WO2025218235A1

WO2025218235A1 - Channel status information processing

Info

Publication number: WO2025218235A1
Application number: PCT/CN2024/141600
Authority: WO
Inventors: Yinghao ZHANG; Bingchao LIU; Hongmei Liu; Jianfeng Wang
Original assignee: Lenovo Beijing Ltd
Current assignee: Lenovo Beijing Ltd
Priority date: 2024-12-23
Filing date: 2024-12-23
Publication date: 2025-10-23
Anticipated expiration: 2027-06-23

Abstract

Example embodiments of the present disclosure relate to CSI processing. In one aspect, a network entity may transmit, to a UE, one or more CSI report configurations for a first functionality. The UE may transmit at least one CSI report to the network entity based on first information indicating at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities; a second number of CPUs occupied by each CSI report associated with the first functionality; first time associated with model activation for the first functionality; second time associated with model inference for the first functionality; or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality. In this way, CSI processing may be enhanced at least for AI/ML use cases.

Description

CHANNEL STATUS INFORMATION PROCESSING

TECHNICAL FIELD

The present disclosure relates to wireless communications, and more specifically to methods, apparatuses and computer-readable media for channel status information (CSI) processing.

BACKGROUND

A wireless communications system may include one or multiple network communication devices, such as base stations, which may be otherwise known as an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. Each network communication device, such as a base station may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE) , or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers) . Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G) ) .

Currently, CSI prediction and downlink (DL) transmitting (Tx) beam prediction has been identified as use cases of an artificial intelligence (AI) /machine learning (ML) model for time domain prediction. Accordingly, CSI processing needs to be enhanced for AI/ML use cases.

SUMMARY

The present disclosure relates to methods, apparatuses, and computer-readable media that support CSI processing. By considering CSI processing time and/or CSI processing unit (CPU) occupation time in AI/ML use cases, CSI processing may be enhanced for AI/ML use cases.

In one aspect, some implementations of the methods, apparatuses, and computer-readable media described herein may comprise: receiving, at a UE from a network entity via a transceiver, one or more configurations of one or more CSI reports for a first functionality; and transmitting, to the network entity, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.

Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: transmitting, to the network entity via the transceiver, the first information in a procedure of reporting capability information of the UE.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the first information comprises a first part and a second part. The first part is associated with one or more supported functionalities, and the second part is associated with one or more applicable functionalities. Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: transmitting, to the network entity via the transceiver, the first part of the first information in a procedure of reporting capability information of the UE; and transmitting, to the network entity via the transceiver, the second part of the first information in a procedure of reporting applicable functionality information of the UE.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the first or second number of CPUs is determined based on a scale factor and a reference number of CPUs.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report occupies one or more CPUs, and a total number of CPUs in the one or more CPUs is determined based on the second number of CPUs for each CSI report in the at least one CSI report, and the total number of CPUs is smaller than or equal to the first number of CPUs.

In some implementations of the methods, apparatuses, and computer-readable media described herein, a total number of CPUs occupied by one or more CSI reports associated with a second functionality is smaller than or equal to a number of CPUs supported by the UE for processing a set of CSI reports associated with a set of second functionalities, or a total number of CPUs occupied by the one or more CSI reports associated with the second functionality and the one or more CSI reports associated with the first functionality is smaller than or equal to the number of CPUs supported by the UE for processing the set of CSI reports associated with the set of second functionalities.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report simultaneously occupies one or more CPUs, and a total number of CPUs in the one or more CPUs is smaller than or equal to the third number of CPUs.

Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: receiving, from the network entity via the transceiver, a configuration indicating a priority of a configuration of each CSI report in the one or more CSI reports; and in accordance with a determination that multiple CSI reports associated with the first functionality are active in overlapped symbols, dropping at least one of the multiple CSI reports based on the priority.

Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: transmitting, to the network entity via the transceiver, second information indicating applicability of the one or more configurations of the one or more CSI reports associated with the first functionality.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the second information comprises at least one of the following: information of multiple configurations of CSI reports that can be activated simultaneously; or information of multiple configurations of CSI reports corresponding to sets of inference parameters that can be activated simultaneously.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is carried by a scheduled uplink transmission, and a time interval between a latest one reference signal transmission occasion for channel measurement and the scheduled uplink transmission carrying the at least one CSI report is greater than a first time interval, and the first time interval is determined based on the second time.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is carried by a scheduled uplink transmission, and a time interval between a downlink transmission triggering the at least one CSI report and the scheduled uplink transmission carrying the at least one report is greater than a second time interval, and the second time interval is determined based on the second time or based on the first time and the second time.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is periodic or semi-persistent. In these implementations, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal of a latest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is periodic or semi-persistent. In these implementations, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal to a first number of symbols after a last symbol of a last one reference signal for a reference signal transmission occasion for channel measurement, and the reference signal transmission occasion is a transmission occasion other than a latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report. The one or more CPUs are occupied from a first symbol of an earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is aperiodic. In these implementations, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal of a latest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is aperiodic. In these implementations, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal to a second number of symbols after a last symbol of a last one reference signal for a reference signal transmission occasion for channel measurement, and the reference signal transmission occasion is a transmission occasion other than a latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report. The one or more CPUs are occupied from a first symbol of an earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is aperiodic. In these implementations, one or more CPUs are occupied for the at least one CSI report during at least one of the following: a time window starting from a first symbol of downlink control information (DCI) triggering the one or more CSI reports until a later one of a third number of symbols after a last symbol of the DCI, and a fourth number of symbols after a last symbol of an earliest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report; one or more time windows starting from a first symbol of a reference signal transmission occasion, until a fifth number of symbols after a last symbol of the reference signal transmission occasion, wherein the reference signal transmission occasion is a transmission occasion other than the earliest one reference signal transmission occasion and a latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report; or a time window starting from a first symbol of the latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In another aspect, some implementations of the methods, apparatuses, and computer-readable media described herein may comprise: transmitting, at a network entity to a UE via a transceiver, one or more configurations of one or more CSI reports for a first functionality; and receiving, from the network entity via the transceiver, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with a first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.

Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: receiving, from the UE via the transceiver, the first information in a procedure of reporting capability information of the UE.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the first information comprises a first part and a second part. Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: receiving, from the UE via the transceiver, the first part of the first information associated with one or more supported functionalities in a procedure of reporting capability information of the UE; and receiving, from the UE via the transceiver, the second part of the first information associated with one or more applicable functionalities in a procedure of reporting applicable functionality information of the UE.

Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: transmitting, to the UE via the transceiver, a configuration indicating a priority of a configuration of each CSI report in the one or more CSI reports.

Some implementations of the methods, apparatuses, and computer-readable media described herein may further comprise: receiving, from the UE via the transceiver, second information indicating applicability of the one or more configurations of the one or more CSI reports associated with the first functionality.

In some implementations of the methods, apparatuses, and computer-readable media described herein, the at least one CSI report is aperiodic. In these implementations, one or more CPUs are occupied for the at least one CSI report during at least one of the following: a time window starting from a first symbol of DCI triggering the one or more CSI reports until a later one of a third number of symbols after a last symbol of the DCI, and a fourth number of symbols after a last symbol of an earliest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report; one or more time windows starting from a first symbol of a reference signal transmission occasion, until a fifth number of symbols after a last symbol of the reference signal transmission occasion, wherein the reference signal transmission occasion is a transmission occasion other than the earliest one reference signal transmission occasion and a latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report; or a time window starting from a first symbol of the latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In the context of the present disclosure, an apparatus may be implemented as a device or a part of the device. In some embodiments, the apparatus may be implemented as a processor at the device.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates an example of a wireless communications system that supports CSI processing in which some embodiments of the present disclosure can be implemented.

FIG. 2 illustrates a diagram illustrating an example applicable functionality reporting procedure in which some embodiments of the present disclosure can be implemented.

FIG. 3 illustrates a signaling chart illustrating an example process of communication that supports CSI processing in accordance with aspects of the present disclosure.

FIG. 4A illustrates a diagram illustrating an example CPU occupation for a periodic or semi-persistent CSI report in accordance with aspects of the present disclosure.

FIG. 4B illustrates a diagram illustrating another example CPU occupation for a periodic or semi-persistent CSI report in accordance with aspects of the present disclosure.

FIG. 5A illustrates a diagram illustrating an example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure.

FIG. 5B illustrates a diagram illustrating another example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure.

FIG. 5C illustrates a diagram illustrating another example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure.

FIG. 5D illustrates a diagram illustrating another example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure.

FIG. 6 illustrates an example of a device that supports CSI processing in accordance with aspects of the present disclosure.

FIG. 7 illustrates an example of a processor that supports CSI processing in accordance with aspects of the present disclosure.

FIG. 8 illustrates a flowchart of a method that supports CSI processing in accordance with aspects of the present disclosure.

FIG. 9 illustrates a flowchart of another method that supports CSI processing in accordance with aspects of the present disclosure.

Throughout the drawings, the same or similar reference numerals represent the same or similar element.

DETAILED DESCRIPTION

Principles of the present disclosure will now be described with reference to some embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein can be implemented in various manners other than the ones described below. In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

References in the present disclosure to “one embodiment, ” “an example embodiment, ” “an embodiment, ” “some embodiments, ” and the like indicate that the embodiment (s) described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment (s) . Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described. The term “embodiment” herein may be interchangeably used with “implementation” .

It shall be understood that although the terms “first” and “second” or the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could also be termed as a second element, and similarly, a second element could also be termed as a first element, without departing from the scope of embodiments. As used herein, the term “and/or” includes any and all combinations of one or more of the listed terms. In some examples, values, procedures, or apparatuses are referred to as “best, ” “lowest, ” “highest, ” “minimum, ” “maximum, ” or the like. It will be appreciated that such descriptions are intended to indicate that a selection among many used functional alternatives can be made, and such selections need not be better, smaller, higher, or otherwise preferable to other selections.

In the context of the present disclosure, the term “functionality” may be interchangeably used with “a feature or feature group” . In some embodiments, a functionality may refer to a feature or feature group based on an AI/ML model. For convenience, this functionality may also be referred to as an AI/ML functionality or a first functionality. In some embodiments, a functionality may refer to a feature or feature group unrelated to an AI/ML model. For convenience, this functionality may also be referred to as a non-AI/ML functionality or a second functionality.

In the context of the present disclosure, the term “supported functionalities” may refer to AI/ML functionalities that UE can indicate by using UE capability information, e.g., via a radio resource control (RRC) signaling or a long term evolution (LTE) positioning protocol (LPP) signaling. The term “applicable functionalities” may refer to AI/ML functionalities that the UE is ready to apply for inference. The term “activated functionalities” may refer to AI/ML functionalities already enabled for performing inference.

Currently, AI/ML models developed by UE vendors have diverse model size and FLOPS depending on their own implementation method. Depending on requirements of AI/ML functionalities, different model algorithms may be adopted, e.g., a convolutional long short term memory (conv-LSTM) model for CSI prediction and a convolutional neural network (CNN) model for beam prediction. Even for the same type of AI/ML functionality, an AI/ML model may be implemented in different ways by UE vendors. It is unclear how to manage processing resources for AI/ML models developed by different UE vendors.

In some AI/ML use cases, there is a timeline issue of CSI processing resource occupation. For beam management (BM) -Case 2, multiple past beam measurements based on a set of beams (also referred to as Set B herein) will be used to predict information of another set of beams (also referred to as Set A herein) in future time instances, e.g., predict the best beam of the future time instances. UE may require a long time for obtaining the beam measurements, e.g., 40ms × 4 past time instances =160ms. It is unclear how to specify CPU occupation time for CSI report for temporal beam reporting. It is inefficient that the CSI report occupies the whole beam measurement window. For performance monitoring of AI/ML functionality or model, a long time is required to calculate a statistic metric such as a ratio of beam prediction success.

In addition, multiple CSI report configurations may be associated with the same AI/ML model, and different time behaviors or report contents may be configured with these CSI report configurations. Activating these CSI report configurations simultaneously will result in collision of AI/ML model usage.

In view of the above, embodiments of the present disclosure provide a solution of communication for CSI processing so as to overcome the above and other potential issues. In the solution, a network entity may transmit, to a UE, one or more configurations of one or more CSI reports for a first functionality. The UE may transmit, to the network entity, at least one CSI report in the one or more CSI reports based on first information. The first information indicates at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities; a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality; first time associated with model activation for the first functionality; second time associated with model inference for the first functionality; or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality. In this way, CSI processing may be enhanced at least for AI/ML use cases.

Aspects of the present disclosure are described in the context of a wireless communications system.

FIG. 1 illustrates an example of a wireless communications system 100 that supports low latency traffic in which some embodiments of the present disclosure can be implemented. The wireless communications system 100 may include one or more network entities 102 (also referred to as network equipment (NE) ) , one or more UEs 104, a core network (CN) 106, and a packet data network 108. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as a long term evolution (LTE) network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a 5G network, such as a new radio (NR) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA) , frequency division multiple access (FDMA) , or code division multiple access (CDMA) , etc.

The one or more network entities 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the network entities 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a radio access network (RAN) , a base transceiver station, an access point (AP) , a NodeB, an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. A network entity 102 and a UE 104 may communicate via a communication link 110, which may be a wireless or wired connection. For example, a network entity 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

A network entity 102 may provide a geographic coverage area 112 for which the network entity 102 may support services (e.g., voice, video, packet data, message, broadcast, etc. ) for one or more UEs 104 within the geographic coverage area 112. For example, a network entity 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc. ) according to one or multiple radio access technologies. In some implementations, a network entity 102 may be moveable, for example, a satellite associated with a non-terrestrial network. In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas 112 may be associated with different network entities 102. Information and signals described herein may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

The one or more UEs 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a mobile device, a wireless device, a remote device, a remote unit, a handheld device, or a subscriber device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station (STA) , a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples. In some implementations, a UE 104 may be stationary in the wireless communications system 100. In some other implementations, a UE 104 may be mobile in the wireless communications system 100.

The one or more UEs 104 may be devices in different forms or having different capabilities. Some examples of UEs 104 are illustrated in FIG. 1. A UE 104 may be capable of communicating with various types of devices, such as the network entities 102, other UEs 104, or network equipment (e.g., the CN 106, the packet data network 108, a relay device, an integrated access and backhaul (IAB) node, or another network equipment) , as shown in FIG. 1. Additionally, or alternatively, a UE 104 may support communication with other network entities 102 or UEs 104, which may act as relays in the wireless communications system 100.

A UE 104 may also be able to support wireless communication directly with other UEs 104 over a communication link 114. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link 114 may be referred to as a sidelink (SL) . For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.

A network entity 102 may support communications with the CN 106, or with another network entity 102, or both. For example, a network entity 102 may interface with the CN 106 through one or more backhaul links 116 (e.g., via an S1, N2, N3, or another network interface) . The network entities 102 may communicate with each other over the backhaul links 116 (e.g., via an X2, Xn, or another network interface) . In some implementations, the network entities 102 may communicate with each other directly (e.g., between the network entities 102) . In some other implementations, the network entities 102 may communicate with each other or indirectly (e.g., via the CN 106) . In some implementations, one or more network entities 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC) . An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs) .

In some implementations, a network entity 102 may be configured in a disaggregated architecture, which may be configured to utilize a protocol stack physically or logically distributed among two or more network entities 102, such as an integrated access backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN alliance) , or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN) ) . For example, a network entity 102 may include one or more of a central unit (CU) , a distributed unit (DU) , a radio unit (RU) , a RAN intelligent controller (RIC) (e.g., a near-real time RIC (Near-RT RIC) , a non-real time RIC (Non-RT RIC) ) , a service management and orchestration (SMO) system, or any combination thereof.

An RU may also be referred to as a radio head, a smart radio head, a remote radio head (RRH) , a remote radio unit (RRU) , or a transmission reception point (TRP) . One or more components of the network entities 102 in a disaggregated RAN architecture may be co-located, or one or more components of the network entities 102 may be located in distributed locations (e.g., separate physical locations) . In some implementations, one or more network entities 102 of a disaggregated RAN architecture may be implemented as virtual units (e.g., a virtual CU (VCU) , a virtual DU (VDU) , a virtual RU (VRU) ) .

Split of functionality between a CU, a DU, and an RU may be flexible and may support different functionalities depending upon which functions (e.g., network layer functions, protocol layer functions, baseband functions, radio frequency functions, and any combinations thereof) are performed at a CU, a DU, or an RU. For example, a functional split of a protocol stack may be employed between a CU and a DU such that the CU may support one or more layers of the protocol stack and the DU may support one or more different layers of the protocol stack. In some implementations, the CU may host upper protocol layer (e.g., a layer 3 (L3) , a layer 2 (L2) ) functionality and signaling (e.g., radio resource control (RRC) , service data adaption protocol (SDAP) , packet data convergence protocol (PDCP) ) . The CU may be connected to one or more DUs or RUs, and the one or more DUs or RUs may host lower protocol layers, such as a layer 1 (L1) (e.g., physical (PHY) layer) or an L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, and may each be at least partially controlled by the CU.

Additionally, or alternatively, a functional split of the protocol stack may be employed between a DU and an RU such that the DU may support one or more layers of the protocol stack and the RU may support one or more different layers of the protocol stack. The DU may support one or multiple different cells (e.g., via one or more RUs) . In some implementations, a functional split between a CU and a DU, or between a DU and an RU may be within a protocol layer (e.g., some functions for a protocol layer may be performed by one of a CU, a DU, or an RU, while other functions of the protocol layer are performed by a different one of the CU, the DU, or the RU) .

A CU may be functionally split further into CU control plane (CU-CP) and CU user plane (CU-UP) functions. A CU may be connected to one or more DUs via a midhaul communication link (e.g., F1, F1-C, F1-U) , and a DU may be connected to one or more RUs via a fronthaul communication link (e.g., open fronthaul (FH) interface) . In some implementations, a midhaul communication link or a fronthaul communication link may be implemented in accordance with an interface (e.g., a channel) between layers of a protocol stack supported by respective network entities 102 that are in communication via such communication links.

The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC) , or a 5G core (5GC) , which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME) , an access and mobility management functions (AMF) ) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW) , a packet data network (PDN) gateway (P-GW) , or a user plane function (UPF) ) . In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc. ) for the one or more UEs 104 served by the one or more network entities 102 associated with the CN 106.

The CN 106 may communicate with the packet data network 108 over one or more backhaul links 116 (e.g., via an S1, N2, N3, or another network interface) . The packet data network 108 may include an application server 118. In some implementations, one or more UEs 104 may communicate with the application server 118. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via a network entity 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server 118 using the established session (e.g., the established PDU session) . The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106) .

In the wireless communications system 100, the network entities 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers) ) to perform various operations (e.g., wireless communications) . In some implementations, the network entities 102 and the UEs 104 may support different resource structures. For example, the network entities 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the network entities 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the network entities 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures) . The network entities 102 and the UEs 104 may support various frame structures based on one or more numerologies.

One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., μ=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., μ=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., μ=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., μ=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., μ=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., μ=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames) . Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., μ=0, μ=1, μ=2, μ=3, μ=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., orthogonal frequency division multiplexing (OFDM) symbols) . In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing) , a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., μ=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz –7.125 GHz) , FR2 (24.25 GHz –52.6 GHz) , FR3 (7.125 GHz –24.25 GHz) , FR4 (52.6 GHz –114.25 GHz) , FR4a or FR4-1 (52.6 GHz –71 GHz) , and FR5 (114.25 GHz –300 GHz) . In some implementations, the network entities 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the network entities 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data) . In some implementations, FR2 may be used by the network entities 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies) . For example, FR1 may be associated with a first numerology (e.g., μ=0) , which includes 15 kHz subcarrier spacing; a second numerology (e.g., μ=1) , which includes 30 kHz subcarrier spacing; and a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies) . For example, FR2 may be associated with a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., μ=3) , which includes 120 kHz subcarrier spacing.

In some embodiments, an AI/ML model may be deployed at the UE 104, and may be called as UE-sided model. The UE 104 may perform an applicable functionality reporting procedure for beam management of the UE-sided model.

FIG. 2 illustrates a diagram illustrating an example applicable functionality reporting procedure 200 in which some embodiments of the present disclosure can be implemented. For the purpose of discussion, in the following, the procedure 200 will be described with reference to FIG. 1. The procedure 200 may involve the UE 104 and the network entity 102 as shown in FIG. 1. It is to be understood that the steps and the order of the steps in FIG. 2 are merely for illustration, and not for limitation. For example, the order of the steps may be changed. Some of the steps may be omitted or any other suitable additional steps may be added.

As shown in FIG. 2, at step 210, the network entity 102 may transmit, to the UE 104, a request to initiate a procedure of reporting supported functionalities at the UE side, e.g., via a UE capability enquiry message or any other suitable messages. At step 220, the UE 104 may transmit, to the network entity 102, UE capability information comprising one or more supported functionalities at the UE side, e.g., via a UE capability information message or any other suitable messages.

At step 230, the network entity 102 may transmit, to the UE 104, a configuration indicating at least one of the following: NW-side additional conditions; or the UE 104 is allowed to do UE assistance information (UAI) reporting via an information element (IE) “OtherConfig” . In some embodiments, the network entity 102 may transmit the configuration via a RRC reconfiguration message or any other suitable messages.

In some embodiments, the configuration provided in the step 230 may indicate that an applicability report is based on: A) one or more CSI report configurations for inference configuration. An associated identity (ID) of each of the one or more CSI report configurations may be configured in CSI framework. In some embodiments, a CSI report configuration for UE-side model inference may not be activated immediately upon reception in the step 230.

In some embodiments, the configuration provided in the step 230 may indicate that an applicability report is based on: B) one set or multiple sets of inference related parameters for applicability report only (not for inference) . In some embodiments, the set of inference related parameters is selected from IEs in/or IEs referred by CSI report configurations as a starting point. In some embodiments, the set of inference related parameters may comprise one or more of the following: an associated ID; Set A related information; Set B related information; report content related information; time instances related information for measurements for BM-Case 2; or time instances related information for prediction for BM-Case 2.

It is to be noted that the configuration provided in the step 230 may indicate that an applicability report is based on A) and B) .

At step 240, the UE 104 may report one or more applicable functionalities to the network entity 102, e.g., via a RRC reconfiguration complete message or any other suitable messages. In some embodiments, the UE 104 may determine the one or more applicable functionalities based on the NW-side additional conditions (if provided) , UE-side additional conditions (internally known by the UE 104) and model availability in the UE 104.

In some embodiments, the UE 104 may report the one or more applicable functionalities via UAI upon being configured to provide applicable functionality and upon change of applicable functionality. In some embodiments, the UE 104 may report the one or more applicable functionalities as a response to NW-side additional conditions requesting applicable functionality reporting in the step 230. It is to be understood that the UE 104 may report the one or more applicable functionalities in any other suitable scenarios.

In some embodiments, the UE 104 may report applicability for all the above A) one or more CSI report configurations and/or B) one set or multiple sets of inference related parameters. In some embodiments, if A) is configured in the step 230, an applicable aperiodic CSI report and semi-persistent CSI report may be activated/triggered by the network entity 102 after the applicability reported. Alternatively or additionally, an applicable periodic CSI report may be considered as activated only if the applicability of the corresponding CSI report configuration is reported (e.g., in a RRC reconfiguration complete message) .

At step 250, the network entity 102 may transmit an inference configuration or an update to the inference configuration to the UE 104 after applicable functionality reporting, e.g., via a RRC reconfiguration message or any other suitable messages. In some embodiments, if an inference configuration based on a supported functionality is not provided in the step 230, the inference configuration may be provided in the step 250. If the inference configuration based on the supported functionality has been provided in the step 230, it is up to network implementation whether to provide an updated configuration or not.

In some embodiments, the network entity 102 may optionally configure a CSI report configuration for inference configuration in a RRC reconfiguration message, where an associated ID of the CSI report configuration may be configured in CSI framework.

It is to be noted that the step 250 may be optional if the UE 104 has already been configured with a CSI report configuration in the step 230.

Embodiments of the present disclosure provide a solution of communication so as to enhance CSI processing for AI/ML use cases. In the solution, UE capability related to a first functionality (also referred to as first information or AI/ML related UE capability herein) is considered for transmission and reception of CSI report (s) for a first functionality. It is to be noted that the present solution is not limited to be applied in AI/ML use cases, and may also be applied to any CSI processing scenarios existing or to be developed in future. The solution will be detailed in connection with FIGs. 3 to 7D below.

FIG. 3 illustrates a signaling chart illustrating an example process 300 of communication that supports CSI processing in accordance with aspects of the present disclosure. For the purpose of discussion, in the following, the process 300 will be described with reference to FIG. 1. The process 300 may involve the UE 104 and the network entity 102 as shown in FIG. 1. It is to be understood that the steps and the order of the steps in FIG. 3 are merely for illustration, and not for limitation. For example, the order of the steps may be changed. Some of the steps may be omitted or any other suitable additional steps may be added.

As shown in FIG. 3, at step 310, the UE 104 may transmit, to the network entity 102, UE capability related to a first functionality (also referred to as first information or AI/ML related UE capability herein) . The UE capability may facilitate the network entity 102 to configure one or more CSI report configurations or one or more sets of inference related parameters for the UE 104.

In some embodiments, the first information may indicate number (also referred to as a first number and denoted as N_CPU, AI herein) of CPUs supported by the UE 104 for processing a set of CSI reports (also referred to AI/ML CSI reports herein) associated with a set of first functionalities. In other words, the first information may indicate the number of supported simultaneous CSI calculations for AI/ML CSI reports.

In some embodiments, the first information may comprise N_CPU, AI . In some embodiments, the first information may comprise a scale factor for N_CPU, AI. In this case, N_CPU, AI may be determined based on the scale factor for N_CPU, AI and a reference number (also referred to as a first reference number herein) of CPUs. For example, N_CPU, AI may be determined by a product of the scale factor for N_CPU, AI and the first reference number of CPUs. It is to be noted that N_CPU, AI may also be determined in any other suitable ways, and the present disclosure does not limit this aspect.

In some embodiments, the first reference number of CPUs may be number (denoted as N_CPU herein) of CPUs occupied by a set of CSI reports (also referred to non-AI/ML CSI reports or legacy CSI reports herein) associated with a set of second functionalities, i.e., number of supported simultaneous CSI calculations for non-AI/ML CSI reports. It is to be noted that the first reference number of CPUs may also be determined in any other suitable ways, and the present disclosure does not limit this aspect.

In some embodiments, the first information may indicate number (for convenience, also referred to as a second number and denoted asherein) of CPUs occupied by each CSI report (e.g., CSI report n) in one or more CSI reports associated with the first functionality.

In some embodiments, the first information may compriseIn some embodiments, the first information may comprise a scale factor forIn this case, may be determined based on the scale factor forand a reference number (also referred to as a second reference number herein) of CPUs. For example, may be determined by a product of the scale factor forand the second reference number of CPUs. It is to be noted thatmay also be determined in any other suitable ways, and the present disclosure does not limit this aspect.

In some embodiments, the second reference number of CPUs may be number (denoted asherein) of CPUs occupied by each CSI report (e.g., CSI report n) in one or more CSI reports (i.e., non-AI/ML CSI reports) associated with a second functionality, i.e., number of CPUs occupied by a non-AI/ML CSI report. For example, for a CSI report for AI/ML beam prediction, the second reference number of CPUs is the number of CPUs occupied by a legacy or non-AI/ML CSI report for beam report. It is to be noted that the second reference number of CPUs may also be determined in any other suitable ways, and the present disclosure does not limit this aspect.

In some embodiments, the first information may indicate time (also referred to as first time or activation time herein, and denoted as X_activation herein) associated with model activation for the first functionality. In some embodiments, the first information may indicate time (also referred to as second time or inference time herein, and denoted as X_inference herein) associated with model inference for the first functionality.

In some embodiments, the first information may indicate a number (for convenience, also referred to as a third number and denoted as N_{CPU, AI, CSI} herein) of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality. That is, the first information may indicate the number of supported simultaneous CSI calculations for a supported functionality.

It is to be noted that the first information may indicate any combinations of the above information and any other suitable information.

In some embodiments, as shown in step 311, the UE 104 may transmit the first information to the network entity 102 in a procedure of reporting capability information of the UE 104. For example, with reference to FIG. 2, the UE 104 may transmit the first information to the network entity 102 in the step 220. As such, all AI/ML related UE capabilities may be reported by UE capability, and functionality-specific UE capabilities may be reported with a granularity of supported functionality. In some embodiments, the first information may comprise N_CPU, AI or the scale factor for N_CPU, AI , and also comprise X_activation and X_inference associated with each first functionality (e.g., {AI-CSI prediction functionality |X_{activation, CSI} , X_{inference, CSI} } , {AI-beam prediction functionality |X_{activation, beam}, X_{inference, beam}} , etc. ) . In some embodiments, the UE 104 may report supported AI/ML functionalities and the number of supported simultaneous CSI calculations for each supported functionality, e.g., {AI/ML CSI prediction functionality | N_{CPU, AI, CSI}} .

In some alternative embodiments, the first information may be divided into a first part and a second part. The first part is associated with one or more supported functionalities. The second part is associated with one or more applicable functionalities. As shown in step 312, the UE 104 may transmit the first part of the first information in a procedure of reporting capability information of the UE 104. As shown in step 313, the UE 104 may transmit the second part of the first information in a procedure of reporting applicable functionality information of the UE 104.

For example, with reference to FIG. 2, the UE 104 may transmit the first part of the first information to the network entity 102 in the step 220 of FIG. 2. In some embodiments, the UE 104 may report N_CPU, AI and supported functionalities in a UE capability information message. Under each supported functionality, activation time and inference time may be reported in the UE capability information message. That is, the first part may comprise N_CPU, AI or the scale factor for N_CPU, AI , and also comprise X_activation and X_inference associated with each first functionality (e.g., {AI-CSI prediction functionality | X_{activation, CSI}, X_{inference, CSI} } , {AI-beam prediction functionality | X_{activation, beam} , X_{inference, beam}} , etc. ) . Alternatively, the activation time may not be necessary. In some embodiments, the UE 104 may report supported AI/ML functionalities and the number of supported simultaneous CSI calculations for each supported functionality, e.g., {AI/ML CSI prediction functionality |N_{CPU, AI, CSI}} .

For example, with reference to FIG. 2, the UE 104 may transmit the second part of the first information to the network entity 102 in the step 240 of FIG. 2. In some embodiments, the UE 104 may report applicability of CSI report configurations or applicability of sets of inference related parameters in a RRC reconfiguration complete or UAI message. For each applicable CSI report configuration or set of inference related parameters, the required number of CPUs is reported together in the RRC reconfiguration complete or UAI message. In some embodiments, the second part may compriseassociated with each first functionality (e.g., for AI-CSI prediction functionality, for AI-beam prediction functionality, etc. ) .

In some embodiments, the UE 104 may report an applicable set of inference related parameters for CSI prediction and the required number of CPUs O_{CPU, AI, CSI1}, which means that O_{CPU, AI, CSI1} CPUs are required to be occupied for a CSI report associated with the applicable set of inference parameters for CSI prediction. Alternatively, a scale factor γfor O_{CPU, AI, CSI1} may be reported in the RRC reconfiguration complete or UAI message. In this case, O_{CPU, AI, CSI1} is the product of the scale factor γ and number of CPUs for a legacy CSI report.

In some embodiments, as shown in step 314, the UE 104 may update the applicability of CSI report configurations or applicability of sets of inference related parameters, and update O_{CPU, AI, CSI1} or the scale factor for O_{CPU, AI, CSI1}, e.g., via a UAI message or any other suitable messages.

As such, common AI related UE capabilities may be reported by UE capability. Functionality-specific capabilities may be reported with a granularity of applicable functionality in applicability report signaling.

Continuing to refer to FIG. 3, at step 320, the UE 104 may receive, from the network entity 102, one or more configurations (also referred to as CSI report configurations herein) of one or more CSI reports for the first functionality. In other words, the first functionality may be associated with one or more CSI report configurations.

In some embodiments, a CSI report configuration may comprise a configuration of a priority of the CSI report configuration. In some embodiments, the CSI report configuration may comprise a configuration of CSI measurement and/or a configuration of CSI report, i.e., a CSI resource setting and/or a CSI reporting setting. In some embodiments, the CSI report configuration may comprise any other suitable information, and the present disclosure does not limit this aspect.

With reference to FIG. 3, at step 330, the UE 104 may transmit at least one CSI report (i.e., at least part) in the one or more CSI reports to the network entity 102 based on the first information. In some embodiments, as shown in step 331, the UE 104 may determine the at least one CSI report based on the first information. As shown in step 332, the UE 104 may transmit the determined at least one CSI report to the network entity 102.

In some embodiments, the UE 104 may determine the at least one CSI report by considering one or more of the following factors: total number of CPUs occupied by the at least one CSI report; CSI computation time; CSI reference resource; or CPU occupation time. These factors may be determined based on AI/ML related UE capabilities (i.e., the first information) . In this way, processing for AI/ML CSI report (s) may be achieved.

In some embodiments, the total number of CPUs occupied by the at least one CSI report may be determined based on the second numberof CPUs for each CSI report in the at least one CSI report. In other words, the total number of occupied CPUs for AI/ML CSI reports may be counted according to the occupied CPU number of each AI/ML CSI report determined by the scale factor for CPU number or the required CPU number for an AI/ML functionality reported by the UE 104.

In one aspect, to determine the at least one CSI report, a condition for CPU number is defined and needs to be satisfied. In some embodiments, the total number of CPUs occupied by the at least one CSI report is not greater than the first number (i.e., N_CPU, AI) of CPUs (i.e., is smaller than or equal to N_CPU, AI) , and a total number of CPUs occupied by one or more CSI reports associated with the second functionality is not greater than (i.e., is smaller than or equal to) the number (i.e., N_CPU) of CPUs supported by the UE 104 for processing a set of CSI reports associated with a set of second functionalities. In other words, the total number of CPUs occupied by all AI/ML CSI reports at same time is not greater than N_CPU, AI, and the total number of CPUs occupied by all non-AI/ML CSI reports at the same time is not greater than N_CPU.

In some alternative embodiments, the total number of CPUs occupied by the at least one CSI report is not greater than the first number (i.e., N_CPU, AI) of CPUs (i.e., is smaller than or equal to N_CPU, AI) , and the total number of CPUs occupied by the one or more CSI reports associated with the second functionality and the one or more CSI reports associated with the first functionality is not greater than (i.e., is smaller than or equal to) the number (i.e., N_CPU) of CPUs supported by the UE for processing the set of CSI reports associated with the set of second functionalities. In other words, the total number of CPUs occupied by all AI/ML CSI reports at same time is not greater than N_CPU, AI, and the total number of CPUs occupied by all CSI reports (including AI/ML CSI reports and non-AI/ML CSI reports) at the same time is not greater than N_CPU.

For illustration, an example CPU number counting may be described as below.
- A UE supports N_CPU, AI simultaneous CSI calculations for AI/ML CSI reports, which
means to have N_CPU, AI CPUs for processing AI/ML CSI reports. The UE supports N_CPU simultaneous CSI calculations, which means to have N_CPU CPUs for processing CSI reports; or the UE supports N_CPU-N_CPU, AI simultaneous CSI calculations for non-AI/ML CSI reports, which means to have N_CPU-N_CPU, AI CPUs for processing non-AI/ML CSI reports.
- If L CPUs are occupied for calculation of AI/ML CSI reports in a given OFDM symbol,
the UE has N_CPU, AI-L unoccupied CPUs. If N CSI reports start occupying their respective CPUs on the same OFDM symbol on which N_CPU, AI-L CPUs are unoccupied, where each AI/ML CSI report n=0, …, N-1 corresponds toandis determined by the scale factor for CPU number, is a product of the scale factor γ and the CPU number for a legacy CSI report, or the required CPU number for AI/ML functionality reported by UE, e.g., if n-th CSI report corresponds to AI/ML CSI prediction. The UE is not required to update the N-M requested CSI reports with lowest priority, where 0≤M≤N is the largest value such thatholds.

As such, according to the AI related UE capabilities, the number of occupied CPUs for AI/ML CSI reports may be counted. It is helpful to manage processing resources for AI/ML models developed by different UE vendors.

To avoid collision of AI/ML model usage resulted from activating overmuch CSI report configurations associated with the same AI/ML model, an additional condition for CPU number may be defined. In some embodiments, the total number of CPUs occupied by the at least one CSI report is not greater than (i.e., is smaller than or equal to) the third number (i.e., N_{CPU, AI, CSI}) of CPUs supported by the UE 104 for processing one or more CSI reports associated with the first functionality. In other words, the total number of CPUs occupied by all CSI reports associated with the supported functionality in a given OFDM symbol is not greater than N_{CPU, AI, CSI}. For example, the total number of CPUs occupied by CSI reports associated with AI/ML CSI prediction at the same time should be not greater than N_{CPU, AI, CSI}.

In some embodiments, the UE 104 may be configured with a priority level of CSI report configurations associated with one supported functionality by the network entity 102. Alternatively, the priority level may be predefined. In some embodiments, if multiple CSI reports associated with the first functionality are active in overlapped symbols (e.g., OFDM symbols) , the UE 104 may drop at least one of the multiple CSI reports based on priorities of CSI report configurations associated with the multiple CSI reports. For example, when more than one CSI report configuration associated with one supported functionality is active in overlapped OFDM symbols, the UE 104 may drop one or more CSI reports corresponding to one or more CSI report configurations with lower priority.

In some alternative embodiments, the UE 104 may report its ability of activating CSI report configurations simultaneously. In some embodiments, the UE 104 may transmit, to the network entity 102, information (for convenience, also referred to as second information herein) indicating applicability of the one or more configurations of the one or more CSI reports associated with the first functionality. In some embodiments, the second information may comprise information of multiple configurations of CSI reports that can be activated simultaneously. In some embodiments, the second information may comprise information of multiple configurations of CSI reports corresponding to sets of inference parameters that can be activated simultaneously. It is to be noted that the second information may comprise a combination of these information. In this way, the collision of AI/ML model usage resulted from activating overmuch CSI report configurations associated with the same AI/ML model may also be avoided.

In some embodiments, in a UAI or RRC reconfiguration complete message for reporting applicability of CSI report configurations or sets of inference related parameters, the UE 104 may report which CSI report configurations or CSI reports corresponding to the sets of inference parameters can be activated simultaneously. Alternatively, all applicable CSI report configurations or applicable sets of inference related parameters reported by the UE 104 can be active simultaneously.

As such, by reporting an additional AI-related capability on the number of supported simultaneous CSI calculations for a supported functionality, collision of AI/ML model usage may be avoided.

In another aspect, to determine the at least one CSI report, the CSI computation time and/or CSI reference resource also need to be determined. When a CSI request field on DCI triggers CSI report (s) for an AI/ML functionality on a physical uplink shared channel (PUSCH) , the UE 104 shall provide valid CSI report (s) for the triggered report (s) . To obtain the valid CSI report (s) for an AI/ML functionality, following operation is needed: AI/ML model activation for model inference, measurement result calculation, AI/ML model inference operation for obtaining inference results, and preparation of PUSCH carrying the CSI report (s) . To ensure the UE 104 has sufficient time to complete these operations before CSI report (s) for an AI/ML functionality triggered by DCI. Time requirements for the CSI computation time and/or CSI reference resource need to be defined and satisfied.

In some embodiments, a time interval between a latest one reference signal (e.g., CSI reference signal (CSI-RS) or synchronization signal and physical broadcast channel block (SSB) ) transmission occasion for channel measurement and a scheduled uplink transmission (e.g., PUSCH) carrying the at least one CSI report should be greater than a first time interval. The first time interval is determined based on the inference time of the first functionality. In other words, the first time interval is determined based on the inference time reported by the UE 104. It is to be noted that the first time interval may also be determined in any other suitable ways.

In some embodiments, a time interval between a downlink transmission (e.g., PDCCH) triggering the at least one CSI report and the scheduled uplink transmission (e.g., PUSCH) carrying the at least one report should be greater than a second time interval. In some embodiments, the second time interval may be determined based on the inference time. In other words, the second time interval is determined based on the inference time reported by the UE 104. In some embodiments, the second time interval may be determined based on the activation time and the inference time. In other words, the second time interval may be determined based on the activation time and the inference time reported by the UE 104. It is to be noted that the second time interval may also be determined in any other suitable ways.

For illustration, an example CSI computation may be described as below.
- For an aperiodic CSI report configuration, where report quantity is set for AI/ML
inference result, e.g., CSI-RS resource indicator (CRI) of predicted beams for spatial beam prediction, the CSI report starts no earlier than at symbol Z_ref and starts no earlier than at symbol Z′_ref, where Z_ref is defined as the next uplink symbol starting Z symbols after the end of the last symbol of the PDCCH triggering the CSI report (s) , and where Z′_ref is defined as the next uplink symbol starting Z′after the end of the last symbol in time of the latest of aperiodic CSI-RS resource for channel measurements when aperiodic CSI-RS is used for channel measurement for the CSI report.
- Wherein, Z=Z_AI, and Z_AI is determined based on activation time for an AI/ML functionality
reported by UE, e.g., X_{activation, SBP}; Z’ = Z′_AI, and Z′_AI is determined based on the inference time and the activation time for an AI/ML functionality reported by UE, e.g., X_{inference, SBP} and X_{activation, SBP} . For example, Z_AI = Z₃+X_{activation, SBP} and Z′_AI=Z₃+X_{activation, SBP}+X_{inference, SBP}, where Z₃ is a CSI computation delay requirement for legacy beam report.
- Alternatively, Z′_AI=Z_i+ (M-1) ×T+X_{inference, SBP} , where Z_i is the CSI computation
delay requirement for reporting beam or reporting predicted CSI, M is the number of CSI-RS resources for channel measurement and T is a time interval of two adjacent transmission occasions of a CSI-RS resource set. Alternatively, Z′_AI=Z_i+Max ( (M-1) ×T, X_{activation, SBP}) +X_{inference, SBP}, where the Max (A, B) denotes the maximum of A and B.
- When a periodic or semi-persistent CSI-RS resource is used for channel measurement for
the CSI report (s) triggered by DCI for AI/ML functionality, the periodic or semi-persistent CSI-RS resource should be no later than Z′_AI symbols before the PUSCH carrying the CSI report (s) .
- For an aperiodic CSI report for AI/ML functionality, a time slot of a CSI reference
resource should be earlier than Z′_AI symbols before an uplink slot of the corresponding CSI report.

As such, according to the AI related UE capabilities, CSI computation time for AI/ML CSI reports may be determined. It is helpful to manage processing resources for AI/ML models developed by different UE vendors.

In still another aspect, to align between the network entity 102 and the UE 104 that CPU occupation time for a CSI report for an AI/ML functionality, a rule of CPU occupation time needs to be defined for the AI/ML functionality. To avoid long CPU occupation time for AI/ML temporal beam prediction, CPU occupation needs to be designed to cover time of necessary operations.

In some embodiments, when a periodic or semi-persistent CSI report is configured or activated by the network entity 102 for an AI/ML functionality, one or more CPUs may be occupied for one or more durations. Some example embodiments for the periodic or semi-persistent CSI report will be described below. In these embodiments, the at least one CSI report to be transmitted is periodic or semi-persistent.

In some embodiments, the one or more CPUs may be occupied for the at least one CSI report from a first symbol of an earliest one reference signal of a latest one reference signal (e.g., CSI-RS or SSB) transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until a last symbol of a scheduled uplink transmission (e.g., PUSCH or PUCCH) carrying the at least one CSI report. An example will be described in connection with FIG. 4A.

FIG. 4A illustrates a diagram 400A illustrating an example CPU occupation for a periodic or semi-persistent CSI report in accordance with aspects of the present disclosure. As shown in FIG. 4A, a periodic CSI report for temporal beam prediction is configured to be reported in a PUCCH 411. One or more CPUs are occupied from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion 412 of CSI-RS/SSB resource set, no later than the corresponding CSI reference resource, until the last symbol of the PUCCH 411 carrying the CSI report. That is, the one or more CPUs may be occupied in a time window 410.

In some embodiments, the one or more CPUs may be occupied one or more CPUs are occupied for the at least one CSI report from the first symbol of the earliest one reference signal to a first number (e.g., Z′₃) of symbols after the last symbol of a last one reference signal for a reference signal transmission occasion for channel measurement. The reference signal transmission occasion is a transmission occasion other than the latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report. Further, the one or more CPUs are occupied from the first symbol of the earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until the last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In other words, the one or more CPUs may be occupied during multiple durations (i.e., time windows) . The multiple duration may comprise N (where N is a positive integer) durations for channel measurement which correspond to the latest N transmission occasions, no later than the corresponding CSI reference resource, of CSI-RS/SSB resource set corresponding to the CSI report. Each of the N durations starts from the first symbol of the earliest one CSI-RS/SSB of the corresponding transmission occasion, until the first number of symbols after the last symbol of the last one CSI-RS/SSB of the corresponding transmission occasion. Further, the multiple durations may comprise one duration for model inference and PUSCH preparation which starts from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion, no later than the corresponding CSI reference resource, until the last symbol of PUSCH or PUCCH carrying the CSI report. An example will be described in connection with FIG. 4B.

FIG. 4B illustrates a diagram 400B illustrating another example CPU occupation for a periodic or semi-persistent CSI report in accordance with aspects of the present disclosure. As shown in FIG. 4B, one or more CPUs may be occupied in multiple time windows 421, 422, 423 and 424. A periodic CSI report for temporal beam prediction is configured to be reported in a PUCCH 425. Each of the time windows 421, 422 and 423 starts from the first symbol of the earliest one CSI-RS/SSB of the corresponding transmission occasion until Z′₃symbols after the last symbol of the last one CSI-RS/SSB of the corresponding transmission occasion, where the Z′₃is the CSI computation delay requirement for legacy beam report. The time window 424 starts from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion 426, no later than the corresponding CSI reference resource, until the last symbol of the PUCCH 425 carrying the CSI report.

In some embodiments, when an aperiodic CSI report is configured or activated by the network entity 102 for an AI/ML functionality, one or more CPUs may be occupied for one or more durations. Some example embodiments for the aperiodic CSI report will be described below. In these embodiments, the at least one CSI report to be transmitted is aperiodic.

In some embodiments, one or more CPUs may be occupied for the at least one CSI report from the first symbol of the earliest one reference signal of the latest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until the last symbol of a scheduled uplink transmission carrying the at least one CSI report. An example will be described in connection with FIG. 5A.

FIG. 5A illustrates a diagram 500A illustrating an example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure. As shown in FIG. 5A, via DCI, an aperiodic CSI report for temporal beam prediction is configured to be reported in a PUSCH 511. One or more CPUs are occupied for the CSI report during a time window 510 that starts from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion 512, no later than the corresponding CSI reference resource, of CSI-RS/SSB resource set corresponding to the CSI report, until the last symbol of the PUSCH 511 carrying the CSI report.

In some embodiments, the one or more CPUs may be occupied for the at least one CSI report from the first symbol of the earliest one reference signal to a second number (Z′₃) of symbols after the last symbol of the last one reference signal for a reference signal transmission occasion for channel measurement, and the reference signal transmission occasion is a transmission occasion other than the latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report. Further, the one or more CPUs may be occupied from the first symbol of the earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until the last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In other words, the one or more CPUs may be occupied during multiple durations (i.e., time windows) . The multiple duration may comprise N (where N is a positive integer) durations for channel measurement which correspond to the latest N transmission occasions, no later than the corresponding CSI reference resource, of CSI-RS/SSB resource set corresponding to the CSI report. Each of the N durations starts from the first symbol of the earliest one CSI-RS/SSB of the corresponding transmission occasion, until the second number of symbols after the last symbol of the last one CSI-RS/SSB of the corresponding transmission occasion. Further, the multiple durations may comprise one duration for model inference and PUSCH preparation which starts from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion, no later than the corresponding CSI reference resource, until the last symbol of PUSCH or PUCCH carrying the CSI report. An example will be described in connection with FIG. 5B.

FIG. 5B illustrates a diagram 500B illustrating another example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure. As shown in FIG. 5B, one or more CPUs may be occupied in multiple time windows 521, 522, 523 and 524. An aperiodic CSI report for temporal beam prediction is configured to be reported in a PUSCH 525. Each of the time windows 521, 522 and 523 starts from the first symbol of the earliest one CSI-RS/SSB of the corresponding transmission occasion until Z′₃symbols after the last symbol of the last one CSI-RS/SSB of the corresponding transmission occasion, where the Z′₃is the CSI computation delay requirement for legacy beam report. The time window 524 starts from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion 526, no later than the corresponding CSI reference resource, until the last symbol of PUSCH or PUCCH 525 carrying the CSI report.

In some embodiments, the one or more CPUs may be occupied for the at least one CSI report during at least one of multiple time windows. The multiple time windows may comprise a time window (for convenience, also referred to as a first time window herein) starting from the first symbol of DCI triggering the one or more CSI reports until the later one of a third number (e.g., Z) of symbols after the last symbol of the DCI, and a fourth number (e.g., Z’) of symbols after the last symbol of the earliest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report.

The multiple time windows may also comprise one or more time windows (for convenience, also referred to as one or more second time windows herein) starting from the first symbol of a reference signal transmission occasion, until a fifth number (e.g., Z”) of symbols after the last symbol of the reference signal transmission occasion. The reference signal transmission occasion is a transmission occasion other than the earliest one reference signal transmission occasion and the latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report. In some embodiments, the fifth number may be different from the fourth number. In some embodiments, the fifth number may be equal to the fourth number, i.e., Z”= Z’.

The multiple time windows may also comprise a time window (for convenience, also referred to as a third time window herein) starting from the first symbol of the latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report, until the last symbol of a scheduled uplink transmission carrying the at least one CSI report. Some examples will be described in connection with FIGs. 5C and 5D.

FIG. 5C illustrates a diagram 500C illustrating another example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure. As shown in FIG. 5C, one or more CPUs may be occupied in multiple time windows 531, 532, 533 and 534. Via DCI 530, an aperiodic CSI report for temporal beam prediction is configured to be reported in a PUSCH 535.

The time window 531 (i.e., the first time window) starts from the first symbol of the DCI 530 triggering the one or more CSI reports until the later one of: Z symbols after the last symbol of the DCI 530, or Z’ symbols after the last symbol of the earliest one reference signal transmission occasion 536 of a resource set corresponding to the at least one CSI report.

Each of the time windows 532 and 533 (i.e., the second time windows) starts from the first symbol of the earliest one CSI-RS/SSB of the corresponding transmission occasion until Z” symbols after the last symbol of the last one CSI-RS/SSB of the corresponding transmission occasion. For example, Z” may be equal to Z’.

The time window 534 (i.e., the third time window) starts from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion 537, no later than the corresponding CSI reference resource, until the last symbol of PUSCH 535 carrying the CSI report.

FIG. 5D illustrates a diagram 500D illustrating another example CPU occupation for an aperiodic CSI report in accordance with aspects of the present disclosure. As shown in FIG. 5D, one or more CPUs may be occupied in two time windows 541 and 542. Via DCI 540, an aperiodic CSI report for temporal beam prediction is configured to be reported in a PUSCH 543.

The time window 541 (i.e., the first time window) starts from the first symbol of the DCI 540 triggering the one or more CSI reports until the later one of: Z symbols after the last symbol of the DCI 540, or Z’ symbols after the last symbol of the earliest one reference signal transmission occasion 544 of a resource set corresponding to the at least one CSI report.

The time window 534 (i.e., the third time window) starts from the first symbol of the earliest one CSI-RS/SSB of the latest one transmission occasion 545, no later than the corresponding CSI reference resource, until the last symbol of the PUSCH 543 carrying the CSI report.

It is to be noted that FIGs. 4A to 5D are merely for illustration, and do not limit the present disclosure. Any other suitable ways may also be feasible.

As such, CPU occupation time may be reduced, and power saving may be achieved.

Continuing to refer to FIG. 3, at step 340, the network entity 102 may receive and determine the at least one CSI report based on the AI/ML related UE capabilities (i.e., the first information) . In some embodiments, the network entity 102 may determine the at least one CSI report based on the first information in a similar way as that described for the UE 104. Other details are not repeated here for conciseness. As such, a CSI report may be received correctly.

So far, a solution of CSI processing is described. With the solution, CSI processing may be enhanced at least for AI/ML use cases. According to the AI related UE capabilities, the number of occupied CPUs for AI/ML CSI reports may be counted and CSI computation time for AI/ML CSI reports may be determined. Thus, management on processing resources for AI/ML models developed by different UE vendors may be facilitated. Further, by reporting an additional AI-related capability on the number of supported simultaneous CSI calculations for a supported functionality, collision of AI/ML model usage may be avoided. In addition, CPU occupation time may be optimized to cover time of necessary operations.

It is to be noted that operations or steps described in any one or more of the above processes may be carried out separately or in any suitable combinations.

FIG. 6 illustrates an example of a device 600 that supports CSI processing in accordance with aspects of the present disclosure. The device 600 may be an example of a UE or a network entity as described herein. The device 600 may support wireless communication with one or more network entities, UEs, or any combination thereof. The device 600 may include components for bi-directional communications including components for transmitting and receiving communications, such as a processor 602, a memory 604, a transceiver 606, and, optionally, an I/O controller 608. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .

The processor 602, the memory 604, the transceiver 606, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. For example, the processor 602, the memory 604, the transceiver 606, or various combinations or components thereof may support a method for performing one or more of the operations described herein.

In some implementations, the processor 602, the memory 604, the transceiver 606, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure. In some implementations, the processor 602 and the memory 604 coupled with the processor 602 may be configured to perform one or more of the functions described herein (e.g., executing, by the processor 602, instructions stored in the memory 604) .

For example, the processor 602 may support wireless communication at the device 600 in accordance with examples as disclosed herein. In some embodiments where the device 600 is used to implement a UE (e.g., the UE 104) , the processor 602 may be configured to operable to support a means for: receiving, at a UE from a network entity via a transceiver, one or more configurations of one or more CSI reports for a first functionality; and transmitting, to the network entity, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.

In some embodiments where the device 600 is used to implement a network entity (e.g., the network entity 102) , the processor 602 may be configured to operable to support a means for: transmitting, at a network entity to a UE via a transceiver, one or more configurations of one or more CSI reports for a first functionality; and receiving, from the network entity via the transceiver, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with a first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.

The processor 602 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, a microcontroller, an ASIC, an FPGA, a programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, or any combination thereof) . In some implementations, the processor 602 may be configured to operate a memory array using a memory controller. In some other implementations, a memory controller may be integrated into the processor 602. The processor 602 may be configured to execute computer-readable instructions stored in a memory (e.g., the memory 604) to cause the device 600 to perform various functions of the present disclosure.

The memory 604 may include random access memory (RAM) and read-only memory (ROM) . The memory 604 may store computer-readable, computer-executable code including instructions that, when executed by the processor 602 cause the device 600 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some implementations, the code may not be directly executable by the processor 602 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some implementations, the memory 604 may include, among other things, a basic I/O system (BIOS) which may control basic hardware or software operation such as the interaction with peripheral components or devices.

The I/O controller 608 may manage input and output signals for the device 600. The I/O controller 608 may also manage peripherals not integrated into the device 600. In some implementations, the I/O controller 608 may represent a physical connection or port to an external peripheral. In some implementations, the I/O controller 608 may utilize an operating system such asor another known operating system. In some implementations, the I/O controller 608 may be implemented as part of a processor, such as the processor 606. In some implementations, a user may interact with the device 600 via the I/O controller 608 or via hardware components controlled by the I/O controller 608.

In some implementations, the device 600 may include a single antenna 610. However, in some other implementations, the device 600 may have more than one antenna 610 (i.e., multiple antennas) , including multiple antenna panels or antenna arrays, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 606 may communicate bi-directionally, via the one or more antennas 610, wired, or wireless links as described herein. For example, the transceiver 606 may represent a wireless transceiver and may communicate bi-directionally with another wireless transceiver. The transceiver 606 may also include a modem to modulate the packets, to provide the modulated packets to one or more antennas 610 for transmission, and to demodulate packets received from the one or more antennas 610. The transceiver 606 may include one or more transmit chains, one or more receive chains, or a combination thereof.

A transmit chain may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmit chain may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmit chain may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmit chain may also include one or more antennas 610 for transmitting the amplified signal into the air or wireless medium.

A receive chain may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receive chain may include one or more antennas 610 for receive the signal over the air or wireless medium. The receive chain may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receive chain may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receive chain may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

FIG. 7 illustrates an example of a processor 700 that supports CSI processing in accordance with aspects of the present disclosure. The processor 700 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 700 may include a controller 702 configured to perform various operations in accordance with examples as described herein. The processor 700 may optionally include at least one memory 704, such as L1/L2/L3 cache. Additionally, or alternatively, the processor 700 may optionally include one or more arithmetic-logic units (ALUs) 706. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .

The processor 700 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 700) or other memory (e.g., random access memory (RAM) , read-only memory (ROM) , dynamic RAM (DRAM) , synchronous dynamic RAM (SDRAM) , static RAM (SRAM) , ferroelectric RAM (FeRAM) , magnetic RAM (MRAM) , resistive RAM (RRAM) , flash memory, phase change memory (PCM) , and others) .

The controller 702 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. For example, the controller 702 may operate as a control unit of the processor 700, generating control signals that manage the operation of various components of the processor 700. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

The controller 702 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 704 and determine subsequent instruction (s) to be executed to cause the processor 700 to support various operations in accordance with examples as described herein. The controller 702 may be configured to track memory address of instructions associated with the memory 704. The controller 702 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 702 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 700 to cause the processor 700 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 702 may be configured to manage flow of data within the processor 700. The controller 702 may be configured to control transfer of data between registers, arithmetic logic units (ALUs) , and other functional units of the processor 700.

The memory 704 may include one or more caches (e.g., memory local to or included in the processor 700 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementation, the memory 704 may reside within or on a processor chipset (e.g., local to the processor 700) . In some other implementations, the memory 704 may reside external to the processor chipset (e.g., remote to the processor 700) .

The memory 704 may store computer-readable, computer-executable code including instructions that, when executed by the processor 700, cause the processor 700 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 702 and/or the processor 700 may be configured to execute computer-readable instructions stored in the memory 704 to cause the processor 700 to perform various functions. For example, the processor 700 and/or the controller 702 may be coupled with or to the memory 704, and the processor 700, the controller 702, and the memory 704 may be configured to perform various functions described herein. In some examples, the processor 700 may include multiple processors and the memory 704 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.

The one or more ALUs 706 may be configured to support various operations in accordance with examples as described herein. In some implementation, the one or more ALUs 706 may reside within or on a processor chipset (e.g., the processor 700) . In some other implementations, the one or more ALUs 706 may reside external to the processor chipset (e.g., the processor 700) . One or more ALUs 706 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 706 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 706 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 706 may support logical operations such as AND, OR, exclusive-OR (XOR) , not-OR (NOR) , and not-AND (NAND) , enabling the one or more ALUs 706 to handle conditional operations, comparisons, and bitwise operations.

The processor 700 may support wireless communication in accordance with examples as disclosed herein. In some embodiments where the processor 700 is implemented at a UE (e.g., the UE 104) , the processor 700 may be configured to operable to support a means for: receiving, at a UE from a network entity via a transceiver, one or more configurations of one or more CSI reports for a first functionality; and transmitting, to the network entity, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.

In some embodiments where the processor 700 is implemented at a network entity (e.g., the network entity 102) , the processor 700 may be configured to operable to support a means for: transmitting, at a network entity to a UE via a transceiver, one or more configurations of one or more CSI reports for a first functionality; and receiving, from the network entity via the transceiver, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with a first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.

FIG. 8 illustrates a flowchart of a method 800 that supports CSI processing in accordance with aspects of the present disclosure. The operations of the method 800 may be implemented by a device or its components as described herein. For example, the operations of the method 800 may be performed by a UE (e.g., the UE 104) as described herein. In some implementations, the device may execute a set of instructions to control the function elements of the device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

At block 810, the method 800 may include: receiving, at a UE from a network entity via a transceiver, one or more configurations of one or more CSI reports for a first functionality. The operations of 810 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 810 may be performed by a device as described with reference to FIG. 1.

At block 820, the method 800 may include: transmitting, to the network entity via the transceiver, at least one CSI report in the one or more CSI reports based on first information. The first information indicates at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality. The operations of 820 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 820 may be performed by a device as described with reference to FIG. 1.

In some embodiments, the method 800 may further comprise: transmitting, to the network entity via the transceiver, the first information in a procedure of reporting capability information of the UE.

In some embodiments, the first information comprises a first part and a second part. The first part is associated with one or more supported functionalities, and the second part is associated with one or more applicable functionalities. The method 800 may further comprise: transmitting, to the network entity via the transceiver, the first part of the first information in a procedure of reporting capability information of the UE; and transmitting, to the network entity via the transceiver, the second part of the first information in a procedure of reporting applicable functionality information of the UE.

In some embodiments, the first or second number of CPUs may be determined based on a scale factor and a reference number of CPUs.

In some embodiments, the at least one CSI report occupies one or more CPUs. A total number of CPUs in the one or more CPUs is determined based on the second number of CPUs for each CSI report in the at least one CSI report, and the total number of CPUs is smaller than or equal to the first number of CPUs.

In some embodiments, a total number of CPUs occupied by one or more CSI reports associated with a second functionality is smaller than or equal to a number of CPUs supported by the UE for processing a set of CSI reports associated with a set of second functionalities, or a total number of CPUs occupied by the one or more CSI reports associated with the second functionality and the one or more CSI reports associated with the first functionality is smaller than or equal to the number of CPUs supported by the UE for processing the set of CSI reports associated with the set of second functionalities.

In some embodiments, the at least one CSI report simultaneously occupies one or more CPUs, and a total number of CPUs in the one or more CPUs is smaller than or equal to the third number of CPUs.

In some embodiments, the method 800 may further comprise: receiving, from the network entity via the transceiver, a configuration indicating a priority of a configuration of each CSI report in the one or more CSI reports; and in accordance with a determination that multiple CSI reports associated with the first functionality are active in overlapped symbols, dropping at least one of the multiple CSI reports based on the priority.

In some embodiments, the method 800 may further comprise: transmitting, to the network entity via the transceiver, second information indicating applicability of the one or more configurations of the one or more CSI reports associated with the first functionality.

In some embodiments, the second information comprises at least one of the following: information of multiple configurations of CSI reports that can be activated simultaneously; or information of multiple configurations of CSI reports corresponding to sets of inference parameters that can be activated simultaneously.

In some embodiments, the at least one CSI report is carried by a scheduled uplink transmission. A time interval between a latest one reference signal transmission occasion for channel measurement and the scheduled uplink transmission carrying the at least one CSI report is greater than a first time interval, and the first time interval is determined based on the second time.

In some embodiments, the at least one CSI report is carried by a scheduled uplink transmission. A time interval between a downlink transmission triggering the at least one CSI report and the scheduled uplink transmission carrying the at least one report is greater than a second time interval, and the second time interval is determined based on the second time or based on the first time and the second time.

In some embodiments where the at least one CSI report is periodic or semi-persistent, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal of a latest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some embodiments where the at least one CSI report is periodic or semi-persistent, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal to a first number of symbols after a last symbol of a last one reference signal for a reference signal transmission occasion for channel measurement, and the reference signal transmission occasion is a transmission occasion other than a latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report. The one or more CPUs are occupied from a first symbol of an earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some embodiments where the at least one CSI report is aperiodic, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal of a latest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some embodiments where the at least one CSI report is aperiodic, one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal to a second number of symbols after a last symbol of a last one reference signal for a reference signal transmission occasion for channel measurement, and the reference signal transmission occasion is a transmission occasion other than a latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report. The one or more CPUs are occupied from a first symbol of an earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

In some embodiments where the at least one CSI report is aperiodic, one or more CPUs are occupied for the at least one CSI report during at least one of the following: a time window starting from a first symbol of DCI triggering the one or more CSI reports until a later one of a third number of symbols after a last symbol of the DCI, and a fourth number of symbols after a last symbol of an earliest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report; one or more time windows starting from a first symbol of a reference signal transmission occasion, until a fifth number of symbols after a last symbol of the reference signal transmission occasion, wherein the reference signal transmission occasion is a transmission occasion other than the earliest one reference signal transmission occasion and a latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report; or a time window starting from a first symbol of the latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.

FIG. 9 illustrates a flowchart of another method 900 that supports CSI processing in accordance with aspects of the present disclosure. The operations of the method 900 may be implemented by a device or its components as described herein. For example, the operations of the method 900 may be performed by a network entity (e.g., the network entity 102) described herein. In some implementations, the device may execute a set of instructions to control the function elements of the device to perform the described functions. Additionally, or alternatively, the device may perform aspects of the described functions using special-purpose hardware.

At block 910, the method 900 may include transmitting, at a network entity to a UE via a transceiver, one or more configurations of one or more CSI reports for a first functionality. The operations of 910 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 910 may be performed by a device as described with reference to FIG. 1.

At block 920, the method 900 may include receiving, from the network entity via the transceiver, at least one CSI report in the one or more CSI reports based on first information. The first information indicates at least one of the following: a first number of CPUs supported by the UE for processing a set of CSI reports associated with a set of first functionalities, a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality, first time associated with model activation for the first functionality, second time associated with model inference for the first functionality, or a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality. The operations of 920 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 920 may be performed by a device as described with reference to FIG. 1.

In some embodiments, the method 900 may further comprise: receiving, from the UE via the transceiver, the first information in a procedure of reporting capability information of the UE.

In some embodiments, the first information comprises a first part and a second part. the first part is associated with one or more supported functionalities, and the second part is associated with one or more applicable functionalities. The method 900 may further comprise: receiving, from the UE via the transceiver, the first part of the first information in a procedure of reporting capability information of the UE; and receiving, from the UE via the transceiver, the second part of the first information in a procedure of reporting applicable functionality information of the UE.

In some embodiments, the first or second number of CPUs is determined based on a scale factor and a reference number of CPUs.

In some embodiments, the at least one CSI report occupies one or more CPUs, and a total number of CPUs in the one or more CPUs is determined based on the second number of CPUs for each CSI report in the at least one CSI report, and the total number of CPUs is smaller than or equal to the first number of CPUs.

In some embodiments, the method 900 may further comprise: transmitting, to the UE via the transceiver, a configuration indicating a priority of a configuration of each CSI report in the one or more CSI reports.

In some embodiments, the method 900 may further comprise: receiving, from the UE via the transceiver, second information indicating applicability of the one or more configurations of the one or more CSI reports associated with the first functionality.

In some embodiments, the at least one CSI report is carried by a scheduled uplink transmission, and a time interval between a latest one reference signal transmission occasion for channel measurement and the scheduled uplink transmission carrying the at least one CSI report is greater than a first time interval, and the first time interval is determined based on the second time.

In some embodiments, the at least one CSI report is carried by a scheduled uplink transmission, and a time interval between a downlink transmission triggering the at least one CSI report and the scheduled uplink transmission carrying the at least one report is greater than a second time interval, and the second time interval is determined based on the second time or based on the first time and the second time.

It is to be understood that operations of the methods 800 and 900 correspond to the processes described in connection with FIGs. 1 to 5D, and thus other details are omitted here for conciseness.

It should be noted that the methods described herein describes possible implementations, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible. Further, aspects from two or more of the methods may be combined.

The various illustrative blocks and components described in connection with the disclosure herein may be implemented or performed with a general-purpose processor, a DSP, an ASIC, a CPU, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope of the disclosure and appended claims. For example, due to the nature of software, functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.

Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer. By way of example, non-transitory computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM) , flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that may be used to carry or store desired program code means in the form of instructions or data structures and that may be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor.

As used herein, including in the claims, an article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a, ” “at least one, ” “one or more, ” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of” or “one or more of” or “one or both of” ) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) . Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.

The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.

Claims

A user equipment (UE) , comprising:

a processor; and

a transceiver coupled to the processor,

wherein the processor is configured to:

receive, from a network entity via the transceiver, one or more configurations of one or more channel status information (CSI) reports for a first functionality; and

transmit, to the network entity via the transceiver, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following:

a first number of CSI processing units (CPUs) supported by the UE for processing a set of CSI reports associated with a set of first functionalities,

a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality,

first time associated with model activation for the first functionality,

second time associated with model inference for the first functionality, or

a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.
The UE of claim 1, wherein the processor is further configured to:

transmit, to the network entity via the transceiver, the first information in a procedure of reporting capability information of the UE.
The UE of claim 1, wherein the first information comprises a first part associated with one or more supported functionalities and a second part associated with one or more applicable functionalities, and wherein the processor is further configured to:

transmit, to the network entity via the transceiver, the first part of the first information in a procedure of reporting capability information of the UE; and

transmit, to the network entity via the transceiver, the second part of the first information in a procedure of reporting applicable functionality information of the UE.
The UE of claim 1, wherein the first or second number of CPUs is determined based on a scale factor and a reference number of CPUs.
The UE of claim 1, wherein the at least one CSI report occupies one or more CPUs, and a total number of CPUs in the one or more CPUs is determined based on the second number of CPUs for each CSI report in the at least one CSI report, and

wherein the total number of CPUs is smaller than or equal to the first number of CPUs.
The UE of claim 5, wherein a total number of CPUs occupied by one or more CSI reports associated with a second functionality is smaller than or equal to a number of CPUs supported by the UE for processing a set of CSI reports associated with a set of second functionalities, or

wherein a total number of CPUs occupied by the one or more CSI reports associated with the second functionality and the one or more CSI reports associated with the first functionality is smaller than or equal to the number of CPUs supported by the UE for processing the set of CSI reports associated with the set of second functionalities.
The UE of claim 1, wherein the at least one CSI report simultaneously occupies one or more CPUs, and a total number of CPUs in the one or more CPUs is smaller than or equal to the third number of CPUs.
The UE of claim 1, wherein the processor is further configured to:

receive, from the network entity via the transceiver, a configuration indicating a priority of a configuration of each CSI report in the one or more CSI reports; and

in accordance with a determination that multiple CSI reports associated with the first functionality are active in overlapped symbols, drop at least one of the multiple CSI reports based on the priority.
The UE of claim 1, wherein the processor is further configured to:

transmit, to the network entity via the transceiver, second information indicating applicability of the one or more configurations of the one or more CSI reports associated with the first functionality.
The UE of claim 9, wherein the second information comprises at least one of the following:

information of multiple configurations of CSI reports that can be activated simultaneously; or

information of multiple configurations of CSI reports corresponding to sets of inference parameters that can be activated simultaneously.
The UE of claim 1, wherein the at least one CSI report is carried by a scheduled uplink transmission, and

wherein a time interval between a latest one reference signal transmission occasion for channel measurement and the scheduled uplink transmission carrying the at least one CSI report is greater than a first time interval, and the first time interval is determined based on the second time.
The UE of claim 1, wherein the at least one CSI report is carried by a scheduled uplink transmission, and

wherein a time interval between a downlink transmission triggering the at least one CSI report and the scheduled uplink transmission carrying the at least one report is greater than a second time interval, and the second time interval is determined based on the second time or based on the first time and the second time.
The UE of claim 1, wherein the at least one CSI report is periodic or semi-persistent, and

wherein one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal of a latest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.
The UE of claim 1, wherein the at least one CSI report is periodic or semi-persistent,

wherein one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal to a first number of symbols after a last symbol of a last one reference signal for a reference signal transmission occasion for channel measurement, and the reference signal transmission occasion is a transmission occasion other than a latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report, and

wherein the one or more CPUs are occupied from a first symbol of an earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.
The UE of claim 1, wherein the at least one CSI report is aperiodic, and

wherein one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal of a latest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report, no later than a CSI reference resource, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.
The UE of claim 1, wherein the at least one CSI report is aperiodic,

wherein one or more CPUs are occupied for the at least one CSI report from a first symbol of an earliest one reference signal to a second number of symbols after a last symbol of a last one reference signal for a reference signal transmission occasion for channel measurement, and the reference signal transmission occasion is a transmission occasion other than a latest one reference signal transmission occasion, no later than a CSI reference resource, of a resource set corresponding to the at least one CSI report, and

wherein the one or more CPUs are occupied from a first symbol of an earliest one reference signal of the latest one reference signal transmission occasion, no later than the CSI reference resource, of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.
The UE of claim 1, wherein the at least one CSI report is aperiodic, and wherein one or more CPUs are occupied for the at least one CSI report during at least one of the following:

a time window starting from a first symbol of downlink control information (DCI) triggering the one or more CSI reports until a later one of a third number of symbols after a last symbol of the DCI, and a fourth number of symbols after a last symbol of an earliest one reference signal transmission occasion of a resource set corresponding to the at least one CSI report;

one or more time windows starting from a first symbol of a reference signal transmission occasion, until a fifth number of symbols after a last symbol of the reference signal transmission occasion, wherein the reference signal transmission occasion is a transmission occasion other than the earliest one reference signal transmission occasion and a latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report; or

a time window starting from a first symbol of the latest one reference signal transmission occasion of the resource set corresponding to the at least one CSI report, until a last symbol of a scheduled uplink transmission carrying the at least one CSI report.
A network entity, comprising:

a processor; and

a transceiver coupled to the processor,

wherein the processor is configured to:

transmit, to a user equipment (UE) via the transceiver, one or more configurations of one or more channel status information (CSI) reports for a first functionality; and

receive, from the network entity via the transceiver, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following:

a first number of CSI processing units (CPUs) supported by the UE for processing a set of CSI reports associated with a set of first functionalities,

a second number of CPUs occupied by each CSI report in one or more CSI reports associated with a first functionality,

first time associated with model activation for the first functionality,

second time associated with model inference for the first functionality, or

a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.
A processor for wireless communication, comprising:

at least one memory; and

a controller coupled with the at least one memory and configured to cause the processor to:

receive, at a user equipment (UE) from a network entity, one or more configurations of one or more channel status information (CSI) reports for a first functionality; and

transmit, to the network entity, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following:

a first number of CSI processing units (CPUs) supported by the UE for processing a set of CSI reports associated with a set of first functionalities,

a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality,

first time associated with model activation for the first functionality,

second time associated with model inference for the first functionality, or

a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.
A method for wireless communication, comprising:

receiving, at a user equipment (UE) from a network entity, one or more configurations of one or more channel status information (CSI) reports for a first functionality; and

transmitting, to the network entity, at least one CSI report in the one or more CSI reports based on first information indicating at least one of the following:

a first number of CSI processing units (CPUs) supported by the UE for processing a set of CSI reports associated with a set of first functionalities,

a second number of CPUs occupied by each CSI report in one or more CSI reports associated with the first functionality,

first time associated with model activation for the first functionality,

second time associated with model inference for the first functionality, or

a third number of CPUs supported by the UE for processing one or more CSI reports associated with the first functionality.