; and Figure 10 A simplified block diagram of an apparatus suitable for implementing an example embodiment of the present disclosure is shown.

[0016] Throughout the accompanying drawings, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0017] The principles of this disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and to assist those skilled in the art in understanding and implementing this disclosure, and do not imply any limitation on the scope of this disclosure. The embodiments described herein can be implemented in various ways other than those described below.

[0018] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0019] As used herein, the term "terminal device" refers to any device with wireless or wired communication capabilities. Examples of terminal devices include, but are not limited to, user equipment (UE), personal computers, desktop computers, mobile phones, cellular phones, smartphones, personal digital assistants (PDAs), laptops, tablets, wearable devices, Internet of Things (IoT) devices, ultra-reliable and low-latency communication (URLLC) devices, Internet of Everything (IoE) devices, machine-type communication (MTC) devices, devices on vehicles used for V2X communications (where X represents a pedestrian, vehicle, or infrastructure / network), devices used for integrated access and backhaul (IAB), and space vehicles in non-terrestrial networks (NTN). Terminal devices can be airborne (including satellites and high-altitude platforms (HAPs) containing unmanned aerial vehicle systems (UAS), extended reality (XR) devices including different types of reality (such as augmented reality (AR), mixed reality (MR), and virtual reality (VR)), unmanned aerial vehicles (UAVs) commonly referred to as drones (which are aircraft without any human pilots), devices on high-speed trains (HSTs), or image capture devices (such as digital cameras), sensors, gaming devices, music storage and playback devices, or internet-connected appliances that enable wireless or wired internet access and browsing, etc. Terminal devices can also have "multicast / broadcast" characteristics to support public safety and mission-critical applications, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, radio services, software delivery over wireless, group communication, and IoT applications. They can also incorporate one or more subscriber identity modules (SIMs), such as those called multi-SIMs. The term "terminal device" can be used interchangeably with UE, mobile station, user station, mobile terminal, user terminal, or wireless device.

[0020] The term "network device" refers to a device that provides or hosts a cell or coverage area in which terminal devices can communicate. Examples of network devices include, but are not limited to, NodeB (or NB), evolved NodeB (eNodeB or eNB), next-generation NodeB (gNB), transceiver point (TRP), remote radio unit (RRU), radio head (RH), remote radio head (RRH), IAB node, low-power node (such as femtonode, piconode), reconfigurable smart surface (RIS), etc.

[0021] Terminal devices or network devices can have artificial intelligence (AI) or machine learning capabilities. This typically includes models that have been trained on large amounts of data collected for a specific function and can be used to predict some information.

[0022] Terminal or network devices can operate in several frequency ranges, such as FR1 (e.g., 450 MHz to 6000 MHz), FR2 (e.g., 24.25 GHz to 52.6 GHz), bands greater than 100 GHz, and terahertz (THz) bands. Terminal or network devices can also operate on licensed / unlicensed / shared spectrum. In multiple radio dual connectivity (MR-DC) applications, terminal devices can have more than one connection to network devices. Terminal or network devices can operate in full-duplex, flexible-duplex, and cross-division duplex modes.

[0023] The embodiments of this disclosure can be executed in test equipment, such as a signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, or channel simulator. In some embodiments, the terminal device can be connected to a first network device and a second network device. One of the first network device and the second network device can be a master node, and the other can be a slave node. The first network device and the second network device can use different Radio Access Technologies (RATs). In some embodiments, the first network device can be a first RAT device, and the second network device can be a second RAT device. In some embodiments, the first RAT device is an eNB, and the second RAT device is a gNB. Information related to different RATs can be transmitted from at least one of the first network device or the second network device to the terminal device. In some embodiments, first information can be transmitted from the first network device to the terminal device, and second information can be transmitted directly or via the first network device from the second network device to the terminal device. In some embodiments, information related to the configuration of the terminal device configured by the second network device can be transmitted from the second network device via the first network device. Information related to the reconfiguration of the terminal device configured by the second network device can be transmitted directly or via the first network device from the second network device to the terminal device.

[0024] As used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms, unless the context explicitly indicates otherwise. The term “comprising” and its variations should be understood as open-ended terms meaning “including, but not limited to.” The term “based on” should be understood as “at least partially based on.” The terms “one embodiment” and “embodiment” should be understood as “at least one embodiment.” The term “another embodiment” should be understood as “at least one other embodiment.” The terms “first,” “second,” etc., can refer to different or the same objects. Further explicit and implicit definitions may be included below.

[0025] In some examples, values, processes, or devices are referred to as “best,” “lowest,” “highest,” “smallest,” “maximum,” etc. It should be understood that such descriptions are intended to indicate that there are many functional alternatives to choose from, and that such a choice does not need to be better, smaller, higher, or more preferred than other choices.

[0026] As used herein, the terms "resource," "transmission resource," "uplink resource," or "downlink resource" can refer to any resource used to perform communication, such as resources in the time domain, frequency domain, spatial domain, code domain, or any other resource used to implement communication. In the following, unless explicitly stated otherwise, resources in the frequency and time domains will be used as examples of transmission resources used to describe some exemplary embodiments of this disclosure. Note that the exemplary embodiments of this disclosure are equally applicable to other resources in other domains.

[0027] As used in this article, the term "model" refers to the association between inputs and outputs learned from training data, and therefore can generate corresponding outputs for a given input after training. Model generation can be based on machine learning (ML) techniques. ML techniques can also be referred to as AI techniques. Typically, ML models can be built that receive input information and make predictions based on that input information.

[0028] As used herein, "model" is equivalent to AI, ML, AI / ML model, (AI / ML / auto) encoder, CSI generation part, UE part / side model, function, AI-enabled feature / FG, or data-driven / data processing algorithm / process that applies AI / ML technology to generate (AI / ML) output set based on (AI / ML) input set. The term "AI / ML-enabled feature" can refer to a feature that can use AI / ML. Furthermore, a model can be represented or indicated (or replaced) by a model identifier (ID), function, or function ID. As used herein, a model ID can be interchanged with function ID, dataset ID, scene ID, region ID, configuration ID, quantization ID, etc.

[0029] As used herein, the term “identifier” is interchangeable with indicator, identity, index, indication, and ID. The term “includes” is interchangeable with contain, indicate, and carry. The term “corresponds to” is interchangeable with “associated with,” “mapped to / mapped to,” or “used for.” The term “provides” is interchangeable with configure, activate, indicate, and trigger.

[0030] As used in this paper, the term "model inference" refers to the process of using a trained AI / ML model to produce an output set based on an input set. The term "model monitoring" refers to the process of monitoring the inference performance of an AI / ML model.

[0031] In the context of this disclosure, the terms "performance" and "performance metric" are used interchangeably. Furthermore, a "performance metric" can be determined by measurement, calculation, searching a lookup table, etc. Therefore, the term "performance (metric)" can also be replaced by "measured performance (metric)," "calculated performance (metric)," "determined performance (metric)," "obtained determined performance (metric)," etc.

[0032] As used herein, a model can be equivalent to at least one of the following: AI / ML model, ML model, AI model, data-driven, data processing model, algorithm, function, process, entity, feature, feature group, model ID, ID, function ID, configuration ID, scene ID, site ID, or dataset ID. Therefore, the above terms are used interchangeably.

[0033] In some embodiments, the model may be represented or associated with channels, resources, resource sets, reference signal (RS) resources, RS resource sets, RS ports, RS port sets, RS port IDs, or RS port ID sets.

[0034] In some embodiments, the model may include a set of weight values ​​that can be learned during training, for example for a particular architecture or configuration, where the set of weight values ​​may also be referred to as a set of parameters.

[0035] In some embodiments, the model can be used to predict future measurements of the beam set of the target cell or candidate cell set, based at least on historical measurements of the beam set of the candidate cell set (e.g., L1-RSRP, L1-SINR).

[0036] In some embodiments, the input of an ML model (i.e., AI input) may refer to the input of the model and indicate the data input into the model, which may be equivalent to data.

[0037] In some embodiments, the output of the ML model (i.e., the AI ​​output) can refer to the output of the model and indicate the result output by the model, which is equivalent to the label / data.

[0038] The principles and implementation of this disclosure will now be described in detail with reference to the accompanying drawings.

[0039] Figure 1 A schematic diagram of an example communication environment 100 in which exemplary embodiments of the present disclosure may be implemented is shown. In the communication environment 100, multiple communication devices, including terminal device 110 and network device 120, can communicate with each other.

[0040] exist Figure 1 In the example, terminal device 110 can be a UE, and network device 120 can be a base station serving the UE. The service area of ​​network device 120 can be referred to as a cell.

[0041] It should be understood that Figure 1 The number of devices and their connections shown are for illustrative purposes only and do not imply any limitation. Communication environment 100 may include any suitable number of devices configured to implement the exemplary embodiments of this disclosure. Although not shown, it should be understood that one or more additional devices may be located in a cell, and one or more additional cells may be deployed in communication environment 100. Note that although shown as a network device, network device 120 may be another device besides a network device. Although shown as a terminal device, terminal device 110 may be another device besides a terminal device.

[0042] In the following description, for illustrative purposes, some example embodiments are depicted in which terminal device 110 operates as a UE and network device 120 operates as a base station. However, in some example embodiments, the operations described in connection with the terminal device can be implemented at the network device or other devices, and the operations described in connection with the network device can be implemented at the terminal device or other devices.

[0043] In some example embodiments, if terminal device 110 is a terminal device and network device 120 is a network device, the link from network device 120 to terminal device 110 is referred to as a downlink (DL), and the link from terminal device 110 to network device 120 is referred to as an uplink (UL). In the DL, network device 120 is a transmitting (TX) device (or transmitter), and terminal device 110 is a receiving (RX) device (or receiver). In the UL, terminal device 110 is a TX device (or transmitter), and network device 120 is an RX device (or receiver).

[0044] The communications in the communications environment 100 can conform to any suitable standard, including but not limited to Global System for Mobile Communications (GSM), Long Term Evolution (LTE), LTE Evolution, LTE-A Advanced, New Radio (NR), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), GSM EDGE Radio Access Network (GERAN), Machine Type Communication (MTC), etc. Embodiments of this disclosure can be implemented according to any generation of communication protocols currently 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, advanced 5G networks, or sixth-generation (6G) networks.

[0045] In some embodiments, one or more models may be deployed at terminal device 110 and / or network device 120. For example, a first model, such as an AI / ML encoder, may be deployed at terminal device 110. A second model, such as an AI / ML decoder, may be deployed at network device 120. The first and second models may jointly perform AI / ML-based functions, such as CSI compression. For example, the first model may encode channel estimation information into bits. The encoded bits may include, for example, an AI pre-code / decode matrix indicator (PMI). The second model may decode the encoded bits into AI CSI. In this way, CSI compression based on a two-sided model is achieved.

[0046] In some embodiments, the performance of a first model and a second model can be monitored. For example, terminal device 110 and / or network device 120 can perform model monitoring. In some embodiments, network device 120 monitors multiple performance metrics and makes multiple decisions regarding model-related operations such as selection, activation, deactivation, switching, rollback, etc.

[0047] As described above, AI / ML techniques for CSI estimation are proposed. For example, a two-sided model can be used for CSI compression. In some mechanisms, network (NW) side performance monitoring can be performed for CSI compression. That is, the network can monitor performance and make decisions on model activation / deactivation / update / switching. Alternatively, in some mechanisms, user equipment (UE) side performance monitoring can be performed. The UE can monitor performance and report to the network. The network can then make decisions on model activation / deactivation / update / switching.

[0048] The potential coexistence and fallback mechanisms between AI / ML-based and non-AI / ML-based CSI feedback models need to be considered. In some mechanisms, intermediate key performance indicators (KPIs) such as the square of generalized cosine similarity (SGCS) and / or final KPIs such as throughput, hypothesis block error rate (BLER), negative acknowledgment (NACK) / acknowledgment (ACK) can be considered for performance monitoring. In some mechanisms, for monitoring based on traditional CSI (such as non-AI / ML-based CSI monitoring), a scheme using additional traditional CSI reports can be considered. In such mechanisms, other monitoring methods have been proposed, such as monitoring based on input or output data. For example, data drift between the training dataset and the observed dataset, as well as out-of-distribution detection, can be used.

[0049] In the use case of CSI compression using a two-sided model, the necessity, feasibility, and potential canonical impacts of monitoring based on intermediate KPIs are discussed. NW-based monitoring can be performed based on a target CSI that is associated with a CSI report, reported by the UE, or obtained from the UE side based on realistic channel estimates.

[0050] In some mechanisms, UE-side monitoring can be based on the output of a reconstructed CSI model, conforming to an aligned format, and associated with a CSI report, either indicated by the network or obtained from the network side. For example, the network can configure threshold criteria to facilitate UE-side model monitoring.

[0051] In some mechanisms, UE-side monitoring can be based on the output of the UE-side CSI reconstruction model. For example, the UE-side CSI reconstruction model may be the same as or different from the actual CSI reconstruction model used by the network. The network can configure threshold criteria to facilitate UE model monitoring. In some mechanisms, Radio Resource Control (RRC) signaling and / or Layer 1 (L1) signaling procedures can be applied to enable rapid identification of AI / ML model performance.

[0052] Other solutions need to be considered, such as UE-side monitoring using models that directly output intermediate KPIs, and / or NW-side monitoring based on target CSI measured via probe reference signals (SRS) from the UE. Network-side monitoring based on target CSI measured from the UE via SRS is also possible. It should be noted that monitoring methods not based on intermediate KPIs are not excluded. It should also be noted that studies of intermediate KPI-based monitoring may consider monitoring reliability (accuracy), overhead, complexity, and latency.

[0053] In CSI compression using two-sided model use cases, for NW-side monitoring, the necessity, feasibility, and potential regulatory impact of using existing CSI feedback schemes as a reference to make performance monitoring possible need to be discussed. For example, the correlation between AI / ML schemes and existing CSI feedback schemes used for monitoring needs to be considered. It should be noted that the metrics used for monitoring and comparison include intermediate KPIs and final KPIs. Other aspects are not excluded.

[0054] In some mechanisms, regarding NW monitoring, the UE needs to report both the AI ​​CSI (i.e., the CSI obtained from the AI / ML model) and the target CSI (i.e., the ground-truth CSI) to the network. In other methods, the UE can report the AI ​​CSI and the target CSI separately. That is, a first CSI report carrying the AI ​​CSI and a second CSI report carrying the target CSI can be reported to the network separately. The first CSI report can be associated with the second CSI report. The network needs to identify the association between the target CSI in the second CSI report and the AI ​​CSI in the first CSI report.

[0055] In some mechanisms, for network-side monitoring based on final KPIs or traditional CSI feedback, the UE needs to report the complete AI CSI and the complete target CSI. This means that all information in both the AI ​​CSI and the target CSI needs to be reported to the network. However, in some cases, the network may not receive the complete AI CSI or the complete target CSI. For example, if the first CSI report for the AI ​​CSI is not sent by the UE or is not fully sent by the UE, the network may not receive the complete AI CSI. Similarly, if the second CSI report for the target CSI is not sent by the UE or is not fully sent by the UE, the network may not receive the complete target CSI. Furthermore, if neither the first nor the second report is sent or fully sent by the UE, the network may not receive either the complete AI CSI or the complete target CSI. In these cases, the network cannot receive the complete AI CSI and / or the complete target CSI, and therefore cannot perform model monitoring.

[0056] In some mechanisms, for network-side monitoring based on intermediate KPIs, the UE may not need to report the complete AI CSI and the complete target CSI. This means that not all information in the AI ​​CSI or target CSI needs to be reported to the network. Specifically, the following scenarios may exist. The first scenario (referred to as Scenario 1) could be that the network determines the Rank Indicator (RI) and instructs it to the UE. For AI CSI, the UE reports at least the AI ​​PMI and may also report the New Indicator (NI). For target CSI, the UE reports at least the target PMI and the KPI. NZ .

[0057] The second scenario (referred to as Scenario 2) could involve the network identifying multiple RIs and indicating them to the UE. For AI CSI, the UE reports at least multiple AI PMIs corresponding to the indicated RI, and reports (multiple) NIs. For Target CSI, the UE reports at least multiple Target PMIs corresponding to the indicated RI and multiple Ks corresponding to the indicated RI. NZ The third scenario (referred to as Scenario 3) can be that the UE determines the RI, that is, the same as in Scenario 1, the UE reports the complete AI CSI and the complete target CSI.

[0058] In scenarios 1 / 2 / 3, when CSI omission occurs for the first CSI report and / or the second CSI report, for example, when the first CSI report and / or the second CSI report is not sent by the UE or is not fully sent, the network may be unable to perform model monitoring.

[0059] To address at least some of the aforementioned or other potential problems, a solution regarding CSI report transmission is proposed. In this solution, a terminal device receives an instruction from a network device to trigger a CSI report, configured to report a first type of CSI or configured for model monitoring. The CSI report is associated with another CSI report configured to report a second type of CSI different from the first type or configured for model monitoring. The terminal device performs either the transmission of the CSI report or omits the transmission of the CSI report. Thus, the terminal device can transmit or omit a CSI report in response to an instruction, reducing unnecessary reporting overhead.

[0060] Figure 2 Signaling stream 200 for CSI report transmission according to some embodiments of this disclosure is illustrated. For discussion purposes, reference will be made to... Figure 1 For example, signaling flow 200 can be discussed using terminal device 110 and network device 120.

[0061] In operation, network device 120 transmits an instruction (210) to terminal device 110 to trigger a CSI report. The CSI report is configured to report a first type of CSI or is configured for model monitoring. The CSI report is associated with another CSI report, which is configured to report a second type of CSI different from the first type or is configured for model monitoring. Terminal device 110 receives (220) the instruction. As an example, the instruction may be transmitted via RRC, Media Access Control Element (MACCE), Downlink Control Information (DCI), or any other suitable message or signaling (210).

[0062] Terminal device 110 performs (230) the transmission of a CSI report or omits the transmission of a CSI report. In some embodiments, terminal device 110 transmits a CSI report to network device 120. Network device 120 may receive the CSI report.

[0063] Alternatively, in some embodiments, terminal device 110 omits the transmission of CSI reports. As used herein, omitting the transmission of CSI reports means that terminal device 110 does not transmit or send CSI reports, or that CSI reports are omitted entirely. The description “terminal device 110 omits the transmission of CSI reports” as used herein can be interchanged with at least one of the following: terminal device 110 omits or ignores CSI reports; CSI reports are not sent by terminal device 110; or CSI (or at least one piece of information or measurement in a CSI report) is not updated by terminal device 110. Thus, for a CSI report, terminal device 110 can decide how to process the CSI report if the associated CSI report (such as the associated most recent CSI) meets certain conditions. Further embodiments regarding the transmission or omission of CSI reports will be described.

[0064] In some embodiments, a CSI report and / or another CSI report are configured for model monitoring. For a CSI report, it can be considered a CSI report configured for model monitoring if at least one of the following conditions is met: The first condition may be that configuration related to model monitoring is provided to terminal device 110 prior to the transmission of the CSI report. The second condition may be that the CSI report is transmitted or triggered during the duration configured for model monitoring. It should be understood that these two conditions are for illustrative purposes only and do not imply any limitation. These conditions and any other suitable conditions may be applied in any suitable combination. The scope of this disclosure is not limited thereto.

[0065] As described above, a CSI report is associated with another CSI report. As used herein, the other CSI report associated with a CSI report may also be referred to as an "associated CSI report." In an example embodiment, a CSI report is associated with another CSI report if the trigger state associated with the CSI report is the same as the trigger state of another CSI report. For example, the trigger state could be CSI-AperiodicTriggerState or CSI-SemiPersistentOnPUSCH-TriggerState. In another example embodiment, a CSI report is associated with another CSI report if the identifier associated with the CSI report (such as CSI-ReportConfigId) is the same as the identifier associated with another CSI report. In another embodiment, a CSI report is associated with another CSI report if the CSI measurement resource associated with the CSI report is the same as the CSI measurement resource associated with another CSI report. In yet another embodiment, a CSI report is associated with another CSI report if the CSI report and the other CSI report are within a predefined duration or time interval.

[0066] Examples of two related CSI reports have been described. These examples are for illustrative purposes and do not imply any limitation. In the following description, a CSI report and another CSI report will be described as two related CSI reports.

[0067] In some embodiments, the other CSI report is the most recent CSI report associated with the CSI report. For example, the other CSI report could be the most recent associated CSI report transmitted before the CSI report. In another example, the other CSI report could be the most recent associated CSI report transmitted after the CSI report. The order of the CSI report and the other CSI report is not limited thereto. In the following description, it is assumed that the other CSI report is the most recent associated CSI report of the CSI report.

[0068] Several types of CSI exist. For example, CSI determined based on AI / ML models (such as two-sided models) can be called AICSI. As another example, non-AI CSI can refer to CSI that is not determined based on AI / ML models. As used herein, the term "non-AI CSI" may also be referred to as "target CSI," "output CSI by terminal device 110," or "output-CSI-UE." In some embodiments, target CSI may be considered as "high-resolution CSI" or "truth-valued CSI."

[0069] In some embodiments, one of the first type of CSI and the second type of CSI is determined based on an AI / ML model, while the other is not determined based on an AI / ML model. In other words, one of the first type of CSI and the second type of CSI is an AI CSI, while the other is a non-AI CSI or a target CSI. As used herein, the first type of CSI may also be referred to as the first CSI, and the second type of CSI may also be referred to as the second CSI.

[0070] In some embodiments, terminal device 110 may be configured, activated, or triggered by network device 120 using the same signaling or two separate signaling or messages to utilize two CSI reports (CSI report and another CSI report). The CSI report and / or the other CSI report may be periodic, semi-persistent, or aperiodic. For example, the other CSI report may be triggered by a received (220) indication or other indication or message.

[0071] In some embodiments, terminal device 110 may determine CSI, such as AI CSI or target CSI. For example, terminal device 110 may determine or calculate AI CSI and target CSI based on a CSI reference signal (RS), such as by measuring CSI-RS. In some embodiments, the term "RS" may be used interchangeably with "RS resource" or "CSI measurement resource". RS resources may be configured for terminal device 110. For example, network device 120 may transmit CSI-RS to terminal device 110.

[0072] Figure 3 An example diagram of process 300 for CSI determination is shown. Process 300 can be implemented by terminal device 110. As shown, terminal device 110 can estimate the channel to obtain channel estimate 310. Precoding matrix 315 can be determined based on channel estimate 310. Quantization process 320 is performed on precoding matrix 315 to obtain target PMI 330. For example, scalar quantization or codebook-based quantization can be performed for target CSI to obtain target PMI 330. Encoder 325 (such as an AI / ML model-based encoder) can obtain AI PMI 335 based on precoding matrix 315. AI PMI can be coded bits. Terminal device 110 can determine AI CSI based on AI PMI 335. Terminal device 110 can determine target CSI based on target PMI 330.

[0073] The target PMI 330 may indicate one or more parameters determined based on a codebook. As used herein, the term "target PMI (information)" may be used interchangeably with non-AI PMI, conventional PMI, PMI, or eType II (i.e., enhanced type II) PMI. It may include a set of parameters (e.g., i1, i2) associated with a codebook (e.g., an eType II codebook). In some embodiments, scalar quantization and / or codebook-based quantization may be applied to the truth PMI, such as the target PMI.

[0074] As used herein, the term “AI PMI (Information)” may be interchanged with coded bits, compressed bits, quantized bits, latent space, encoder output, or output CSI. It may include a set of binary bits (e.g., 0, 1).

[0075] In some embodiments, AI CSI may include at least one of the following: Rank Indicator (RI), Channel Quality Indicator (CQI), New Indicator (NI), or AI PMI. Target CSI may include at least one of the following: RI, CQI, First Indicator, or Target PMI (such as the PMI of Enhanced Type 2 CSI). Details of these contents or parameters will be described.

[0076] In some embodiments, a CSI report, such as a CSI report including a target CSI (also known as a target CSI report) or a CSI report including an AICSI (also known as an AI CSI report), may include two parts. For example, the first part (also known as part 1) may have a fixed payload size and may be used to identify the number of information bits in the second part (also known as part 2). Part 1 may be transmitted entirely before part 2.

[0077] As an example, a CSI report including a target CSI may include Part 1 and Part 2. Part 1 may include the RI (if reported), CQI, and First Indication. The First Indication (also known as "K")... NZ "" indicates the total number of non-zero coefficients summed across all layers or the total number of non-zero amplitude coefficients across layers. As used herein, the RI in a CSI report for a target CSI may be referred to as the target RI, and the CQI in a CSI report for a target CSI may be referred to as the target CQI. Section 2 of a CSI report for a target CSI may include the target PMI.

[0078] As used herein, the term "RI" may be used interchangeably with "Layer Indicator" (LI). As used herein, the term "RI" refers to rank indicator / identifier / indicator / index, rank indicator / identifier / indicator / index, and rank indicator / identifier / indicator / index of indicator / identifier / indicator / index. As used herein, the term "LI" may refer to layer indicator / identifier / indicator / index, layer indicator / identifier / indicator / index, and layer indicator / identifier / indicator / index of indicator / identifier / indicator / index.

[0079] In some embodiments, for Type I, Type II, Enhanced Type II, and Further Enhanced Type II Port Selection CSI feedback on the Physical Uplink Shared Channel (PUSCH), the CSI report (such as the target CSI) may include two parts. For example, Part 1 may have a fixed payload size and may be used to identify the number of information bits in Part 2. Part 1 may be transmitted entirely before Part 2. For Enhanced Type II CSI feedback and Further Enhanced Type II Port Selection CSI feedback, Part 1 may include RI (if reported), CQI, and K. NZ Part 1 fields - RI (if reporting), CQI, and K NZ They can be encoded separately. Part 2 may contain a PMI for Enhanced Type II or Further Enhanced Type II Port Selection CSI. Parts 1 and 2 are encoded separately.

[0080] In some embodiments, the target CSI may include at least a CQI for the first codeword, and the CQI (information) may include a wideband CQI (information) and at least one subband CQI (information) or subband differential CQI.

[0081] In some embodiments, for a CSI report that includes AI CSI (also referred to as an “AI CSI report”), part 1 of the CSI report may include an RI, a CQI, and a new indicator (NI). As used herein, the NI may also be referred to as a second indicator. The NI may be an identifier associated with information representing factors indicating the size and / or model of a particular CSI payload, such as a UE part model compatible with the network part model used by the gNB, a rank, a quantization method / granularity, the size of the potential space from the scalable dimension for each layer, etc. In some embodiments, the RI may be equivalent to the NI, or vice versa. As used herein, the RI in a CSI report for AI CSI may be referred to as an AI RI, and the CQI in a CSI report for AI CSI may be referred to as an AI CQI. The AI ​​CQI (information) may include a wideband CQI (information) and at least one subband CQI (information) or subband differential CQI.

[0082] Part 2 of the AI ​​CSI report may include the AI ​​PMI. The AI ​​PMI can indicate one or more bits determined based on an AI / ML model. The structure of the AI ​​PMI can be layer-wise, sub-band-wise, or antenna port-wise. In other words, the AI ​​PMI can be scaled using layers, sub-bands, or antenna ports.

[0083] In some embodiments, AI RI may be the same as the target RI. AI RI or target RI may be interchanged with RI. RI may be interchanged with LI. AI CQI may be the same as the target CQI. AI CQI or target CQI may be interchanged with CQI.

[0084] In some embodiments, for CSI compression using a two-sided model use case, if a CQI is configured in the CSI report, there are several options for determining the CQI in the CSI report. In a first option (referred to as Option 1), the CQI is not calculated based on the output of the CSI reconstruction portion from the actual channel estimation. Option 1 may include Options 1a, 1b, and 1c. For Option 1a, the CQI may be calculated based on a target CSI with actual channel measurements. For Option 1b, the CQI may be calculated based on a target CSI with actual channel measurements and potential adjustments. For Option 1c, the CQI may be calculated based on a conventional codebook. In a second option (referred to as Option 2), the CQI is calculated based on the output of the CSI reconstruction portion from the actual channel estimation. Option 2 may include Options 2a and 2b. For Option 2a, if the CSI reconstruction model is available at the UE and the UE can perform reconstruction model inference with potential adjustments, the CQI may be calculated based on the CSI reconstruction output.

[0085] It should be noted that the CSI reconstruction portion at terminal device 110 may differ from the actual CSI reconstruction portion used at the NW. For option 2b, a two-stage method is used to calculate the CQI, whereby the UE derives the CQI using precoded CSI-RS transmitted with the reconstructed precoder. It should be understood that other options are not excluded. The feasibility of different options can be evaluated. The gap analysis between the UE-side CQI calculation results and the NW-side results, as well as the impact on scheduling performance, can be evaluated. The complexity of CQI calculation needs to be evaluated, including computational complexity and potential RS / signaling overhead.

[0086] Several embodiments regarding the content or information in the first and second parts of a CSI report for AI CSI and a CSI report for target CSI have been described. It should be understood that these example embodiments are for illustrative purposes only and do not imply any limitation. Any suitable content or information may be included in the first or second part of the CSI report.

[0087] Return to Figure 2 In some embodiments, terminal device 110 may not expect the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH to be greater than the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH. For example, terminal device 110 may not expect the number of encoded / decoded modulation symbols for a CSI report (e.g., CSI section 2) transmitted on the PUSCH to be greater than the number of available / configurable encoded / decoded modulation symbols for a CSI report (e.g., CSI section 2) transmitted on the PUSCH.

[0088] As used herein, the aforementioned unexpected event can be referred to as “Event-1”. Unexpected Event-1 can be represented as follows (1).

[0089] (1) in This indicates the number of bits for CSI part 2; This indicates the number of Cyclic Redundancy Check (CRC) bits for CSI Part 2; Configured by higher-level parameters; This refers to the number of code blocks in the UL shared channel (SCH) for PUSCH transmission. It refers to the size of the r-th code block of UL-SCH for PUSCH transmission; It is the total number of orthogonal frequency division multiplexing (OFDM) symbols for UL-SCH transmission for PUSCH. It can be used in OFDM symbols during PUSCH transmission. ( The number of resource elements transmitting uplink control information (UCI) in the ), and This is the total number of OFDM symbols for PUSCH, including all OFDM symbols used for demodulation reference signals (DMRS); for any OFDM symbol carrying the DMRS of PUSCH, For any OFDM symbol that does not carry a PUSCH, ; In PUSCH transmission in OFDM symbols The number of subcarriers carrying the phase tracking reference signal (PTRS); By higher-level parameters Scaling To configure; the number of encoded / decoded modulation symbols for each layer used in CSI Part 1 transmission is expressed as The number of encoded / decoded modulation symbols per layer used for Hybrid Automatic Repeat Request (HARQ)-Acknowledgment (ACK) and Configuration Grant (CG)-UCI transmissions is expressed as follows: The number of encoded / decoded modulation symbols per layer used for CG-UCI transmission is expressed as follows: , It can be or .

[0090] In some embodiments, a CSI report may be transmitted if the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH is less than or equal to the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH. Terminal device 110 may not expect CSI omissions for both the CSI report and another CSI report. If the above conditions are met, normal model monitoring on the network side can be supported by transmitting CSI reports.

[0091] In some embodiments, a CSI report may have a higher priority than a CSI report that does not include either the first type of CSI or the second type of CSI. For example, a CSI report that includes AI CSI or target CSI may have a higher priority than a CSI report that does not include either AI CSI or target CSI. Alternatively or additionally, in some embodiments, a CSI report may have a higher priority than a CSI report that is not configured for model monitoring.

[0092] In some embodiments, terminal device 110 may assume that a CSI report has a higher priority than another CSI report that meets at least one of the following conditions: The first condition may be that the other CSI report does not include AI CSI or target CSI. The second condition may be that the other CSI report is not configured for model monitoring. In other words, the priority value associated with the CSI report is lower than the priority value associated with the other CSI report.

[0093] In some embodiments, the CSI report may be transmitted by the terminal device 110 in several scenarios. For example, a first scenario may be that another CSI report has been transmitted. A second scenario may be that another CSI report has been fully transmitted. A third scenario may be that another CSI report has been updated. As used herein, an updated CSI report means that at least one piece of information or measurement in the CSI report has been updated. The CSI report may be transmitted in response to at least one of the above scenarios or any other suitable scenario.

[0094] As used herein, a CSI report being fully transmitted or fully sent means that all information in the CSI report is fully transmitted by terminal device 110. In other words, the number of encoded / decoded modulation symbols for the associated CSI portion (e.g., CSI portion 2) transmitted on the PUSCH is no greater than the number of available / configurable encoded / decoded modulation symbols for the associated CSI portion (e.g., CSI portion 2) transmitted on the PUSCH. In some embodiments, a CSI report can be fully transmitted if the following (2) is satisfied.

[0095] (2) in This indicates the number of bits for CSI part 2; This indicates the number of CRC bits for CSI part 2; Configured by higher-level parameters; This refers to the number of UL-SCH code blocks transmitted via PUSCH. It refers to the size of the r-th code block of UL-SCH for PUSCH transmission; It is the total number of OFDM symbols for UL-SCH transmissions for PUSCH. It can be used in OFDM symbols during PUSCH transmission. ( The number of UCI resource elements transmitted in the data, and It is the total number of OFDM symbols for PUSCH, including all OFDM symbols used for DMRS; for any OFDM symbol carrying PUSCH in DMRS, For any OFDM symbol that does not carry a PUSCH, ; In PUSCH transmission in OFDM symbols The number of subcarriers carrying PTRS; By higher-level parameters Scaling To configure; the number of encoded / decoded modulation symbols for each layer used in CSI Part 1 transmission is expressed as The number of encoded / decoded modulation symbols for each layer used in HARQ-ACK and CG-UCI transmissions is expressed as follows: The number of encoded / decoded modulation symbols per layer used for CG-UCI transmission is expressed as follows: , It can be or .

[0096] For the (most recent) CSI report associated with a CSI report, if the most recent CSI report (also known as the associated CSI report) meets the three scenarios described above, then terminal device 110 may not expect event-1 to occur for the CSI report. Alternatively or additionally, terminal device 110 may assume that the CSI report has a higher priority than another CSI report that does not include AI CSI or target CSI or another CSI report that is not configured for model monitoring.

[0097] In some embodiments, if no CSI omission occurs for another CSI report associated with a CSI report, the terminal device 110 may not expect a CSI omission for that CSI report. A CSI report can have a higher priority than another CSI report. In this way, normal model monitoring on the network side can be ensured.

[0098] Alternatively or additionally, in some embodiments, the transmission of CSI reports may be omitted in several different scenarios. For example, an example scenario may be that another CSI report has not yet been transmitted. Another example scenario may be that another CSI report has not yet been fully transmitted. A CSI report not being fully transmitted or sent means that not all information in the CSI report (such as information in CSI Part 1 or CSI Part 2) has been transmitted by the terminal device 110. In other words, if (1) is satisfied, the CSI report has not been fully transmitted. Another example scenario may be that another CSI report has not yet been updated. A CSI report not being updated means that at least one piece of information or measurement in the CSI report has not been updated. In response to any of these scenarios or any other suitable scenario, the transmission of CSI reports may be omitted.

[0099] For CSI reports, terminal device 110 may not send a CSI report if the (most recent) associated CSI report was not sent by terminal device 110 or was not fully sent by terminal device 110, or if the associated CSI report has not been updated. That is, if a CSI omission occurs in another CSI report associated with a CSI report, terminal device 110 may not transmit the CSI report. In this way, unnecessary reporting overhead can be reduced.

[0100] In some embodiments, if the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH is greater than the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH, the transmission of the CSI report is omitted. That is, if event-1 as shown in (1) occurs for a CSI report or another CSI report, the terminal device 110 may not transmit the CSI report or another CSI report. For example, if event-1 as shown in (1) occurs for a CSI report, i.e., the number of encoded / decoded modulation symbols for a CSI report (e.g., CSI section 2) transmitted on the PUSCH is greater than the number of available / configurable encoded / decoded modulation symbols for a CSI report (e.g., CSI section 2) transmitted on the PUSCH, the CSI report is not transmitted by the terminal device 110. In this way, unnecessary reporting overhead can be reduced.

[0101] In some mechanisms, the terminal device can report CQI information in the first CSI report. The terminal device can also report CQI information in a second CSI report associated with the first CSI report. However, these two CQI reports may be completely identical (because the determination methods may be the same), which will result in unnecessary reporting overhead and power consumption for the terminal device.

[0102] To at least address such problems, according to some embodiments of this disclosure, a CSI report may exclude a CQI if at least one condition is met. For example, terminal device 110 may not determine or calculate a CQI. Terminal device 110 may also choose not to report a CQI. In other words, terminal device 110 does not expect to determine or report a CQI for the CSI report. The first condition may be that another CSI report associated with the CSI report includes a CQI or CQI-related information. The second condition may be that another CSI report has been transmitted by terminal device 110. The third condition may be that another CSI report has been fully transmitted by terminal device 110. The fourth condition may be that another CSI report has been updated. For example, the CQI in the other CSI report has been updated. It should be understood that these example conditions are for illustrative purposes only and do not imply any limitation. These conditions and any other suitable conditions may be applied in any suitable manner. The scope of this disclosure is not limited thereto.

[0103] Similarly, in some embodiments, a CSI report may exclude an RI if at least one condition is met. That is, terminal device 110 may not determine or report an RI. In other words, terminal device 110 may not expect to determine or report an RI for the CSI report. The first condition for excluding an RI may be that another CSI report associated with the CSI report includes an RI or RI-related information. The second condition may be that another CSI report has been transmitted by terminal device 110. The third condition may be that another CSI report has been fully transmitted by terminal device 110. The fourth condition may be that another CSI report has been updated. For example, the RI in the other CSI report has been updated. It should be understood that these example conditions are for illustrative purposes only and do not imply any limitation. These conditions and any other suitable conditions may be applied in any suitable manner. The scope of this disclosure is not limited thereto.

[0104] Excluding CQI and / or RI from CSI reports reduces unnecessary reporting overhead. Furthermore, it reduces power consumption of end devices.

[0105] In some embodiments, terminal device 110 may transmit a CSI report to network device 120. Terminal device 110 may also transmit another CSI report to network device 120. One of the CSI report and the other CSI report may include AI CSI, and the other may include target CSI. Network device 120 may perform model monitoring based on the received CSI report and the other CSI report. That is, network device 120 may perform model monitoring based on AI CSI and target CSI.

[0106] In some embodiments, model monitoring may be based on final KPIs or CSI feedback or CSI reports. Examples of final KPIs may include, but are not limited to, throughput, assumption BLER, BLER, NACK / ACK, etc. Alternatively or additionally, in some embodiments, model monitoring may be based on intermediate KPIs such as SGCS. It should be understood that these example factors or KPIs are for illustrative purposes only and do not imply any limitations. Any suitable KPI can be applied to network-side model monitoring. The scope of this disclosure is not limited thereto.

[0107] Network device 120 can perform model monitoring based on final KPIs or intermediate KPIs, based on the CSI report and the AI ​​CSI and target CSI in another CSI report. As used herein, the final KPI and / or intermediate KPI can be referred to as performance monitoring metrics.

[0108] Figure 4 An example diagram of a process 400 for model monitoring is shown. Process 400 can be implemented by network device 120. Network device 120 can obtain AI PMI and target PMI from AI CSI and target CSI. For example, AI PMI could be... Figure 3 The AI ​​PMI is 335, and the target PMI can be... Figure 3 The target PMI 330 is shown in the figure. A dequantization process 410 can be performed on the target PMI 330 to obtain the target precoded matrix 430. A decoder (such as an AI / ML-based decoder 420) can decode the AIPMI 335 into an AI precoded matrix 440. It should be understood that the dequantization process 410 can be combined with... Figure 3 The quantization process in step 320 is the reverse. Decoder 420 can be used with... Figure 3 The encoder 325 is associated with this. That is, the operation or process performed by the decoder 420 can be the reverse of the operation or process of the encoder 325. Based on the target precoding matrix 430 and the AI ​​precoding matrix 440, a performance monitoring metric 450 can be determined. Furthermore, other information in the target CSI and / or the AI ​​CSI can be used to determine the performance monitoring metric 450. For example, a final KPI such as throughput can be determined based on the target precoding matrix 430 and the AI ​​precoding matrix 440, the target CSI, and / or any other suitable information in the AI ​​CSI. For another example, an intermediate KPI such as SGCS can be determined based on the target precoding matrix 430 and the AI ​​precoding matrix 440, the target CSI, and / or the AI ​​CSI. Model monitoring can be performed based on the performance monitoring metric 450.

[0109] An embodiment of network-side model monitoring based on a CSI report and another CSI report has been described. The CSI report and another CSI report can be transmitted according to embodiments of this disclosure. In this way, network-side model monitoring can be ensured.

[0110] As mentioned above, in some mechanisms, for network-side monitoring based on intermediate KPIs, the terminal device may not need to report the complete AI CSI and the complete target CSI. For example, in Scenario 2, the network identifies multiple RIs and indicates them to the terminal device. For AI CSI, the terminal device reports at least the AI ​​PMIs corresponding to the indicated RI and multiple AI PMIs corresponding to the reported RI. For target CSI, the terminal device reports at least the target PMIs corresponding to the indicated RI and multiple KPIs corresponding to the indicated RI. NZ .

[0111] In scenario 2, when event-1 in (1) occurs for the first CSI report (e.g., a CSI report including AI CSI), the terminal device may omit a portion of the AI ​​CSI. As a possible example, the terminal device may omit the AI ​​PMI corresponding to a certain rank / RI. Suppose that for the first CSI report, AI PMIs corresponding to 4 ranks (i.e., rank = 1, 2, 3, 4) may already be included in the first CSI report. When event-1 occurs, the terminal device omits the PMIs corresponding to 2 ranks (e.g., rank = 3 and rank = 4).

[0112] When no CSI omission occurs in the second CSI report (e.g., a CSI report including the target CSI), the terminal device can report the complete second CSI report. This means that the target PMI corresponding to rank 4 can be reported to the network. Therefore, model monitoring can perform normally. However, the target PMIs corresponding to rank=3 and rank=4 appear to be useless to the network, resulting in unnecessary reporting overhead.

[0113] When a CSI is omitted in the second CSI report, the terminal device may omit a portion of the target CSI. For example, the terminal device may omit the target PMI corresponding to a certain rank(s). If the rank corresponding to the omitted target PMI is different from the rank corresponding to the omitted AI PMI (e.g., the target PMIs corresponding to ranks 1 and 2 are omitted), model monitoring may not be performed. Reporting resources will be wasted.

[0114] To at least address the problems in Scenario 2, according to some embodiments of this disclosure, if the transmission of the first portion of information in another CSI report is omitted, the transmission of the second portion of information in the CSI report is also omitted. The second portion of information corresponds to the first portion of information. For example, the first portion of information may include at least one PMI corresponding to at least one rank in a second type of CSI, and the second portion of information may include at least one PMI corresponding to at least one rank in a first type of CSI.

[0115] As an example, if another CSI report associated with a CSI report is not fully transmitted by terminal device 110, for example, if some information in the other CSI report is omitted or event-1 occurs, terminal device 110 may omit some information in the CSI report based on CSI omissions corresponding to or applied to the other CSI report.

[0116] In some embodiments, if a CSI corresponding to a first group rank is omitted in another CSI report, the terminal device 110 may omit partial information in the CSI report based on the CSI omission corresponding to the other CSI report. For example, the CSI omission may correspond to a first group rank, such as rank=3 and rank=4, and the terminal device 110 may omit the CSIs corresponding to the first group rank (such as rank=3 and rank=4). In embodiments where another CSI report includes an AI PMI, the terminal device 110 may omit the target PMI corresponding to the first group rank in the CSI report. Alternatively, in some embodiments, such partial information omission may occur when event-1 occurs for a CSI report, but may not occur for CSIs corresponding to the omission of the first group rank.

[0117] By omitting certain information in the CSI report, the same CSI omissions can be maintained between the two reports, such as consistent omission rank. This ensures normal model monitoring on the network side and reduces unnecessary reporting overhead. Furthermore, this information omission avoids wasting reporting resources.

[0118] Several embodiments regarding CSI report transmission have been described. These embodiments can ensure network-side model monitoring and reduce unnecessary reporting overhead. Another solution regarding CSI report transmission is also proposed in this disclosure. In this solution, the terminal device receives an instruction from the network device to trigger a CSI report. The CSI report is configured to report a first type of CSI or to be configured for model monitoring. The terminal device transmits the CSI report to the network device. The network device receives the CSI report. Network-side model monitoring can be ensured.

[0119] Figure 5 Signaling stream 500 for CSI report transmission according to some embodiments of this disclosure is shown. For discussion purposes, reference will be made to... Figure 1 For example, signaling flow 500 can be discussed using terminal device 110 and network device 120.

[0120] In operation, network device 120 transmits (510) an indication to terminal device 110 to trigger a CSI report, which is configured to report a first type of CSI or to be configured for model monitoring. As an example, the indication may be transmitted (510) via RRC, MAC CE, DCI, or any other suitable message or signaling. Terminal device 110 receives (520) the indication. For example, the first type of CSI may be an AI CSI. Alternatively, the first type of CSI may be a non-AI CSI, such as a target CSI.

[0121] For a CSI report, a CSI report can be considered a CSI report configured for model monitoring if at least one of the following conditions is met. The first condition may be that configuration related to model monitoring is provided to terminal device 110 prior to the transmission of the CSI report. The second condition may be that the CSI report is transmitted or triggered during the duration configured for model monitoring. It should be understood that these two conditions are for illustrative purposes only and do not imply any limitation. These conditions, and any other suitable conditions, may be applied in any suitable combination. The scope of this disclosure is not limited thereto.

[0122] Terminal device 110 transmits a (530) CSI report to network device 120. Network device 120 receives the (540) CSI report.

[0123] In some embodiments, terminal device 110 may not expect the number of encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH to be greater than the number of available or configurable encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH. That is, terminal device 110 may not expect event-1 represented as (1).

[0124] In some embodiments, a CSI report may be transmitted if the number of encoded modulated symbols for a CSI report transmitted on a PUSCH is less than or equal to the number of available or configurable encoded modulated symbols for a CSI report transmitted on a PUSCH (530).

[0125] In some embodiments, a CSI report may have a higher priority than another CSI report. For example, a CSI report may have a higher priority than a CSI report that is not configured for model monitoring. As another example, a CSI report may have a higher priority than a CSI report that does not include either a first-type CSI or a second-type CSI that is different from the first type. If the first-type CSI is an AI CSI, then the second-type CSI may be a target CSI. If the first-type CSI is a target CSI, then the second-type CSI may be an AI CSI. It should be understood that the first-type CSI and the second-type CSI may also be any other suitable type besides AI CSI and target CSI. The scope of this disclosure is not limited thereto. As another example, a CSI report may have a higher priority than a CSI report that is not configured for model monitoring.

[0126] In some embodiments, network device 120 may perform model monitoring based on the received (540) CSI report and another CSI report associated with the CSI report. For example, the other CSI report may include a second type of CSI. One of the first type of CSI and the second type of CSI may be an AI CSI, while the other may be a target CSI. The other CSI report may be the most recently associated CSI report of the CSI report.

[0127] Using the CSI report and another CSI report, network device 120 can perform model monitoring. For example, model monitoring based on final KPIs or intermediate KPIs can be performed. (Already mentioned...) Figure 2 and Figure 4 The details regarding network-side model monitoring have been described and will not be repeated here. This approach ensures the monitoring of the network-side model.

[0128] Example embodiments for CSI report transmission have been described with respect to signaling flows 200 and 500 and procedures 300 and 400. In some embodiments, embodiments described with reference to two or more of the signaling flows and procedures described above may be combined. By using these signaling flows and / or procedures, network-side model monitoring can be ensured.

[0129] It should be understood that the above example embodiments are for illustrative purposes only and do not imply any limitation. This disclosure is not limited in this respect.

[0130] Figure 6 A flowchart of a communication method 600 implemented at a terminal device according to some embodiments of the present disclosure is shown. For discussion purposes, [the following will be discussed]. Figure 1 The angle description method of terminal device 110 in the 600.

[0131] At box 610, terminal device 110 receives an instruction from network device to trigger a CSI report. The CSI report is configured to report a first type of CSI or is configured for model monitoring. The CSI report is associated with another CSI report, and the other CSI report is configured to report a second type of CSI that is different from the first type or is configured for model monitoring.

[0132] At box 620, terminal device 110 performs the transmission of CSI report or omits the transmission of CSI report.

[0133] In some example embodiments, another CSI report is the most recent CSI report associated with the CSI report.

[0134] In some example embodiments, terminal device 110 does not expect the number of encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH to be greater than the number of available or configurable encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH.

[0135] In some example embodiments, a CSI report is transmitted if the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH is less than or equal to the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH.

[0136] In some example implementations, CSI reports have a higher priority than at least one of the following: CSI reports that do not include either the first type of CSI or the second type of CSI, or CSI reports that are not configured for model monitoring.

[0137] In some example embodiments, a CSI report is transmitted in response to at least one of the following: another CSI report has been transmitted, another CSI report has been fully transmitted, or another CSI report has been updated.

[0138] In some example embodiments, the transmission of a CSI report is omitted in response to at least one of the following: another CSI report has not yet been transmitted, another CSI report has not yet been fully transmitted, or another CSI report has not yet been updated.

[0139] In some example embodiments, the transmission of a CSI report is omitted if the number of encoded modulation symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is greater than the number of available or configurable encoded modulation symbols for a CSI report transmitted on the PUSCH.

[0140] In some example embodiments, a CSI report excludes a Channel Quality Indicator (CQI) in response to at least one of the following: another CSI report includes a CQI, another CSI report has been transmitted by terminal device 110, another CSI report has been fully transmitted by terminal device 110, or the CQI in another CSI report has been updated.

[0141] In some exemplary embodiments, a CSI report excludes a rank indication (RI) in response to at least one of the following: another CSI report includes an RI, another CSI report has been transmitted by terminal device 110, another CSI report has been fully transmitted by terminal device 110, or the RI in another CSI report has been updated.

[0142] In some example embodiments, if the transmission of the first part of information in another CSI report is omitted, the transmission of the second part of information in the CSI report, which corresponds to the first part of information, is also omitted.

[0143] In some example embodiments, the first part of the information includes at least one precoded matrix indicator (PMI) corresponding to at least one rank in the second type of CSI, and the second part of the information includes at least one PMI corresponding to at least one rank in the first type of CSI.

[0144] In some example embodiments, one of the first type of CSI and the second type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, and the other of the first type of CSI and the second type of CSI is not determined based on an AI / ML model.

[0145] Figure 7 A flowchart of a communication method 700 implemented at a terminal device according to some embodiments of the present disclosure is shown. For discussion purposes, [the following will be discussed]. Figure 1 Angle description method 700 for terminal device 110 in the middle.

[0146] At box 710, terminal device 110 receives from network device an instruction to trigger a CSI report, which is configured to report a first type of CSI or to be configured for model monitoring.

[0147] At frame 720, terminal device 110 transmits a CSI report to network device.

[0148] In some example embodiments, terminal device 110 does not expect the number of encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH to be greater than the number of available or configurable encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH.

[0149] In some example embodiments, a CSI report is transmitted if the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH is less than or equal to the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH.

[0150] In some example embodiments, CSI reports have a higher priority than at least one of the following: CSI reports that do not include either the first type of CSI or the second type of CSI that is different from the first type, or CSI reports that are not configured for model monitoring.

[0151] In some example embodiments, the first type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, or the first type of CSI is not determined based on an AI / ML model.

[0152] Figure 8 A flowchart of a communication method 800 implemented at a network device according to some embodiments of the present disclosure is shown. For discussion purposes, [the following will be discussed]. Figure 1 Method 800 describes the network device 120 from the perspective of network device 120.

[0153] At box 810, network device 120 transmits an instruction to the terminal device to trigger a CSI report. The CSI report is configured to report a first type of CSI or to be configured for model monitoring. The CSI report is associated with another CSI report, and the other CSI report is configured to report a second type of CSI that is different from the first type or to be configured for model monitoring.

[0154] At box 820, network device 120 receives CSI reports from terminal devices.

[0155] In some example embodiments, another CSI report is the most recent CSI report associated with the CSI report.

[0156] In some example embodiments, the terminal device does not expect the number of encoded modulated symbols for a CSI report transmitted on the PUSCH to be greater than the number of available or configurable encoded modulated symbols for a CSI report transmitted on the PUSCH.

[0157] In some example embodiments, a CSI report is transmitted if the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH is less than or equal to the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH.

[0158] In some example implementations, CSI reports have a higher priority than at least one of the following: CSI reports that do not include either the first type of CSI or the second type of CSI, or CSI reports that are not configured for model monitoring.

[0159] In some example embodiments, a CSI report is transmitted in response to at least one of the following: another CSI report has been transmitted, another CSI report has been fully transmitted, or another CSI report has been updated.

[0160] In some example embodiments, the transmission of a CSI report is omitted in response to at least one of the following: another CSI report has not yet been transmitted, another CSI report has not yet been fully transmitted, or another CSI report has not yet been updated.

[0161] In some example embodiments, the transmission of a CSI report is omitted if the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH is greater than the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH.

[0162] In some exemplary embodiments, a CSI report excludes a Channel Quality Indicator (CQI) in response to at least one of the following: another CSI report includes a CQI, another CSI report has been transmitted by the terminal device, another CSI report has been fully transmitted by the terminal device, or the CQI in another CSI report has been updated.

[0163] In some example embodiments, a CSI report excludes a rank indication (RI) in response to at least one of the following: another CSI report includes an RI, another CSI report has been transmitted by the terminal device, another CSI report has been fully transmitted by the terminal device, or the RI in another CSI report has been updated.

[0164] In some example embodiments, if the transmission of the first part of information in another CSI report is omitted, the transmission of the second part of information in the CSI report, which corresponds to the first part of information, is also omitted.

[0165] In some example embodiments, the first part of the information includes at least one precoded matrix indicator (PMI) corresponding to at least one rank in the second type of CSI, and the second part of the information includes at least one PMI corresponding to at least one rank in the first type of CSI.

[0166] In some example embodiments, one of the first type of CSI and the second type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, and the other of the first type of CSI and the second type of CSI is not determined based on an AI / ML model.

[0167] Figure 9 A flowchart of a communication method 900 implemented at a network device according to some embodiments of the present disclosure is shown. For discussion purposes, [the following will be discussed]. Figure 1 Method 900 describes the network device 120 from the perspective of network device 120.

[0168] At box 910, network device 120 transmits an instruction to terminal device to trigger a CSI report, which is configured to report a first type of CSI or to be configured for model monitoring.

[0169] At box 920, network device 120 receives CSI reports from terminal devices.

[0170] In some example embodiments, the terminal device does not expect the number of encoded modulated symbols for a CSI report transmitted on the PUSCH to be greater than the number of available or configurable encoded modulated symbols for a CSI report transmitted on the PUSCH.

[0171] In some example embodiments, a CSI report is transmitted if the number of encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH is less than or equal to the number of available or configurable encoded / decoded modulation symbols for a CSI report transmitted on the PUSCH.

[0172] In some example embodiments, CSI reports have a higher priority than at least one of the following: CSI reports that do not include the first type of CSI or the second type of CSI that are different from the first type, or CSI reports that are not configured for model monitoring.

[0173] In some example embodiments, the first type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, or the first type of CSI is not determined based on an AI / ML model.

[0174] Figure 10 This is a simplified block diagram of a device 1000 suitable for implementing embodiments of the present disclosure. The device 1000 can be considered as follows: Figure 1 Another example implementation of any of the devices shown. Thus, device 1000 may be implemented at or as a part of terminal device 110 or network device 120.

[0175] As shown in the figure, device 1000 includes a processor 1010, a memory 1020 coupled to the processor 1010, a suitable transceiver 1040 coupled to the processor 1010, and a communication interface coupled to the transceiver 1040. The memory 1020 stores at least a portion of a program 1030. The transceiver 1040 can be used for bidirectional or unidirectional communication based on requirements. The transceiver 1040 may include at least one of a transmitter 1042 and a receiver 1044. The transmitter 1042 and receiver 1044 may be functional modules or physical entities. The transceiver 1040 has at least one antenna to facilitate communication; however, in practice, the access node mentioned in this application may have several antennas. The communication interface can represent any interface required for communication with other network elements, such as the X2 / Xn interface for bidirectional communication between eNB / gNB, the S1 / NG interface for communication between the Mobility Management Entity (MME) / Access and Mobility Management Function (AMF) / SGW / UPF and eNB / gNB, the Un interface for communication between eNB / gNB and Relay Node (RN), or the Uu interface for communication between eNB / gNB and terminal equipment.

[0176] Assume that program 1030 includes program instructions that, when executed by the associated processor 1010, enable device 1000 to operate according to embodiments of this disclosure, as referenced herein. Figures 1 to 9 The embodiments discussed herein may be implemented by computer software executable by the processor 1010 of device 1000, or by hardware, or by a combination of software and hardware. The processor 1010 may be configured to implement various embodiments of this disclosure. Furthermore, a combination of the processor 1010 and the memory 1020 may form a processing unit 1050 suitable for implementing various embodiments of this disclosure.

[0177] As a non-limiting example, memory 1020 can be of any type suitable for a local technology network and can be implemented using any suitable data storage technology, such as non-transitory computer-readable storage media, semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory, and removable memory. Although only one memory 1020 is shown in device 1000, several physically different memory modules may exist in device 1000. As a non-limiting example, processor 1010 can be of any type suitable for a local technology network and may include one or more of a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. Device 1000 may have multiple processors, such as dedicated technology chips that are time-dependent on a clock of a synchronous main processor.

[0178] According to embodiments of this disclosure, a terminal device including circuitry is provided. The circuitry is configured to: receive from a network device an indication for triggering a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report being associated with another CSI report, and the other CSI report being configured to report a second type of CSI different from the first type or is configured for model monitoring; and to perform the transmission of the CSI report or the omission of the transmission of the CSI report. According to embodiments of this disclosure, the circuitry can be configured to perform any method implemented by the terminal device as described above.

[0179] According to embodiments of this disclosure, a terminal device including circuitry is provided. The circuitry is configured to: receive from a network device an indication for triggering a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and transmit the CSI report to the network device. According to embodiments of this disclosure, the circuitry can be configured to perform any method implemented by the terminal device as described above.

[0180] According to embodiments of this disclosure, a network device including circuitry is provided. The circuitry is configured to: transmit to a terminal device an indication for triggering a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report is associated with another CSI report, and the other CSI report is configured to report a second type of CSI different from the first type or is configured for model monitoring; and receive the CSI report from the terminal device. According to embodiments of this disclosure, the circuitry can be configured to perform any method implemented by the network device as described above.

[0181] According to embodiments of this disclosure, a network device including circuitry is provided. The circuitry is configured to: transmit to a terminal device an indication for triggering a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and receive the CSI report from the terminal device. According to embodiments of this disclosure, the circuitry can be configured to perform any method implemented by the network device as described above.

[0182] As used herein, the term "circuit" can refer to hardware circuitry and / or a combination of hardware circuitry and software. For example, a circuit can be a combination of analog and / or digital hardware circuitry with software / firmware. As another example, a circuit can be any part of a hardware processor with software, including digital signal processors, software, and memory, which work together to enable a device, such as a terminal device or network device, to perform various functions. In yet another example, a circuit can be hardware circuitry and / or a processor that requires software / firmware to operate, such as a microprocessor or a portion thereof, but which may be absent when software is not required to operate. As used herein, the term "circuit" also encompasses the implementation of hardware circuitry or processor(s) alone, or a portion thereof, and its accompanying software and / or firmware.

[0183] According to embodiments of this disclosure, a terminal device is provided. The terminal device includes: components for receiving from a network device an indication to trigger a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or configured for model monitoring, the CSI report being associated with another CSI report, and the other CSI report being configured to report a second type of CSI different from the first type or configured for model monitoring; and components for performing the transmission of the CSI report or an omission of the transmission of the CSI report. In some embodiments, the first device may include components for performing corresponding operations of method 600. In some example embodiments, the first device may also include components for performing other operations in some example embodiments of method 600. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit or software module.

[0184] According to embodiments of this disclosure, a terminal device is provided. The terminal device includes: components for receiving from a network device an indication to trigger a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and components for transmitting the CSI report to the network device. In some embodiments, a second device may include components for performing corresponding operations of method 700. In some example embodiments, the second device may also include components for performing other operations in some example embodiments of method 700. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit or software module.

[0185] According to embodiments of this disclosure, a network apparatus is provided. The network apparatus includes: components for transmitting to a terminal device an indication for triggering a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or configured for model monitoring, the CSI report being associated with another CSI report, and the other CSI report being configured to report a second type of CSI different from the first type or configured for model monitoring; and components for receiving the CSI report from the terminal device. In some embodiments, a third component may include components for performing corresponding operations of method 800. In some example embodiments, the third component may also include components for performing other operations in some example embodiments of method 800. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit or software module.

[0186] According to embodiments of this disclosure, a network apparatus is provided. The network apparatus includes: components for transmitting to a terminal device an indication for triggering a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and components for receiving the CSI report from the terminal device. In some embodiments, a fourth component may include components for performing corresponding operations of method 900. In some example embodiments, the fourth component may also include components for performing other operations in some example embodiments of method 900. The components may be implemented in any suitable form. For example, the components may be implemented in a circuit or software module.

[0187] In summary, the embodiments of this disclosure provide the following aspects.

[0188] In one aspect, a terminal device is proposed, comprising: a processor configured to cause the terminal device to: receive from a network device an instruction for triggering a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report is associated with another CSI report, and the other CSI report is configured to report a second type of CSI different from the first type or is configured for model monitoring; and to perform the transmission of the CSI report or an omission of the transmission of the CSI report.

[0189] In some embodiments, another CSI report is the most recent CSI report associated with the CSI report.

[0190] In some embodiments, the terminal device does not expect the number of encoded modulation symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) to be greater than the number of encoded modulation symbols available or configurable for a CSI report transmitted on the PUSCH.

[0191] In some embodiments, a CSI report is transmitted if the number of encoded modulation symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is less than or equal to the number of available or configurable encoded modulation symbols for a CSI report transmitted on the PUSCH.

[0192] In some embodiments, CSI reports have a higher priority than at least one of the following: CSI reports that do not include either the first type of CSI or the second type of CSI, or CSI reports that are not configured for model monitoring.

[0193] In some embodiments, a CSI report is transmitted in response to at least one of the following: another CSI report has been transmitted, another CSI report has been fully transmitted, or another CSI report has been updated.

[0194] In some embodiments, the transmission of a CSI report is omitted in response to at least one of the following: another CSI report has not yet been transmitted, another CSI report has not yet been fully transmitted, or another CSI report has not yet been updated.

[0195] In some embodiments, the transmission of a CSI report is omitted if the number of encoded / decoded modulated symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is greater than the number of available or configurable encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH.

[0196] In some embodiments, a CSI report excludes a Channel Quality Indicator (CQI) in response to at least one of the following: another CSI report includes a CQI, another CSI report has been transmitted by the terminal device, another CSI report has been fully transmitted by the terminal device, or the CQI in another CSI report has been updated.

[0197] In some embodiments, a CSI report excludes a rank indication (RI) in response to at least one of the following: another CSI report includes an RI, another CSI report has been transmitted by the terminal device, another CSI report has been fully transmitted by the terminal device, or the RI in another CSI report has been updated.

[0198] In some embodiments, if the transmission of the first part of information in another CSI report is omitted, the transmission of the second part of information in the CSI report, which corresponds to the first part of information, is omitted.

[0199] In some embodiments, the first part of the information includes at least one precoded matrix indicator (PMI) corresponding to at least one rank in the second type of CSI, and the second part of the information includes at least one PMI corresponding to at least one rank in the first type of CSI.

[0200] In some embodiments, one of the first type of CSI and the second type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, and the other of the first type of CSI and the second type of CSI is not determined based on an AI / ML model.

[0201] In one aspect, a terminal device is proposed, comprising: a processor configured to cause the terminal device to: receive from a network device an instruction for triggering a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or to be configured for model monitoring; and transmit the CSI report to the network device.

[0202] In some embodiments, the terminal device does not expect the number of encoded modulated symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) to be greater than the number of available or configurable encoded modulated symbols for a CSI report transmitted on the PUSCH.

[0203] In some embodiments, a CSI report is transmitted if the number of encoded modulation symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is less than or equal to the number of available or configurable encoded modulation symbols for a CSI report transmitted on the PUSCH.

[0204] In some embodiments, CSI reports have a higher priority than at least one of the following: CSI reports that do not include either the first type of CSI or the second type of CSI that is different from the first type, or CSI reports that are not configured for model monitoring.

[0205] In some embodiments, the first type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, or the first type of CSI is not determined based on an AI / ML model.

[0206] In one aspect, a network device is proposed, comprising: a processor configured to cause the network device to: transmit to a terminal device an indication for triggering a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report is associated with another CSI report, and the other CSI report is configured to report a second type of CSI different from the first type or is configured for model monitoring; and receive the CSI report from the terminal device.

[0207] In some embodiments, another CSI report is the most recent CSI report associated with the CSI report.

[0208] In some embodiments, the terminal device does not expect the number of encoded modulation symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) to be greater than the number of encoded modulation symbols available or configurable for a CSI report transmitted on the PUSCH.

[0209] In some embodiments, a CSI report is transmitted if the number of encoded modulation symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is less than or equal to the number of available or configurable encoded modulation symbols for a CSI report transmitted on the PUSCH.

[0210] In some embodiments, CSI reports have a higher priority than at least one of the following: CSI reports that do not include either the first type of CSI or the second type of CSI, or CSI reports that are not configured for model monitoring.

[0211] In some embodiments, a CSI report is transmitted in response to at least one of the following: another CSI report has been transmitted, another CSI report has been fully transmitted, or another CSI report has been updated.

[0212] In some embodiments, the transmission of a CSI report is omitted in response to at least one of the following: another CSI report has not yet been transmitted, another CSI report has not yet been fully transmitted, or another CSI report has not yet been updated.

[0213] In some embodiments, the transmission of a CSI report is omitted if the number of encoded / decoded modulated symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is greater than the number of available or configurable encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH.

[0214] In some embodiments, a CSI report excludes a Channel Quality Indicator (CQI) in response to at least one of the following: another CSI report includes a CQI, another CSI report has been transmitted by the terminal device, another CSI report has been fully transmitted by the terminal device, or the CQI in another CSI report has been updated.

[0215] In some embodiments, a CSI report excludes a rank indication (RI) in response to at least one of the following: another CSI report includes an RI, another CSI report has been transmitted by the terminal device, another CSI report has been fully transmitted by the terminal device, or the RI in another CSI report has been updated.

[0216] In some embodiments, if the transmission of the first part of information in another CSI report is omitted, the transmission of the second part of information in the CSI report, which corresponds to the first part of information, is omitted.

[0217] In some embodiments, the first part of the information includes at least one precoded matrix indicator (PMI) corresponding to at least one rank in the second type of CSI, and the second part of the information includes at least one PMI corresponding to at least one rank in the first type of CSI.

[0218] In some embodiments, one of the first type of CSI and the second type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, and the other of the first type of CSI and the second type of CSI is not determined based on an AI / ML model.

[0219] In one aspect, a network device is proposed, comprising: a processor configured to cause the network device to: transmit to a terminal device an indication for triggering a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or configured for model monitoring; and receive a CSI report from the terminal device.

[0220] In some embodiments, the terminal device does not expect the number of encoded / decoded modulated symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) to be greater than the number of available or configurable encoded / decoded modulated symbols for a CSI report transmitted on the PUSCH.

[0221] In some embodiments, a CSI report is transmitted if the number of encoded modulation symbols for a CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is less than or equal to the number of available or configurable encoded modulation symbols for a CSI report transmitted on the PUSCH.

[0222] In some embodiments, CSI reports have a higher priority than at least one of the following: CSI reports that do not include either the first type of CSI or the second type of CSI that is different from the first type, or CSI reports that are not configured for model monitoring.

[0223] In some embodiments, the first type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, or the first type of CSI is not determined based on an AI / ML model.

[0224] In one aspect, a terminal device includes: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, which, when executed by the at least one processor, cause the device to perform a method implemented by the terminal device described above.

[0225] In one aspect, a network device includes: at least one processor; and at least one memory coupled to the at least one processor and storing instructions thereon, which, when executed by the at least one processor, cause the device to perform a method implemented by the network device described above.

[0226] In one aspect, a computer-readable medium stores instructions thereon that, when executed on at least one processor, cause the at least one processor to perform the method implemented by the terminal device discussed above.

[0227] In one aspect, a computer-readable medium stores instructions thereon that, when executed on at least one processor, cause the at least one processor to perform the method implemented by the network device discussed above.

[0228] In one aspect, a computer program includes instructions that, when executed on at least one processor, cause the at least one processor to perform the method implemented by the aforementioned terminal device.

[0229] In one aspect, a computer program includes instructions that, when executed on at least one processor, cause the at least one processor to perform the method implemented by the aforementioned network device.

[0230] Generally, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of this disclosure are illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, as non-limiting examples, the blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0231] This disclosure also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as those included in a program module that executes on a device on a target real or virtual processor, to perform the above-referenced instructions. Figures 1 to 10The process or method described herein. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of a program module can be combined or split among program modules as needed. The machine-executable instructions used in a program module can be executed locally or on a distributed device. In a distributed device, the program module can reside on both local and remote storage media.

[0232] Program code used to perform the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code enables the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a stand-alone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0233] The aforementioned program code may be embodied on a machine-readable medium, which may be any tangible medium that can contain or store a program used by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. More specific examples of machine-readable storage media will include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0234] Furthermore, although the operations are described in a specific order, this should not be construed as requiring that these operations be performed in the specific order shown or in sequential order, or that all the operations shown be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, while several specific embodiment details are contained in the foregoing discussion, these details should not be construed as limiting the scope of this disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0235] Although this disclosure has been described in language specific to structural features and / or methodological actions, it should be understood that the disclosure as defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms for implementing the claims.

Claims

1. A terminal device, comprising: The processor is configured to cause the terminal device to: Receive an instruction from a network device to trigger a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report is associated with another CSI report, and the other CSI report is configured to report a second type of CSI different from the first type or is configured for model monitoring; as well as Perform the transmission of the CSI report or omit the transmission of the CSI report.

2. The terminal device of claim 1, wherein the other CSI report is the most recent CSI report associated with the CSI report.

3. The terminal device of claim 1, wherein the terminal device does not expect the number of encoded / decoded modulation symbols for the CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) to be greater than the number of available or configurable encoded / decoded modulation symbols for the CSI report transmitted on the PUSCH.

4. The terminal device of claim 1, wherein the CSI report is transmitted if the number of encoded / decoded modulation symbols for the CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is less than or equal to the number of available or configurable encoded / decoded modulation symbols for the CSI report transmitted on the PUSCH.

5. The terminal device of claim 1, wherein the CSI report has a higher priority than at least one of the following: CSI reports that exclude neither the first type of CSI nor the second type of CSI, or CSI reports not configured for model monitoring.

6. The terminal device of claim 1, wherein the CSI report is transmitted in response to at least one of the following: The other CSI report has been transmitted. The other CSI report has been fully transmitted, or The other CSI report has been updated.

7. The terminal device of claim 1, wherein the transmission of the CSI report is omitted in response to at least one of the following: The other CSI report has not yet been transmitted. The other CSI report has not yet been fully transmitted, or The other CSI report has not yet been updated.

8. The terminal device of claim 1, wherein the transmission of the CSI report is omitted if the number of encoded / decoded modulation symbols for the CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is greater than the number of available or configurable encoded / decoded modulation symbols for the CSI report transmitted on the PUSCH.

9. The terminal device of claim 1, wherein the CSI report excludes the Channel Quality Indicator (CQI) in response to at least one of the following: The other CSI report mentioned includes CQI. The other CSI report has already been transmitted by the terminal device. The other CSI report has been fully transmitted by the terminal device, or The CQI in the other CSI report has been updated.

10. The terminal device of claim 1, wherein the CSI report excludes the Rank Indication (RI) in response to at least one of the following: The other CSI report includes RI, The other CSI report has already been transmitted by the terminal device. The other CSI report has been fully transmitted by the terminal device, or The RI in the other CSI report has been updated.

11. The terminal device according to claim 1, wherein if the transmission of the first portion of information in the other CSI report is omitted, the transmission of the second portion of information in the CSI report is omitted, the second portion of information corresponding to the first portion of information.

12. The terminal device of claim 11, wherein the first portion of the information includes at least one precoding matrix indicator (PMI) corresponding to at least one rank in the CSI of the second type, and the second portion of the information includes at least one PMI corresponding to the at least one rank in the CSI of the first type.

13. The terminal device according to any one of claims 1 to 12, wherein one of the first type of CSI and the second type of CSI is determined based on an artificial intelligence / machine learning (AI / ML) model, and The other of the CSI of the first type and the CSI of the second type is not determined based on the AI / ML model.

14. A terminal device, comprising: The processor is configured to cause the terminal device to: Receive an instruction from a network device to trigger a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or to be configured for model monitoring; as well as The CSI report is transmitted to the network device.

15. The terminal device of claim 14, wherein the terminal device does not expect the number of encoded / decoded modulated symbols for the CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) to be greater than the number of available or configurable encoded / decoded modulated symbols for the CSI report transmitted on the PUSCH.

16. The terminal device of claim 14, wherein the CSI report is transmitted if the number of encoded / decoded modulation symbols for the CSI report transmitted on the Physical Uplink Shared Channel (PUSCH) is less than or equal to the number of available or configurable encoded / decoded modulation symbols for the CSI report transmitted on the PUSCH.

17. The terminal device of claim 14, wherein the CSI report has a higher priority than at least one of the following: CSI reports that exclude neither the first type of CSI nor the second type of CSI that is different from the first type, or CSI reports not configured for model monitoring.

18. The terminal device according to any one of claims 14 to 17, wherein the CSI of the first type is determined based on an artificial intelligence / machine learning (AI / ML) model, or The CSI of the first type is not determined based on the AI / ML model.

19. A network device, comprising: The processor is configured to cause the network device to: Transmit an instruction to a terminal device for triggering a Channel State Information (CSI) report, wherein the CSI report is configured to report a first type of CSI or is configured for model monitoring, the CSI report is associated with another CSI report, and the other CSI report is configured to report a second type of CSI different from the first type or is configured for model monitoring; as well as Receive the CSI report from the terminal device.

20. A network device, comprising: The processor is configured to cause the network device to: Transmit an instruction to the terminal device for triggering a Channel State Information (CSI) report, the CSI report being configured to report a first type of CSI or configured for model monitoring; as well as Receive the CSI report from the terminal device.

Images