Control information capability signaling, reporting configuration and payload determination based on machine learning

Abstract

Systems, apparatus, processes, and computer-readable media for wireless communications using machine learning (ML) models are disclosed. A method of wireless communication includes determining at least one set of capability information associated with at least one feature group, at least one identifier associated with one or more machine learning (ML) models, and channel state information reference signal (CSI-RS) capabilities of a UE; sending the capability information to the network entity; and receiving a CSI report configuration including an identifier of the at least one identifier.

Description

Technical Field

[0001] This disclosure relates in general to artificial intelligence (AI) / machine learning (ML) based systems for wireless communications. For example, aspects of this disclosure relate to systems and techniques for providing AI / ML-based control information capabilities, signaling, reporting configuration, and payload determination. Background Technology

[0002] Wireless communication systems are deployed to provide a variety of telecommunications and data services, including telephone, video, data, messaging, and broadcasting. Broadband wireless communication systems have evolved through several generations, including first-generation analog wireless telephone service (1G), second-generation (2G) digital wireless telephone service (including the transitional 2.5G networks), third-generation (3G) high-speed data wireless devices with internet capabilities, and fourth-generation (4G) services (e.g., LTE, WiMax). Examples of wireless communication systems include Code Division Multiple Access (CDMA) systems, Time Division Multiple Access (TDMA) systems, Frequency Division Multiple Access (FDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, and the Global System for Mobile Communications (GSM) system. Other wireless communication technologies include 802.11 Wi-Fi, Bluetooth, etc.

[0003] Fifth-generation (5G) mobile standards demand higher data transfer speeds, a greater number of connections, better coverage, and other improvements. According to the Next Generation Mobile Networks Alliance (NGC), the 5G standard (also known as “New Radio” or “NR”) is designed to provide tens of megabits per second of data rate to each of tens of thousands of users, and 1 gigabits per second to dozens of employees on an office floor. To support large-scale sensor deployments, it should support hundreds of thousands of simultaneous connections. Artificial intelligence (AI) and machine learning (ML) algorithms can be incorporated into 5G, 6G, and future standards to improve telecommunications and data services. Summary of the Invention

[0004] The following is a simplified summary of the invention relating to one or more aspects disclosed herein. Therefore, this summary should not be considered an exhaustive overview relating to all conceived aspects, nor should it be considered to identify key or decisive elements relating to all conceived aspects or to depict the scope associated with any particular aspect. Accordingly, the following summary presents certain concepts in a simplified form relating to one or more aspects of the mechanisms disclosed herein, preceding the detailed description presented below.

[0005] Artificial intelligence / machine learning (AI / ML) based models can be used for various purposes, such as generating channel state information (CSI) feedback. For example, CSI ML encoders and / or CSI ML decoders can replace the pre-decoded matrix indicator (PMI) used in wireless communication systems. A CSI ML encoder is similar to a PMI search algorithm in current systems, and a CSI ML decoder is similar to a PMI codebook. For example, a CSI ML decoder can be used to convert CSI report bits from a CSI ML encoder into PMI codewords. However, there is no well-defined technique for providing AI / ML-based control information capabilities for signaling, report configuration, and / or payload determination (e.g., the payload of a message output by the UE's AI / ML model).

[0006] This document describes systems and techniques for providing machine learning-based control information capability signaling, report configuration, and payload determination. For example, a UE's ML-based encoder may be configured to pair with an ML-based decoder at a network entity (e.g., a base station, such as a gNB, or a portion of a base station, such as a central unit (CU), distributed unit (DU), radio unit (RU), near real-time (near RT) radio access network (RAN) intelligent controller (RIC), or non-real-time (non-RT) RIC), which may also be referred to as the network entity. Information can be exchanged between the UE and the network entity to establish CSI reports. In some cases, the UE may determine capability information associated with at least one set of features, at least one identifier associated with one or more ML models, and at least one set of the UE's CSI-RS capabilities. The UE may send the capability information to the network entity. In one aspect, at least one identifier may identify a pair of ML-based models, such as an ML-based encoder for encoding CSI and a corresponding ML-based decoder for decoding CSI. In some respects, the UE may receive explicit signaling from a network entity that indicates the payload size, or the payload size may be determined based on one or more parameters of the UE’s ML-based encoder output (e.g., compressed or latent representation of CSI feedback).

[0007] According to at least one example, a method for wireless communication at a user equipment (UE) includes: determining capability information associated with at least one set of features, at least one identifier associated with one or more machine learning (ML) models, and at least one set of the UE's channel state information reference signal (CSI-RS) capabilities; transmitting the capability information to a network entity; and receiving a CSI report configuration that includes the identifier from the at least one identifier.

[0008] In another exemplary example, an apparatus for wireless communication is provided, the apparatus including at least one memory and at least one processor (e.g., implemented in a circuit), the at least one processor being coupled to the at least one memory and configured to: determine capability information associated with at least one set of features, at least one identifier associated with one or more ML models, and at least one set of CSI-RS capabilities of the apparatus; transmit the capability information to a network entity; and receive a CSI report configuration including the identifier from the at least one identifier.

[0009] In another exemplary example, a non-transitory computer-readable storage medium for a user equipment (UE) is provided, the non-transitory computer-readable storage medium including instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to: determine capability information associated with at least one feature group, at least one identifier associated with one or more ML models, and at least one set of CSI-RS capabilities of the UE; send the capability information to a network entity; and receive a CSI report configuration including the identifier among the at least one identifier.

[0010] In another exemplary example, an apparatus for wireless communication is provided, the apparatus comprising: components for determining capability information associated with at least one set of features, at least one identifier associated with one or more machine learning (ML) models, and at least one set of channel state information reference signal (CSI-RS) capabilities of the apparatus; transmitting the capability information to a network entity; and components for receiving a CSI report configuration including the identifier among the at least one identifier.

[0011] In another exemplary example, a method for wireless communication at a network entity includes: receiving capability information associated with at least one set of features, at least one identifier associated with one or more ML models, and at least one set of CSI-RS capabilities of a user equipment (UE); and sending a CSI report configuration to the UE including the identifier from the at least one identifier.

[0012] In another example, an apparatus for wireless communication is provided, the apparatus including at least one memory and at least one processor (e.g., implemented in a circuit), the at least one processor being coupled to the at least one memory and configured to: receive capability information associated with at least one feature group, at least one identifier associated with one or more ML models, and at least one set of CSI-RS capabilities of a user equipment (UE); and send a CSI report configuration to the UE including the identifier from the at least one identifier.

[0013] In another exemplary example, a non-transitory computer-readable storage medium is provided, the non-transitory computer-readable storage medium including instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to: receive capability information associated with at least one feature group, at least one identifier associated with one or more ML models, and at least one set of CSI-RS capabilities of a user equipment (UE); and send a CSI report configuration to the UE including the identifier among the at least one identifier.

[0014] In another exemplary example, an apparatus for wireless communication is provided, the apparatus comprising: components for receiving capability information associated with at least one feature group, at least one identifier associated with one or more ML models, and at least one set of CSI-RS capabilities of a user equipment (UE); and components for transmitting a CSI report configuration including the identifier among the at least one identifier to the UE.

[0015] The aspects generally include methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, wireless communication devices and / or processing systems, as fully described herein with reference to the accompanying drawings and description, and as illustrated in the accompanying drawings and description.

[0016] The features and technical advantages of the examples according to this disclosure have been summarized rather extensively above in order to provide a better understanding of the detailed description that follows. Additional features and advantages will be described below. The disclosed concepts and specific examples can be readily used as the basis for modifying or designing other structures for achieving the same purpose as this disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, in both their organization and manner of operation, and the associated advantages, will be better understood by considering the following description in conjunction with the accompanying drawings. Each of the drawings provided is for illustrative and descriptive purposes and not as a definition of limitation of the claims.

[0017] While aspects are described herein by way of example, those skilled in the art will understand that such aspects can be implemented in many different arrangements and scenarios. The techniques described herein can be implemented using different platform types, devices, systems, shapes, sizes, and / or package arrangements. For example, some aspects can be implemented via integrated chip implementations or other devices based on non-modular components (e.g., end-user equipment, vehicles, communication equipment, computing devices, industrial equipment, retail / shopping devices, medical devices, and / or artificial intelligence devices). Aspects can be implemented in chip-level components, modular components, non-modular components, non-chip-level components, device-level components, and / or system-level components. Devices incorporating the described aspects and features may include additional components and features for implementing and practicing the claimed and described aspects. For example, the transmission and reception of wireless signals may include one or more components for analog and digital purposes (e.g., hardware components including antennas, radio frequency (RF) chains, power amplifiers, modulators, buffers, processors, interleavers, adders, and / or summers). The aspects described herein are intended to be practiced in a wide variety of devices, components, systems, distributed arrangements, and / or end-user equipment of various sizes, shapes, and configurations.

[0018] Based on the accompanying drawings and detailed description, other objects and advantages associated with the aspects disclosed herein will be apparent to those skilled in the art. Attached Figure Description

[0019] Examples of specific implementations are described in detail below with reference to the accompanying figures:

[0020] Figure 1 This is a block diagram illustrating an example of a wireless communication network based on some examples;

[0021] Figure 2 These are illustrations of base station and user equipment (UE) designs based on some examples, which enable the transmission and processing of signals exchanged between the UE and the base station;

[0022] Figure 3 This is a diagram illustrating an example of a decomposed base station based on some examples;

[0023] Figure 4 This is a block diagram illustrating the components of a user device based on some examples;

[0024] Figure 5 Examples of neural network architectures that can be used according to some aspects of this disclosure are shown;

[0025] Figure 6 This is a block diagram illustrating various aspects of an ML engine according to this disclosure;

[0026] Figure 7 The illustration, according to various aspects of this disclosure, shows a block diagram of an encoder encoding an input to generate a potential message that is sent to a decoder at a 3GPP gNodeB (gNB), based on which the decoder generates an output;

[0027] Figure 8 Example decoder inputs and example decoder outputs according to various aspects of this disclosure are illustrated;

[0028] Figure 9 The configuration of CSI capability is illustrated;

[0029] Figure 10 This is a conceptual diagram illustrating the ability to transmit ML-based capabilities according to various aspects of this disclosure;

[0030] Figure 11 Examples illustrate potential changes to ML-based CSI feedback or CSF by determining what capabilities the UE should report for ML-based CSI feedback;

[0031] Figure 12 This is a conceptual illustration of the ability information that a UE can report to a network entity, based on some aspects of this disclosure;

[0032] Figure 13 A conceptual diagram illustrating reporting capability information based on some aspects of this disclosure is shown;

[0033] Figure 14 This is a flowchart of an example method 1400 for providing wireless communication at a UE, according to various aspects of this disclosure;

[0034] Figure 15 This is a flowchart illustrating examples of a process or method 1500 for wireless communication from the perspective of a network entity (such as a base station) according to various aspects of this disclosure; and

[0035] Figure 16 This is a diagram illustrating an example of a system used to implement certain aspects of this technology. Detailed Implementation

[0036] Certain aspects and embodiments of this disclosure are provided below. Some of these aspects and embodiments may be applied independently, and some may be combined, as will be apparent to those skilled in the art. Specific details are set forth in the following description for purposes of explanation in order to provide a thorough understanding of the various embodiments of this application. However, it will be apparent, however, that the various embodiments may be practiced without these specific details. The accompanying drawings and descriptions are not intended to be limiting.

[0037] The following description provides only exemplary embodiments and is not intended to limit the scope, applicability, or configuration of this disclosure. Rather, the subsequent description of exemplary embodiments will provide those skilled in the art with enabling descriptions for implementing the exemplary embodiments. It should be understood that various changes may be made to the function and arrangement of the elements without departing from the spirit and scope of this application as set forth in the appended claims.

[0038] Various technologies are provided to enhance wireless communication, referencing wireless technologies such as the 3GPP 5G / New Radio (NR) standard. Wireless networks are deployed to provide a variety of communication services, such as voice, video, packet data, message sending and receiving, broadcasting, etc. Wireless networks can support two types of access links for communication between wireless devices. An access link can refer to any communication link between components of a client device (e.g., a User Equipment (UE), Station (STA), or other client device) and a base station (e.g., a 3GPP gNodeB (gNB) for 5G / NR, a 3GPP eNodeB (eNB) for LTE, a Wi-Fi access point (AP), or other base station) or a distributed base station (e.g., a central unit, distributed units, and / or radio units). In one example, the access link between a UE and a 3GPP gNB can be via the Uu interface. In some cases, the access link can support uplink signaling, downlink signaling, connection procedures, etc.

[0039] Channel State Information (CSI) feedback can be used by network entities in a wireless communication system (e.g., base stations such as 3GPP gNodeB (NB)) to determine channel conditions in order to schedule downlink data transmissions. For example, a User Equipment (UE) can receive a CSI Reference Signal (CSI-RS) from a base station (e.g., gNB) and perform channel estimation based on that CSI-RS. According to current 3GPP standards, CSI reporting configuration includes a codebook used as a Pre-decoded Matrix Indicator (PMI) dictionary, based on which the UE can report the optimal PMI codeword based on channel and / or interference measurements from the received CSI-RS and / or one or more CSI-Interference Measurement (IM) resources. The UE can use bit sequences to report the PMI. For example, CSI IM resources may include a set of specific resource elements reserved for interference measurements. In some cases, CSI IM resources can be configured by an RRC message sent by the base station (e.g., gNB) and received by the UE.

[0040] A question arises regarding what to provide as feedback, relative to X-node Channel State Feedback (CSF) or Channel State Information (CSI). CSI feedback can be used by network entities in a wireless communication system (e.g., base stations such as 3GPP gNodeB(NB)) to determine channel conditions. For example, a User Equipment (UE) can receive a CSI Reference Signal (CSI-RS) from a network entity (e.g., a base station such as a gNodeB(gNB)) and perform channel estimation based on that CSI-RS. According to current 3GPP standards, the CSI reporting configuration includes a codebook used as a Pre-decoded Matrix Indicator (PMI) dictionary, based on which the UE can report the optimal PMI codeword based on the received CSI-RS. The UE can use bit sequences to report the PMI.

[0041] In some cases, AI / ML-based CSI feedback can use a CSI ML encoder and / or CSI ML decoder instead of PMI. For example, a UE intending to deliver CSI to a gNB can use a CSI ML encoder (e.g., an encoder neural network model) to derive a compressed representation of the CSI (also known as a latent representation or latent message) for transmission to the gNB. The gNB can use a CSI ML decoder (e.g., a decoder neural network model) to reconstruct the target CSI from the compressed representation. The CSIML encoder is similar to the PMI search algorithm in current systems. The CSI ML decoder is similar to the PMI codebook and is used to convert CSI report bits into PMI codewords. However, there is no explicit technique for providing AI / ML-based control information capability signaling, reporting configuration, and / or payload determination (e.g., the payload relative to the message output by the UE's AI / ML model).

[0042] This document describes systems, apparatuses, processes (also referred to as methods), and computer-readable media (collectively referred to herein as systems and technologies) for providing machine learning-based control information capability signaling, report configuration, and payload determination. In some cases, an ML-based encoder at the UE is configured to pair with an ML-based decoder at a network entity (e.g., a base station, such as a gNB, or a portion of a base station, such as a central unit (CU), distributed unit (DU), radio unit (RU), near real-time (near RT) radio access network (RAN) intelligent controller (RIC), or non-real-time (non-RT) RIC), which may also be referred to as the network entity. For example, information may be transmitted between the UE and the network entity to establish a CSI report. In one exemplary aspect, the UE may determine capability information associated with at least one set of features, at least one identifier associated with one or more ML models, and at least one set of the UE's CSI-RS capabilities. The UE may transmit the capability information to the network entity. In one aspect, at least one identifier may identify a pair of ML-based models, such as an ML-based encoder for encoding CSI and a corresponding ML-based decoder for decoding CSI. In some respects, the UE may receive explicit signaling from a network entity that indicates the payload size, or the payload size may be determined based on one or more parameters of the UE’s ML-based encoder output (e.g., compressed or latent representation of CSI feedback).

[0043] Additional aspects of this disclosure are described in more detail below with reference to the accompanying drawings. Illustrative aspects are also provided in Appendix A, which is provided herein.

[0044] As used herein, the terms “User Equipment” (UE) and “Network Entity” are not intended to be specific to or otherwise limited to any particular Radio Access Technology (RAT) unless otherwise specified. In general, a UE can be any wireless communication device (e.g., mobile phone, router, tablet computer, laptop computer, and / or tracking device, etc.), wearable device (e.g., smartwatch, smart glasses, wearable ring, and / or extended reality (XR) device (such as virtual reality (VR) headsets, augmented reality (AR) headsets or glasses, or mixed reality (MR) headsets)), vehicle (e.g., car, motorcycle, bicycle, etc.), and / or Internet of Things (IoT) device, etc., for use by a user to communicate over a wireless communication network. A UE can be mobile or can (e.g., at certain times) be stationary and can communicate with a Radio Access Network (RAN). As used herein, the term "UE" may be interchangeably referred to as "access terminal" or "AT," "client device," "wireless device," "subscriber device," "subscriber terminal," "subscriber station," "user terminal," or "UT," "mobile device," "mobile terminal," "mobile station," or variations thereof. Generally, a UE can communicate with the core network via the RAN, and through the core network, the UE can connect to external networks such as the Internet and other UEs. Of course, other mechanisms for connecting to the core network and / or the Internet are also possible for the UE, such as through wired access networks, wireless local area network (WLAN) networks (e.g., based on the IEEE 802.11 communication standard), etc.

[0045] Network entities can be implemented in a converged or monolithic base station architecture, or alternatively, in a decomposed base station architecture, and may include one or more of a central unit (CU), a distributed unit (DU), a radio unit (RU), a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. A base station (e.g., having a converged / monolithic or decomposed base station architecture) may operate according to one of several RATs communicating with the UE (depending on the network in which it is deployed), and may alternatively be referred to as an access point (AP), network node, NodeB (NB), evolved NodeB (eNB), next-generation eNB (ng-eNB), new radio (NR) NodeB (also referred to as gNB or gNodeB), etc. The base station may primarily be used to support the UE's radio access, including supporting data, voice, and / or signaling connections for the supported UE. In some systems, the base station may provide edge node signaling functions, while in other systems, the base station may provide additional control and / or network management functions. The communication link through which a UE transmits signals to a base station is called an uplink (UL) channel (e.g., reverse traffic channel, reverse control channel, access channel, etc.). The communication link through which a base station transmits signals to a UE is called a downlink (DL) or forward link channel (e.g., paging channel, control channel, broadcast channel, or forward traffic channel, etc.). As used herein, the term traffic channel (TCH) can refer to uplink, reverse or downlink, and / or forward traffic channel.

[0046] The terms "network entity" or "base station" (e.g., having a converged / monolithic or decomposed base station architecture) can refer to a single physical transmit / receive point (TRP) or multiple physical TRPs that may be co-located or non-co-located. For example, when the term "network entity" or "base station" refers to a single physical TRP, the physical TRP may be a base station antenna corresponding to a cell (or several cell sectors) of the base station. When the term "network entity" or "base station" refers to multiple co-located physical TRPs, these physical TRPs may be antenna arrays of the base station (e.g., as in a multiple-input multiple-output (MIMO) system or where the base station employs beamforming). When the term "base station" refers to multiple non-co-located physical TRPs, the physical TRPs may be a distributed antenna system (DAS) (a network of spatially separated antennas connected via a transmission medium to a common source) or a remote radio headend (RRH) (a remote base station connected to a serving base station). Alternatively, a non-co-located physical TRP may be a serving base station receiving measurement reports from a UE and a neighboring base station where the UE is measuring its reference radio frequency (RF) signal (or simply "reference signal"). As used in this article, a TRP is the point by which a base station transmits and receives wireless signals, so any mention of transmitting from or receiving at a base station should be understood as referring to a specific TRP of the base station.

[0047] In some specific implementations supporting UE positioning, network entities or base stations may not support the UE's radio access (e.g., may not support data, voice, and / or signaling connections regarding the UE), but may instead transmit reference signals to the UE for measurement, and / or receive and measure signals transmitted by the UE. Such a base station may be referred to as a positioning beacon (e.g., in the case of transmitting signals to the UE) and / or as a location measurement unit (e.g., in the case of receiving and measuring signals from the UE).

[0048] RF signals comprise electromagnetic waves of a given frequency that transmit information across the space between a transmitter and a receiver. As used herein, a transmitter may send a single “RF signal” or multiple “RF signals” to a receiver. However, due to the propagation characteristics of RF signals through multipath channels, a receiver may receive multiple “RF signals” corresponding to each transmitted RF signal. The same transmitted RF signal on different paths between the transmitter and receiver can be referred to as a “multipath” RF signal. As used herein, where the context clearly indicates that the term “signal” refers to a wireless signal or RF signal, an RF signal may also be referred to as a “wireless signal” or simply a “signal.”

[0049] Various aspects of the systems and technologies described herein will be discussed below with reference to the accompanying drawings. According to these aspects, Figure 1An example of a wireless communication system 100 is illustrated. The wireless communication system 100 (which may also be referred to as a wireless wide area network (WWAN)) may include various base stations 102 and various UEs 104. In some aspects, base station 102 may also be referred to as a “network entity” or a “network node.” One or more base stations in base station 102 may be implemented in an aggregated or monolithic base station architecture. Additionally or alternatively, one or more base stations in base station 102 may be implemented in a decomposed base station architecture and may include one or more of a central unit (CU), a distributed unit (DU), a radio unit (RU), a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. Base station 102 may include macro cell base stations (high-power cellular base stations) and / or small cell base stations (low-power cellular base stations). In one aspect, macro cell base stations may include eNBs and / or ng-eNBs (where wireless communication system 100 corresponds to a Long Term Evolution (LTE) network), or gNBs (where wireless communication system 100 corresponds to an NR network), or a combination of both, and small cell base stations may include femtocells, picocells, microcells, etc.

[0050] Base station 102 can collectively form a RAN and interface with core network 170 (e.g., evolved packet core (EPC) or 5G core (5GC)) via backhaul link 122, and interface with one or more location servers 172 (which may be part of core network 170 or external to core network 170) via core network 170. Among other functions, base station 102 can perform functions related to one or more of the following: delivering user data, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection establishment and release, load balancing, distribution of non-access stratum (NAS) messages, NAS node selection, synchronization, RAN sharing, multimedia broadcast multicast service (MBMS), subscriber and equipment tracking, RAN information management (RIM), paging, location, and delivery of warning messages. Base station 102 can communicate with each other directly or indirectly (e.g., via EPC or 5GC) via backhaul link 134 (which may be wired and / or wireless).

[0051] Base station 102 can wirelessly communicate with UE 104. Each base station in base station 102 can provide communication coverage for a corresponding geographical coverage area 110. In one aspect, base station 102 in each coverage area 110 can support one or more cells. A “cell” is a logical communication entity used to communicate with a base station (e.g., on a frequency resource, referred to as a carrier frequency, component carrier, carrier, frequency band, etc.) and can be associated with an identifier (e.g., Physical Cell Identifier (PCI), Virtual Cell Identifier (VCI), Cell Global Identifier (CGI)) to distinguish cells operating via the same or different carrier frequencies. In some cases, different cells can be configured according to different protocol types that can provide access for different types of UEs (e.g., Machine Type Communication (MTC), Narrowband IoT (NB-IoT), Enhanced Mobile Broadband (eMBB), or other protocol types). Because a cell is supported by a specific base station, the term “cell” can refer to either or both of the logical communication entity and the base station supporting the logical communication entity, depending on the context. Furthermore, since the TRP is typically the physical transmission point of the cell, the terms “cell” and “TRP” can be used interchangeably. In some cases, the term "cell" may also refer to the geographic coverage area (e.g., sector) of a base station, provided that a carrier frequency can be detected within a portion of the geographic coverage area 110 and that carrier frequency is used for communication within that portion.

[0052] While the geographic coverage areas 110 of adjacent macro cell base stations 102 may partially overlap (e.g., in handover areas), some areas within geographic coverage areas 110 may substantially overlap with larger geographic coverage areas 110. For example, a small cell base station 102' may have a coverage area 110' that substantially overlaps with the coverage areas 110 of one or more macro cell base stations 102. A network that includes both small cell base stations and macro cell base stations can be referred to as a heterogeneous network. A heterogeneous network may also include home eNBs (HeNBs) that can provide service to restricted groups referred to as closed subscriber groups (CSGs).

[0053] The communication link 120 between base station 102 and UE 104 may include uplink (also referred to as the reverse link) transmission from UE 104 to base station 102 and / or downlink (also referred to as the forward link) transmission from base station 102 to UE 104. The communication link 120 may use MIMO antenna techniques, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link 120 may use one or more carrier frequencies. Carrier allocation may be asymmetric for the downlink and uplink (e.g., more or fewer carriers may be allocated to the downlink compared to the uplink).

[0054] The wireless communication system 100 may further include a WLAN AP 150 communicating with a WLAN station (STA) 152 via a communication link 154 in unlicensed spectrum (e.g., 5 GHz). When communicating in unlicensed spectrum, the WLAN STA 152 and / or WLAN AP 150 may perform a Free Channel Assessment (CCA) or Listen-After-Talk (LBT) process before communication to determine if the channel is available. In some examples, the wireless communication system 100 may include devices (e.g., UEs, etc.) that communicate with one or more UEs 104, base stations 102, APs 150, etc., using ultra-wideband (UWB) spectrum. The UWB spectrum may range from 3.1 GHz to 10.5 GHz.

[0055] Small cell base station 102' can operate in licensed and / or unlicensed spectrum. When operating in unlicensed spectrum, small cell base station 102' can employ LTE or NR technology and use the same 5 GHz unlicensed spectrum as WLAN AP 150. Small cell base station 102' employing LTE and / or 5G in unlicensed spectrum can enhance coverage of the access network and / or increase the capacity of the access network. NR in unlicensed spectrum can be referred to as NR-U. LTE in unlicensed spectrum can be referred to as LTE-U, Licensed Assisted Access (LAA), or MulteFire.

[0056] The wireless communication system 100 may also include a millimeter-wave (mmW) base station 180, which can operate at mmW and / or near-mmW frequencies to communicate with the UE 182. The mmW base station 180 may be implemented in a converged or monolithic base station architecture, or alternatively, in a decomposed base station architecture (e.g., including one or more of a CU, DU, RU, near-RT RIC, or non-RT RIC). Extremely high frequency (EHF) is a portion of the electromagnetic spectrum that contains radio frequency (RF). EHF has a range of 30 GHz to 300 GHz, with wavelengths between 1 mm and 10 mm. Radio waves in this band may be referred to as millimeter waves. Near-mmW extends down to frequencies of 3 GHz with wavelengths of 100 mm. Ultra-high frequency (SHF) bands extend between 3 GHz and 30 GHz, and are also referred to as centimeter waves. Communication using mmW and / or near-mmW radio bands has high path loss and relatively short range. mmW base station 180 and UE 182 can utilize beamforming (transmit and / or receive) on mmW communication link 184 to compensate for extremely high path loss and short range. Furthermore, it should be understood that in alternative configurations, one or more base stations 102 may also use mmW or near-mmW and beamforming for transmission. Therefore, it should be understood that the foregoing illustrations are merely examples and should not be construed as limiting the various aspects disclosed herein.

[0057] In some aspects related to 5G, the spectrum operated by wireless network nodes or entities (e.g., base station 102 / 180, UE 104 / 182) is divided into multiple frequency ranges: FR1 (from 450 MHz to 6000 MHz), FR2 (from 24250 MHz to 52600 MHz), FR3 (above 52600 MHz), and FR4 (between FR1 and FR2). In multi-carrier systems such as 5G, one of the carrier frequencies is referred to as the "primary carrier," "anchor carrier," "primary serving cell," or "PCell," and the remaining carrier frequencies are referred to as "secondary carriers," "secondary serving cells," or "SCell." In carrier aggregation, the anchor carrier is the carrier operating on the primary frequency (e.g., FR1) used by UE 104 / 182 and the cell, where UE 104 / 182 performs an initial radio resource control (RRC) connection establishment procedure or initiates an RRC connection re-establishment procedure in that cell. The primary carrier carries all common control channels as well as UE-specific control channels and can be a carrier on a licensed frequency (however, this is not always the case). The secondary carrier is a carrier operating on a second frequency (e.g., FR2) that can be configured and used to provide additional radio resources once an RRC connection is established between UE 104 and the anchor carrier. In some cases, the secondary carrier can be a carrier on an unlicensed frequency. The secondary carrier may contain only the necessary signaling information and signals; for example, since the primary uplink and primary downlink carriers are typically UE-specific, those UE-specific signaling information and signals may not be present on the secondary carrier. This means that different UEs 104 / 182 in a cell can have different downlink primary carriers. The same applies to the uplink primary carrier. The network can change the primary carrier of any UE 104 / 182 at any time. This is done, for example, to balance the load on different carriers. Because a “serving cell” (whether PCell or SCell) corresponds to the carrier frequency and / or component carrier through which some base stations are communicating, the terms “cell,” “serving cell,” “component carrier,” “carrier frequency,” etc., can be used interchangeably.

[0058] For example, still refer to Figure 1One of the frequencies used by macro cell base station 102 may be an anchor carrier (or "PCell"), and the other frequencies used by macro cell base station 102 and / or mmW base station 180 may be secondary carriers ("SCell"). In carrier aggregation, each carrier of base station 102 and / or UE 104 may use a spectrum with a bandwidth of up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz), with up to a total of Yx MHz (x component carriers) for transmission in each direction. Component carriers may or may not be adjacent to each other in the spectrum. Carrier allocation may be asymmetric with respect to downlink and uplink (e.g., more or fewer carriers may be allocated to downlink compared to uplink). Simultaneous transmission and / or reception on multiple carriers enables UE 104 / 182 to significantly increase its data transmission and / or reception rates. For example, two aggregated 20 MHz carriers in a multi-carrier system would theoretically result in a doubling of the data rate (i.e., 40 MHz) compared to the data rate obtained by a single 20 MHz carrier.

[0059] To operate on multiple carrier frequencies, base station 102 and / or UE 104 may be equipped with multiple receivers and / or transmitters. For example, UE 104 may have two receivers, namely "Receiver 1" and "Receiver 2", where "Receiver 1" is a multi-band receiver that can be tuned to band (i.e., carrier frequency) 'X' or band 'Y', and "Receiver 2" is a single-band receiver that can be tuned to only band 'Z'. In this example, if UE 104 is being served in band 'X', then band 'X' will be referred to as PCell or active carrier frequency, and "Receiver 1" will need to tune from band 'X' to band 'Y' (SCell) to measure band 'Y' (and vice versa). In contrast, regardless of whether UE 104 is being served in band 'X' or band 'Y', due to the separate "Receiver 2", UE 104 can measure band 'Z' without interrupting service on band 'X' or band 'Y'.

[0060] The wireless communication system 100 may further include a UE 164, which can communicate with the macro cell base station 102 on the communication link 120 and / or with the mmW base station 180 on the mmW communication link 184. For example, the macro cell base station 102 may support PCells and one or more SCells for the UE 164, and the mmW base station 180 may support one or more SCells for the UE 164.

[0061] The wireless communication system 100 may also include one or more UEs, such as UE 190, which are indirectly connected to one or more communication networks via one or more device-to-device (D2D) peer-to-peer (P2P) links (referred to as "side links"). Figure 1 In the example, UE 190 has a D2D P2P link 192 with one of UEs 104 connected to one of the base stations in base station 102 (e.g., UE 190 can indirectly obtain cellular connectivity through this D2D P2P link), and has a D2D P2P link 194 with a WLAN STA 152 connected to WLAN AP 150 (UE 190 can indirectly obtain WLAN-based internet connectivity through this D2D P2P link). In one example, D2D P2P links 192 and 194 can use any known D2D RAT (such as LTE Direct (LTE-D), Wi-Fi Direct (Wi-Fi-D)). (etc.) to support.

[0062] Figure 2 A block diagram of a base station 102 and a UE 104 designed according to some aspects of this disclosure is shown, which enables the transmission and processing of signals exchanged between the UE and the base station. Design 200 includes components of base station 102 and UE 104, which may be... Figure 1 The base station 102 is a base station and the UE 104 is a UE. The base station 102 may be equipped with T antennas 234a to 234t, and the UE 104 may be equipped with R antennas 252a to 252r, wherein typically T≥1 and R≥1.

[0063] At base station 102, transmitting processor 220 can receive data for one or more UEs from data source 212, select one or more modulation and decoding schemes (MCS) for each UE based at least in part on the Channel Quality Indicator (CQI) received from each UE, process (e.g., encode and modulate) the data for each UE based at least in part on the MCS selected for each UE, and provide data symbols for all UEs. Transmitting processor 220 can also process system information (e.g., semi-static resource allocation information (SRPI), etc.) and control information (e.g., CQI requests, grants, upper-layer signaling, channel state information, channel state feedback, etc.), and provide overhead symbols and control symbols. Transmitting processor 220 can also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS)) and synchronization signals (e.g., primary synchronization signal (PSS) and secondary synchronization signal (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 can perform spatial processing (e.g., pre-decoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols, where applicable, and can provide T output symbol streams to T modulators (MODs) 232a to 232t. Modulators 232a to 232t are shown as combined modulator-demodulator (MOD-DEMOD). In some cases, the modulator and demodulator can be separate components. Each modulator in modulators 232a to 232t can process a corresponding output symbol stream (e.g., for an orthogonal frequency division multiplexing (OFDM) scheme, etc.) to obtain an output sample stream. Each modulator in modulators 232a to 232t can further process (e.g., convert to analog, amplify, filter, and up-convert) the output sample stream to obtain a downlink signal. The T downlink signals can be transmitted from modulators 232a to 232t via T antennas 234a to 234t, respectively. Based on some aspects described in more detail below, position coding can be used to generate synchronization signals to transmit additional information.

[0064] At UE 104, antennas 252a to 252r can receive downlink signals from base station 102 and / or other base stations, and can provide the received signals to demodulators (DEMODs) 254a to 254r respectively. Demodulators 254a to 254r are shown as combined modulator-demodulators (MOD-DEMODs). In some cases, the modulator and demodulator can be separate components. Each demodulator in demodulators 254a to 254r can adjust (e.g., filter, amplify, down-convert, and digitize) the received signal to obtain an input sample. Each demodulator in demodulators 254a to 254r can further process the input sample (e.g., for OFDM, etc.) to obtain the received symbols. MIMO detector 256 can obtain the received symbols from all R demodulators 254a to 254r, perform MIMO detection on the received symbols (where applicable), and provide the detected symbols. The receiver processor 258 can process (e.g., demodulate and decode) the detected symbols, provide the decoded data for UE 104 to the data sink 260, and provide the decoded control information and system information to the controller / processor 280. The channel processor can determine the Reference Signal Received Power (RSRP), Received Signal Strength Indicator (RSSI), Reference Signal Received Quality (RSRQ), and / or Channel Quality Indicator (CQI), etc.

[0065] On the uplink, at UE 104, the transmitting processor 264 can receive and process data from data source 262 and control information from controller / processor 280 (e.g., reports including RSRP, RSSI, RSRQ, CQI, channel state information, channel state feedback, etc.). The transmitting processor 264 can also (e.g., based at least in part on β values ​​or sets of β values ​​associated with one or more reference signals) generate reference symbols for one or more reference signals. The symbols from the transmitting processor 264 can be pre-decoded by the TX MIMO processor 266 where applicable, further processed by modulators 254a to 254r (e.g., for DFT-s-OFDM, CP-OFDM, etc.), and transmitted to base station 102. At base station 102, uplink signals from UE 104 and other UEs can be received by antennas 234a to 234t, processed by demodulators 232a to 232t, detected by MIMO detector 236 where applicable, and further processed by receiver processor 238 to obtain decoded data and control information transmitted by UE 104. Receiver processor 238 can provide the decoded data to data sink 239 and the decoded control information to controller (processor) 240. Base station 102 may include communication unit 244 and communicates with network controller 231 via communication unit 244. Network controller 231 may include communication unit 294, controller / processor 290, and memory 292.

[0066] In some respects, one or more components of UE 104 may be included in the housing. These include the controller 240 of base station 102, the controller / processor 280 of UE 104, and / or Figure 2 Any other component may perform one or more techniques associated with the implicit determination of UCIβ values ​​for NR.

[0067] Memory 242 and 282 may store data and program code for base station 102 and UE 104, respectively. Scheduler 246 may schedule UE for data transmission on downlink, uplink and / or sidelink.

[0068] In some aspects, the deployment of communication systems such as 5G New Radio (NR) systems can be arranged with various components or parts in multiple ways. In a 5G NR system or network, network nodes, network entities, network mobility elements, radio access network (RAN) nodes, core network nodes, network elements or network equipment (such as base stations (BS)) or one or more units (or components) performing base station functions can be implemented in aggregated or decomposed architectures. For example, BSs (such as Node B (NB), evolved NB (eNB), NR BS, 5G NB, access point (AP), transmit / receive point (TRP), or cell, etc.) can be implemented as aggregated base stations (also known as standalone BS or monolithic BS) or decomposed base stations.

[0069] Aggregated base stations can be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node. Decentralized base stations can be configured to utilize a protocol stack that is physically or logically distributed across two or more units, such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some respects, the CU may be implemented within a RAN node, and one or more DUs may co-located with the CU, or alternatively, may be geographically or virtually distributed across one or more other RAN nodes. DUs may be implemented to communicate with one or more RUs. Each of the CUs, DUs, and RUs may also be implemented as a virtual unit, namely a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0070] Base station type operation or network design can take into account the aggregation characteristics of base station functionality. For example, decomposed base stations can be utilized in Integrated Access Backhaul (IAB) networks, Open Radio Access Networks (O-RAN (such as network configurations initiated by the O-RAN Alliance)), or Virtualized Radio Access Networks (vRAN, also known as Cloud Radio Access Networks (C-RAN)). Decomposition can include distributing functionality across two or more units in various physical locations, as well as virtually distributing the functionality of at least one unit, which enables flexibility in network design. Individual units in a decomposed base station or decomposed RAN architecture can be configured to communicate wirelessly with at least one other unit.

[0071] Figure 3A diagram illustrating an example of a decomposed base station 300 architecture is shown. The decomposed base station 300 architecture may include one or more central units (CUs) 310, which may communicate directly with the core network 320 via a backhaul link, or indirectly with the core network 320 via one or more decomposed base station units (such as a near real-time (near-RT) RAN Intelligent Controller (RIC) 325 via an E2 link, or a non-real-time (non-RT) RIC 315 associated with a Service Management and Orchestration (SMO) framework 305, or both). CUs 310 may communicate with one or more distributed units (DUs) 330 via corresponding midhaul links (such as F1 interfaces). DUs 330 may communicate with one or more radio units (RUs) 340 via corresponding fronthaul links. RUs 340 may communicate with a corresponding UE 104 via one or more radio frequency (RF) access links. In some implementations, UE 104 may be served simultaneously by multiple RUs 340.

[0072] Each of the units (e.g., CU 310, DU 330, RU 340, and near-RT RIC 325, non-RT RIC 315, and SMO frame 305) may include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via a wired or wireless transmission medium. Each of these units, or an associated processor or controller providing instructions to the communication interfaces of these units, may be configured to communicate with one or more other units via a transmission medium. For example, these units may include a wired interface configured to receive signals via a wired transmission medium or to transmit signals to one or more other units. Additionally, these units may include a wireless interface that may include a receiver, transmitter, or transceiver (such as a radio frequency (RF) transceiver) configured to receive signals via a wireless transmission medium or to transmit signals to one or more other units, or both.

[0073] In some aspects, the CU 310 can host one or more higher-level control functions. Such control functions may include Radio Resource Control (RRC), Packet Data Convergence Protocol (PDCP), or Service Data Adaptation Protocol (SDAP), etc. Each control function can be implemented using an interface configured to signal to other control functions hosted by the CU 310. The CU 310 can be configured to handle user plane functionality (i.e., Central Unit-User Plane (CU-UP)), control plane functionality (i.e., Central Unit-Control Plane (CU-CP)), or a combination thereof. In some specific implementations, the CU 310 can be logically divided into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP units can communicate bidirectionally with the CU-CP units via an interface such as an E1 interface. The CU 310 can be implemented to communicate with the DU 330 for network control and signaling purposes, as needed.

[0074] DU 330 may correspond to a logical unit comprising one or more base station functions for controlling the operation of one or more RU 340s. In some aspects, DU 330 may, at least in part, host one or more of the Radio Link Control (RLC) layer, the Media Access Control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) depending on functional splits (such as those defined by the 3rd Generation Partnership Project (3GPP). In some aspects, DU 330 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface configured to communicate signals with other layers (and modules) hosted by DU 330 or with control functions hosted by CU 310.

[0075] Lower-layer functionality can be implemented by one or more RU 340s. In some deployments, an RU340 controlled by a DU 330 may correspond to a logical node that hosts RF processing functions or low-PHY layer functions (such as performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, Physical Random Access Channel (PRACH) extraction and filtering, or both, at least in part based on functional decomposition (such as lower-layer functional decomposition). In such architectures, the RU 340 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some specific implementations, the real-time and non-real-time aspects of control plane and user plane communications with the RU 340 may be controlled by the corresponding DU 330. In some scenarios, this configuration enables the implementation of the DU 330 and CU 310 in cloud-based RAN architectures (such as vRAN architectures).

[0076] SMO framework 305 can be configured to support RAN deployment and provisioning of both non-virtualized and virtualized network elements. For non-virtualized network elements, SMO framework 305 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via operation and maintenance interfaces such as the O1 interface. For virtualized network elements, SMO framework 305 can be configured to interact with a cloud computing platform such as Open Cloud (O-Cloud) 390 to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface such as the O2 interface. Such virtualized network elements may include, but are not limited to, CU 310, DU 330, RU 340, and near-RT RIC 325. In some implementations, SMO framework 305 can communicate with the hardware aspects of the 4G RAN (such as Open eNB (O-eNB) 311) via the O1 interface. Additionally, in some implementations, SMO framework 305 can communicate directly with one or more RU 340s via the O1 interface. SMO framework 305 may also include a non-RT RIC 315 configured to support the functionality of SMO framework 305.

[0077] The non-RT RIC 315 can be configured to include logical functions enabling non-real-time control and optimization of RAN elements and resources, including AI / ML workflows for model training and updates, or policy-based guidance for applications / features in the near-RT RIC 325. The non-RT RIC 315 can be coupled to or communicate with the near-RT RIC 325 (e.g., via an A1 interface). The near-RT RIC 325 can be configured to include logical functions enabling near real-time control and optimization of RAN elements and resources via data acquisition and actions through an interface (e.g., via an E2 interface) that connects one or more CU 310s, one or more DU 330s, or both, and O-eNBs to the near-RT RIC 325.

[0078] In some implementations, to generate AI / ML models to be deployed in the near-RT RIC 325, the non-RT RIC 315 may receive parameters or external enrichment information from an external server. This information can be utilized by the near-RT RIC 325 and can be received from non-network data sources or network functions at the SMO framework 305 or the non-RT RIC 315. In some examples, the non-RT RIC 315 or near-RT RIC 325 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 315 may monitor long-term trends and patterns in performance and use AI / ML models to perform corrective actions via the SMO framework 305 (such as reconfiguration via O1) or by creating RAN management policies (such as A1 policies).

[0079] Figure 4 An example of a computing system 470 with wireless device 407 is illustrated. Wireless device 407 may include client devices such as UEs (e.g., UE 104, UE 152, UE 190) or other types of devices that can be used by an end user (e.g., a station (STA) configured to communicate using a Wi-Fi interface). For example, wireless device 407 may include mobile phones, routers, tablet computers, laptop computers, tracking devices, wearable devices (e.g., smartwatches, glasses, extended reality (XR) devices such as virtual reality (VR), augmented reality (AR), or mixed reality (MR) devices), Internet of Things (IoT) devices, access points, and / or another device configured to communicate via a wireless communication network. Computing system 470 includes software and hardware components that can be electrically coupled or communicatively coupled (or otherwise communicated, as applicable) via bus 489. For example, computing system 470 includes one or more processors 484. One or more processors 484 may include one or more CPUs, ASICs, FPGAs, APs, GPUs, VPUs, NSPs, microcontrollers, special-purpose hardware, any combination thereof, and / or other processing devices or systems. One or more processors 484 may use bus 489 to communicate between cores and / or with one or more memory devices 486.

[0080] The computing system 470 may also include one or more memory devices 486, one or more digital signal processors (DSPs) 482, one or more subscriber identity modules (SIMs) 474, one or more modems 476, one or more wireless transceivers 478, one or more antennas 487, one or more input devices 472 (e.g., camera, mouse, keyboard, touchscreen, touchpad, keypad, microphone and / or the like) and one or more output devices 480 (e.g., display, speaker, printer and / or the like).

[0081] In some aspects, computing system 470 may include one or more RF interfaces configured to transmit and / or receive radio frequency (RF) signals. In some examples, the RF interface may include components such as modem 476, wireless transceiver 478, and / or antenna 487. One or more wireless transceivers 478 may transmit and receive wireless signals (e.g., signal 488) from one or more other devices via antenna 487, such as other wireless devices, network entities (e.g., base stations such as eNBs and / or gNBs, Wi-Fi access points (APs) such as routers or range extenders, etc.), and / or cloud networks, etc. In some examples, computing system 470 may include multiple antennas or antenna arrays that facilitate simultaneous transmission and reception functionality. Antenna 487 may be an omnidirectional antenna, allowing radio frequency (RF) signals to be received from and transmitted in all directions. Wireless signal 488 may be transmitted via a wireless network. The wireless network may be any wireless network, such as cellular or telecommunications networks (e.g., 3G, 4G, 5G, etc.), wireless local area networks (e.g., Wi-Fi networks), Bluetooth, etc. TM Networks and / or other networks.

[0082] In some examples, wireless signal 488 can be transmitted directly to other wireless devices using sidelink communication (e.g., using a PC5 interface, using a DSRC interface, etc.). Wireless transceiver 478 can be configured to transmit RF signals via antenna 487 for performing sidelink communication according to one or more transmit power parameters that can be associated with one or more regulated modes. Wireless transceiver 478 can also be configured to receive sidelink communication signals with different signal parameters from other wireless devices.

[0083] In some examples, one or more wireless transceivers 478 may include an RF front end, which includes one or more components such as amplifiers, mixers (also known as signal multipliers) for down-converting signals, frequency synthesizers (also known as oscillators) that supply signals to the mixers, baseband filters, analog-to-digital converters (ADCs), one or more power amplifiers, and other components. The RF front end typically handles the selection of wireless signals 488 and the conversion of wireless signals to baseband frequencies or intermediate frequencies, and can convert RF signals to the digital domain.

[0084] In some cases, computing system 470 may include a decoder-decoder device (or codec) configured to encode and / or decode data transmitted and / or received using one or more wireless transceivers 478. In some cases, computing system 470 may include an encryption-decryption device or component configured (e.g., according to AES and / or DES standards) to encrypt and / or decrypt data transmitted and / or received by one or more wireless transceivers 478.

[0085] One or more SIMs 474 may each securely store an International Mobile Subscriber Identity (IMSI) number and associated key assigned to a user of a wireless device 407. The IMSI and key can be used to identify and authenticate the subscriber when accessing a network provided by a network service provider or operator associated with one or more SIMs 474. One or more modems 476 may modulate one or more signals to encode information to be transmitted using one or more wireless transceivers 478. One or more modems 476 may also demodulate signals received by one or more wireless transceivers 478 to decode the transmitted information. In some examples, one or more modems 476 may include a Wi-Fi modem, a 4G (or LTE) modem, a 5G (or NR) modem, and / or other types of modems. One or more modems 476 and one or more wireless transceivers 478 may be used to transmit data from one or more SIMs 474.

[0086] The computing system 470 may also include one or more non-transitory machine-readable storage media or storage devices (e.g., one or more memory devices 486) (and / or communicate with them), which may include, but are not limited to, local and / or network-accessible storage devices, disk drives, drive arrays, optical storage devices, solid-state storage devices (such as RAM and / or ROM), which may be programmable and / or flash-updatable, etc. Such storage devices may be configured to implement any suitable data storage, including but not limited to various file systems and / or database structures, etc.

[0087] In various embodiments, functionality may be stored as one or more computer program products (e.g., instructions or code) in memory device 486 and executed by one or more processors 484 and / or one or more DSPs 482. Computing system 470 may also include software elements (e.g., residing within one or more memory devices 486) including, for example, operating systems, device drivers, executable libraries, and / or other code, such as one or more application programs, which may include computer programs implementing the functionality provided by the various embodiments and / or may be designed to implement methods and / or configure systems as described herein.

[0088] Figure 5An example architecture of a neural network 500 that can be used according to some aspects of this disclosure is illustrated. The example architecture of the neural network 500 may be defined by an example neural network description 502 in the neural controller 501. The neural network 500 is an example of a machine learning model that can be deployed and implemented at base station 102, central unit (CU) 310, distributed unit (DU) 330, radio unit (RU) 340, and / or UE 104. The neural network 500 may be a feedforward neural network or any other known or under-development neural network or machine learning model.

[0089] Neural network description 502 may include the complete specification of neural network 500, including Figure 5 The neural architecture shown is illustrated. For example, neural network description 502 may include: a description or specification of the architecture of neural network 500 (e.g., layers, layer interconnections, number of nodes in each layer, etc.); input and output descriptions indicating how the inputs and outputs are formed or processed; indications of activation functions, operations or filters in the neural network, etc.; neural network parameters such as weights, biases, etc.; and so on.

[0090] Neural network 500 may reflect the neural architecture defined in neural network description 502. Neural network 500 may include any suitable neural or deep learning type of network. In some cases, neural network 500 may include a feedforward neural network. In other cases, neural network 500 may include a recurrent neural network, which may have loops that allow information to be carried across nodes when reading input. Neural network 500 may include any other suitable neural network or machine learning model. One example includes a convolutional neural network (CNN), which includes an input layer and an output layer, with multiple hidden layers between the input and output layers. The hidden layers of a CNN include a series of hidden layers as described below, such as convolutional layers, nonlinear layers, pooling layers (for downsampling), and fully connected layers. In other examples, neural network 500 may represent any other neural network or deep learning network, such as an autoencoder, a deep belief network (DBN), a recurrent neural network (RNN), a generative adversarial network (GAN), etc.

[0091] exist Figure 5In a non-limiting example, neural network 500 includes an input layer 503 that receives one or more sets of input data. The input data can be any type of data (e.g., image data, video data, network parameter data, user data, etc.). Neural network 500 may include hidden layers 504A to 504N (collectively referred to as "504"). Hidden layers 504 may include n hidden layers, where n is an integer greater than or equal to one. The n hidden layers may include many layers required for the desired processing result and / or presentation intent. In an exemplary example, any of the hidden layers 504 may include data representing one or more of the data provided at input layer 503. Neural network 500 also includes an output layer 506 that provides the output produced by the processing performed by hidden layers 504. Output layer 506 may provide output data based on the input data.

[0092] exist Figure 5 In the example, neural network 500 is a multi-layer neural network with interconnected nodes. Each node can represent a piece of information. The information associated with these nodes is shared between different layers, and each layer retains the information while processing it. Information can be exchanged between nodes via node-to-node interconnects between the layers. Nodes in input layer 503 can activate a set of nodes in the first hidden layer 504A. For example, as shown, each input node of input layer 503 is connected to each node in the first hidden layer 504A. Nodes in hidden layer 504A can transform the information by applying an activation function to the information of each input node. The information derived from this transformation can then be passed to nodes in the next hidden layer (e.g., 504B) and can activate these nodes, which can perform their own specified functions. Example functions include convolution, upsampling, data transformation, pooling, and / or any other suitable function. The output of the hidden layer (e.g., 504B) can then activate nodes in the next hidden layer (e.g., 504N), and so on. The output of the last hidden layer can activate one or more nodes in output layer 506, providing the output at that point. In some cases, although nodes in neural network 500 (e.g., nodes 508A, 508B, 508C) are shown as having multiple output lines, a node may have a single output and all lines shown as outputs from the node may represent the same output value.

[0093] In some cases, each node or the interconnections between nodes may have weights derived from a set of parameters trained on the neural network 500. For example, an interconnection between nodes may represent a piece of information learned about the interconnected nodes. Interconnections may have numerical weights that can be tuned (e.g., based on the training dataset), allowing the neural network 500 to adapt to the input and learn as it processes more data.

[0094] The neural network 500 can be pre-trained to process features from the data in the input layer 503 using different hidden layers 504, so as to provide an output through the output layer 506. For example, in some cases, the neural network 500 can use a training process called backpropagation to adjust the weights of the nodes. Backpropagation may include forward pass, loss function, backpropagation, and weight update. Forward pass, loss function, backpropagation, and parameter update can be performed for one training iteration. This process can be repeated for each training dataset up to a certain number of iterations until the weights of these layers are accurately tuned (e.g., meeting a configurable threshold determined based on experimental and / or empirical research).

[0095] More and more ML (e.g., AI) algorithms (e.g., models) are being incorporated into a variety of technologies, including wireless telecommunications standards. Figure 6 This is a block diagram illustrating an ML engine 600 according to various aspects of this disclosure. As an example, one or more devices in a wireless system may include the ML engine 600. In some cases, the ML engine 600 may resemble a neural network 500. In this example, the ML engine 600 includes three parts: an input 602 to the ML engine 600, an ML engine, and an output 604 from the ML engine 600. The input 602 to the ML engine 600 may be data that the ML engine 600 can use to make predictions or otherwise operate. As an example, an ML engine 600 configured to select an RF beam may use data about current RF conditions, location information, network load, etc., as input 602. As another example, data related to data packets transmitted to the UE, along with historical data packet data, may be used as input 602 to an ML engine 600 configured to predict the UE's discontinuous reception (DRX) scheduling. In some cases, the output 604 may be predictions or other information generated by the ML engine 600, and the output 604 may be used to configure the wireless device, adjust settings, parameters, operating modes, etc. Continuing with the previous example, the ML engine 600, configured to select RF beams, can output 604 the available RF beams or sets of RF beams. Similarly, the ML engine 600, configured to predict the UE's DRX schedule, can output the UE's DRX schedule.

[0096] In another example, ML engine 600 may be an encoder for compressing channel state information (e.g., channel state information (CSI) or channel state feedback (CSF)) determined by the UE to generate a representation of control information (e.g., a latent representation). In yet another example, ML engine 600 may be an encoder used by a network entity (e.g., a base station) to decode a representation (e.g., a latent representation) of control information (e.g., CSI) generated by the UE.

[0097] Figure 7This is an illustration of an example network 750 including UE 751 and base station 753 (e.g., a gNB or a part of a gNB, such as the CU, DU, RU, etc. of a gNB with a decomposed architecture). Figure 7 As shown, a downlink channel estimate 752 (e.g., CSI or CSF) is provided to an encoder 754 of the UE 751. The CSI encoder 754 encodes the CSI, and the UE 751 transmits the encoded CSI (e.g., a potential representation of the CSI as a potential message 761, such as a feature vector representing the CSI) to the receive antenna 762 of the base station 753 via a data or control channel 756 using antenna 758 through a wireless or air interface 760. In some cases, the UE 751 may transmit a potential message representing the CSI 761. As noted above, the CSI encoder 754 may replace the PMI codebook used to convert the CSI report bits into PMI codewords.

[0098] The encoded CSI or potential message 761 is provided via data or control channel 764 to a CSI decoder 767 of base station 753, which can decode the encoded CSI to generate a reconstructed downlink channel estimate 768 (or reconstructed CSI). In some cases, base station 753 may then determine the pre-decoding matrix, modulation and decoding scheme (MCS), and / or rank associated with one or more antennas of the base station. Based on the pre-decoding matrix, MCS, and / or rank, base station 753 may determine the configuration of control resources (e.g., via physical downlink control channel (PDCCH)) or data resources (e.g., via physical downlink shared channel (PDSCH)).

[0099] The decoder output can be several different data structures. For example, the decoder output can be the downlink channel matrix (H), the transmit covariance matrix, the downlink pre-decoder (V), the interference covariance matrix (Rnn), or the original whitened downlink channel. In some examples, when the encoder input is (H) (the channel matrix), the decoder output can be H (the channel matrix), V (the eigenvectors), or SV (eigenvalues ​​multiplied by V). When the encoder input is the eigenvector V, the decoder output can also be the eigenvector V. When the encoder input is the inferred covariance matrix Rnn, the output can also be the interference covariance matrix Rnn. The H or V values ​​can correspond to the original channel or to the channel pre-whitened by the UE 751 based on its demodulation filter.

[0100] In some cases, AI / ML-based CSI feedback can use a CSI ML encoder and / or CSI ML decoder instead of PMI. The ML encoder is similar to the PMI search algorithm in current systems. The ML decoder is similar to the PMI codebook and is used to convert CSI report bits into PMI codewords. The following... Figure 8An example of such an ML-based CSI feedback system is shown, along with the input of the ML encoder and the output of the ML decoder.

[0101] Figure 8 Example decoder inputs and example decoder outputs according to various aspects of this disclosure are illustrated. In some cases, the decoder output may be one or more of the following: downlink channel matrix (), transmit covariance matrix, downlink pre-decoder (), interference covariance matrix (), original whitened downlink channel, any combination thereof, and / or other information.

[0102] Figure 9 This illustrates the configuration of CSI-RS capabilities that a UE can send to a network entity (e.g., a base station (such as a gNB) or a portion thereof), such as capability reports for PMI codebooks. Instead of capability reports for PMI codebooks, the UE can report CSI-RS capabilities based on the basic components {maximum number of ports per resource (#), maximum number of resources, maximum number of total ports} to indicate the complexity of the basic features supported by the UE. Figure 9 Other features of the 16-3a-x index are optional features (also known as sub-level features) of the eT2 codebook with additional signaling. The UE can also report CSI-RS capabilities to support additional features, such as the following: Figure 9 16-3a-1. The UE can report whether it supports or does not support additional features, for example, such as... Figure 9 The figures are illustrated by reference numerals 16-3a-2, 16-3a-3, and 16-3a-4.

[0103] Figure 10 This is a conceptual diagram illustrating RRC signaling including CSI-ReportConfig messages. In some cases, network entities (e.g., base stations, such as gNBs) can configure CSI-ReportConfig, including carrier ID, reporting time type, CMR, IMR, reporting quantity, frequency configuration (subband), and codebook configuration, such as based on... Figure 10 The syntax is illustrated. In some cases, ML-based CSI feedback or CSF can be configured differently from regular CSI feedback.

[0104] Figure 11 Examples illustrate potential changes to ML-based CSI feedback or CSF by determining what capabilities the UE should report for ML-based CSI feedback / CSF. In some aspects, the UE reports capabilities related to ML-based two-sided CSI feedback (e.g., such as...). Figure 7(As shown). Similar to older codebook-based CSI reporting, the UE may need to report capabilities for various functions supported by ML models. In some aspects, the UE and base station (e.g., gNB) can develop various ML model pairs, where each different model supports different functions through specific capabilities. In some aspects, the PMI or codebook can be omitted, and various information can be encoded by the ML model at the UE into potential messages output by the ML model (e.g., by an ML-based encoder at the UE (such as...) Figure 7 The codebook configuration may include rank indicator constraints, W1 layout, PMI granularity, and combinations of identifiers or parameters. In an exemplary example, the parameter combinations may include a combination of the number of spatial domain (SD) bases or beams, the number of frequency domain (FD) bases, and the number of non-zero coefficients.

[0105] In some cases, the potential message may include the characteristic representation of the CSI mentioned above (e.g., Figure 7 The potential message (761) reduces the overhead associated with reporting CSI. The potential message also has a specific maximum payload, and the UE may perform different techniques based on the aspects described herein to determine the maximum size of the potential message payload.

[0106] As previously mentioned, this paper describes systems and techniques for performing ML-based control information capability signaling, report configuration, and payload determination. Various aspects are described below. In some aspects, the systems and techniques can provide feature sets and paired identifiers (IDs) for ML-based CSI feedback or CSF (referred to as ML-CSF). For example, paired IDs are a naming process during the model development phase. In one example, specific scenarios or purposes (e.g., for CSI feedback or CSF, as described above relative to...) can be considered. Figure 7 The described development pairing involves a logical UE-side model and a logical network (NW)-side model (e.g., on a base station, such as a gNB). For example, a pairing identifier may be associated with one or more criteria or conditions, such as district, area, scenario, site, cell, or other criteria.

[0107] The criteria / conditions used to determine the pairing ID can be based on one or more vendor offline protocols. The pairing model can implement basic, intermediate, advanced features, or any combination thereof. Feature groups (or sub-features) that can provide PMI reporting can be provided, such as eT2 pairing combinations, rank, etc. For example, for ML-CSF, a feature group can be considered as one or a combination of rank, number of SBs, payload (similar to legacy CSI capability), number of PMIs per subband, pre-decoding limits, etc. In one example, basic features may include rank 1-2, up to 13 SBs, and low / medium payload. In another example, intermediate features may include rank 3-4, up to 13 SBs, and low / medium payload. In yet another example, advanced features may include rank 3-4, 13 to 19 SBs, and high payload. In some cases, pre-decoding matrix limits may exist (e.g., disallowing UEs to report pre-decoders along certain spatial directions) to mitigate inter-cell interference. As an example, a gNB may require UEs to report pre-decoders along some other directions to prevent interference to neighboring cells.

[0108] Figure 12This is a conceptual illustration of capability information reported from a UE to a network entity based on various aspects described herein. In some aspects, capability information may include information pairs. For example, pair information 1202 includes feature groups (FGs) mapped one-to-one with corresponding pair identifiers (e.g., FG1 is mapped to pair ID 1, FG2 to pair ID 2, and FG3 to pair ID 3). In such an example, one or more ML models registered with pair ID 1 are developed to implement FG1, one or more ML models registered with pair ID 2 are developed to implement FG2, and one or more ML models registered with pair ID 3 are developed to implement FG3. In other aspects, pair information 1204 may include pair information corresponding to different feature groups. For example, pair 2 in pair information 1204 corresponds to feature groups FG2 and FG3. In such an example, one or more ML models registered with pair ID 2 are developed to implement FG2 and FG3. In some cases, feature groups may be logical identifiers associated with different models. For example, pair information 1206 includes feature groups mapped to multiple other models. In some aspects, the network entity (e.g., gNB) may be unaware of the specific model implemented at the UE, and the feature set in information 1206 enables the UE to select a model based on a logical pair identifier. In some aspects, the UE may encode information (e.g., CSI) to generate a potential message (e.g., a feature representation of the CSI) based on a specific ML-based model (e.g., an ML-based encoder) selected by the UE, which can be decoded by an ML-based decoder on the network entity. For example, for a feature set including low and medium payload configurations, the UE may use a single ML model to implement low and medium payload feedback, while another UE may design two ML models to implement low and medium payload feedback respectively. However, both ML models are registered with the same logical pair ID.

[0109] In some aspects, systems and technologies can provide capability signaling and Radio Resource Control (RRC) configuration. For example, a UE can report capabilities based on a mapping between CSI-RS capabilities, feature groups, and pairing IDs. CSI-RS capabilities can provide an assessment of the complexity of the UE processing CSI measurements and calculations, such as relative to CSI-RS resources, the number of ports / resources (#ports / res), the total number of ports (#total ports), etc. For example, in any time slot, it is not expected that a UE will have more active CSI-RS ports or active CSI-RS resources in the Active Bandwidth Part (BWP) than reported as capable. Non-zero power (NZP) CSI-RS resources are active for a duration defined as follows: For aperiodic CSI-RS, it begins at the end of the PDCCH containing the request and ends at the end of the Scheduled Physical Uplink Shared Channel (PUSCH) containing the report associated with that aperiodic CSI-RS. When a PDCCH candidate is associated with a searchspace set configured with searchSpaceLinking, the PDCCH candidate that ends later in time among the two linked PDCCH candidates is used to determine the activity duration of an NZP CSI-RS resource. For semi-persistent CSI-RS, it begins at the end when an activation command is applied and ends at the end when a deactivation command is applied. For periodic CSI-RS, it begins when periodic CSI-RS is configured by higher-layer signaling and ends when the periodic CSI-RS configuration is released. If a CSI-RS resource is referenced N times by one or more CSI report settings, the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted N times. For a CSI-RS resource set configured with two resource groups and N resource pairs for channel measurement, if a CSI-RS resource is referenced X times by one of M CSI-RS resources (where M is defined in Clause 5.2.1.4.2) and / or one or two resource pairs, then the CSI-RS resource and the CSI-RS ports within the CSI-RS resource are counted X times.

[0110] In an exemplary example, in any time slot, it is not expected that the UE has more than eight (8) active resources for Type I CSI and more than one (1) active resource for Type I ICSI. In a similar exemplary example of ML-CSF, if the UE reports K resources for a pair ID or feature group, it is not expected that the UE has more than K active resources for that pair ID or feature group. CSI-RS capabilities can be defined not only for resources but also for the number of ports / resources (#ports / res) and the total number of ports (#total ports). In an exemplary example, if the UE reports {P,K,Ptot} for a CSI-RS triple, it is not expected that the UE has more than K resources or more than Ptot total ports if the number of ports for each resource is not greater than P.

[0111] In the first exemplary option (referred to as Option 1) according to the aspects described herein, for each pair ID, the UE may report the supported feature groups and corresponding CSI-RS capabilities. For example, the UE may report CSI-RS capabilities for basic features and may report {supported, not supported} for other more advanced features. In some cases, the UE may additionally or alternatively report CSI-RS capabilities for other more advanced features. In some cases, for each feature, the UE may report multiple CSI-RS triples, where the CSI-RS triples are {maximum number of ports / resources, maximum number of resources, maximum number of total ports}. In some cases, the supported features (including basic features) may be different for different pair IDs.

[0112] In the second exemplary example (referred to as Option 2), for each feature group, the UE may report the supported pair IDs and their CSI-RS capabilities. In some cases, at least one pair ID should be supported for a basic feature group. In some aspects, CSI-RS capability = {maximum number of ports / resources, maximum number of resources, maximum number of total ports}. In some cases, the pair ID is part of the feature group. For example, the feature group is defined as {supported rank, supported payload range, pair ID} or {supported rank, supported payload range, PMI granularity, pair ID} or {supported rank, supported payload range, supported bandwidth or subband number, pair ID}. For Option 1 and / or Option 2, reporting feature groups may be reporting feature group indexes from a pool; reporting CSI-RS capabilities may be reporting CSI-RS capability IDs from a pool. Figure 12 and Figure 13The example shown is exemplary. In some cases, option 1 is considered to be model ID-based lifecycle management (LCM), where feature groups and CSI-RS capabilities are reported for each pair ID, and option 2 is considered to be functionality-based LCM, where the pair ID is part of the functionality / feature group definition.

[0113] Figure 13 A conceptual diagram illustrating reporting capability information according to options 1 and 2 is provided. In some cases, the UE generates capability information 1302 based on the identifiers, feature groups, and CSI-RS capabilities supported by the UE according to option 1. For example, identifier 1 in capability information 1302 indicates that the ML model implemented by the UE registered with ID 1 supports feature group FG1 with CSI-RS capability CSR-RSI cap1, feature group FG2 with CSI-RS capability CSR-RSI cap2, and feature group FG3 with CSI-RS capability CSR-RSI cap3. Identifier 2 in capability information 1302 indicates that the ML model implemented by the UE registered with identifier 2 supports FG1 with CSI-RS capability CSI-RS cap2 and FG3 with CSI-RS capability CSI-RS cap4.

[0114] On the other hand, capability information 1304 can be generated by the UE based on the feature group according to option 2. Capability information 1304 can group pair identifiers with different CSI-RS capabilities and map the groups to different feature groups. For example, capability information 1304 indicates that feature group FG1 is supported with CSI-RS capability 1 by pair identifier 1, and is supported with CSI-RS capability 2 by pair identifier 2. Capability information 1302 and 1304, which identify feature group indices from a pool of feature groups, can be reported. Reporting CSI-RS capabilities can be done by reporting CSI-RS capability IDs from a pool of predetermined CSI-RS capabilities. On the other hand, the UE can report capability information as a combination of pair ID and feature group. The combination of pair ID and feature group is considered functional. The UE can report CSI-RS capabilities for functionality.

[0115] In some aspects, capability signaling is per-band, per-band combination, and per-cell (e.g., site / cell specific) capability. For example, cell specificity can be achieved by naming a pair ID associated with the cell ID. In other aspects, the pair ID is associated with the NW vendor. For example, the pair ID for the first NW vendor may differ from the pair ID for the second NW vendor. This is because some UEs may implement different ML models for different NW vendors, making it impossible for them to share the same ID when performing ML model inference with the first and second NW vendors.

[0116] As an example of CSI reporting settings, in some cases, one or more pair IDs can be configured with the following additional information (if required): rank limits, subband masks, payload configuration, antenna port layout configuration, pre-decoding matrix limits, any combination thereof, and / or other information. In some cases, the configuration should comply with capability signaling.

[0117] In some aspects, the system and techniques allow for payload determination (relative to NW configuration). In some cases, the eT2 payload can be determined based on: number of sub-bands (#SB), antenna layout, number of antenna ports (#ports), number of FD bases, rank, number of non-zero coefficients, and / or other information. In an illustrative example, Where W1 is a spatial domain (SD) basis (e.g., the number of SD bases = the number of columns in W1), W2 is the coefficient matrix, and W f It is a frequency domain (FD) basis (e.g., the number of FD bases = W) f The maximum rank can be configured via a rank limit, and the actual rank can be reported by the UE in Uplink Control Information (UCI) Part 1. The maximum NNZC (in the W2 matrix) can be configured via a parameter combination index, and the actual NNZC can be reported by the UE in UCI Part 1. Based on the aspects described herein, the ML-CSF payload can be determined based on: the number of sub-bands (SBs), antenna layout, number of ports, potential message payload, rank, any combination thereof, and / or other information. The configuration and reporting of the rank can be reused. The configuration of the number of SBs, antenna layout, and number of ports can be reused, but it may be necessary to determine how the final payload scales with them. The configuration of the potential message payload and its reporting may require a new signaling design.

[0118] Other aspects of this disclosure include the identification of payload information. In some cases, the payload information may be explicit and include multiple parameters for explicitly setting the size of the potential message.

[0119] In an illustrative example (referred to as Example 1) of payload determination relative to a network entity configuration, the network entity (e.g., a base station, such as a gNB, or a portion thereof) may explicitly configure the maximum payload of potential messages. In some cases (referred to as Case 1.1), the maximum payload is per subband or subband range, per port or port range, and / or per rank or per rank group. In some examples, for the number of subbands <= 6, the number of bits N_1 is 32; for the number of subbands > 6 but <= 12, the number of bits N_2 is 64; and for the number of subbands > 12, the number of bits N_3 = 96. Relative to rank, for each rank 1 / 2 layer, the number of bits N_1,2 is 64; and for each rank 3 / 4 layer, N_3,4 is 32. In some cases (referred to as Case 1.2), the maximum payload is per basic subband, which is predetermined by the network entity, and the maximum payload for other #SBs scales with this configuration number. In some examples, Where N_0 is the maximum payload per N_(SB, basic) SBs. In some cases (referred to as Case 1.3), the maximum payload is per basic #port, and the maximum payload for other #ports scales with the configuration number. In some examples, Where N_0 is the maximum payload per N_(ports, basic) ports. In some respects, the maximum payload in case 1.1 and the scaling factors (α and β, respectively) in cases 1.2 and 1.3 are predefined in the standard, or determined in offline model development based on the model ID or functionality. Depending on cases 1.1, 1.2, and 1.3, as well as others, the payload determination may scale with the number of subbands or subband ranges, the number of ports or port ranges, or the rank or rank group.

[0120] In another exemplary example of payload determination relative to the NW configuration (referred to as Example 2), it can be implicit. For example, it can be implicitly defined by the total dimension of the CSI feature representation reported by the CSI output from one or more ML encoders of the UE, the codeword length of a subset of the values ​​used to quantize the CSI feature representation, or the number of bits used to quantize the values ​​of the CSI feature representation (e.g., {dimension d_z, quantization bits Q, codeword length cw_len}, where dimension d zThe potential message (e.g., per layer) payload is parameterized by the dimensions of the potential message, Q being the number of bits used for quantization, and the codeword length cw_len being the codeword length used for quantization. For example, the final payload can be determined by N = Q × d_z / (CW_len) (or if {d_z, Q, CW_len} is configured for each layer, then N = Q × d_z / (CW_len) × RI, and RI is the rank reported by the UE). In some cases, at least one of {d_z, Q, cw_len} is developed offline per model ID or per function. In some examples, at least one of {d_z, Q, cw_len} is configured by the NW (e.g., by the base station, such as gNB). In some cases, the dictionary is non-normalized, and it is developed per model ID or per function.

[0121] For example, dimension d_z can be expressed in 64 dimensions (d_z = 64){z1, z2, z3, z4, z5…z 64 The parameterization is d_z, where the codeword length cw_len is 4. In this case, vectors z1, z2, z3, and z4 are quantized into a single vector represented by Q bits. According to various aspects of this disclosure, the dimension d_z, the quantization bits Q, or the codeword length cw_len can be scaled with the number of subbands or subband ranges, the number of ports or port ranges, or the rank or rank group.

[0122] In some respects, the system and technology provide solutions for UE-based payload determination. For example, the principle behind actual payload determination in versions 15, 16, and 17 (R15 / 16 / 17) involves the UE being able to observe fewer non-zero coefficients in the W2 matrix during CSI calculation, eliminating the need for the UE to quantify and report those near-zero coefficients. Observation is a byproduct of CSI calculation and does not impose any complexity burden.

[0123] In some respects, the systems and techniques described herein can provide alternatives for compressing potential messages using non-zero configuration number (NNZC) reporting. In one respect, the UE can report the actual non-zero entries in the potential message. In another respect, the UE can explicitly report the NNZC and its location (e.g., this can result in even greater overhead than reporting them all). In another exemplary respect, the UE can identify a predefined pattern of non-zero entries, and the UE can report the index corresponding to the non-zero entry (if the UE observes a non-zero entry in the predefined pattern and other locations are nearly zero). In yet another exemplary example, the UE can report only the number of non-zero entries, where the last d_z-K_NZ entries are zero, where K_NZ is the number of non-zero entries.

[0124] Figure 14This is a flowchart of an example method 1400 for providing wireless communication at a UE according to various aspects of this disclosure. Process 1400 can be performed by the UE (e.g., Figure 7 The operation of process 1400 can be implemented in one or more processors (e.g., UE 751) or any component or system of the UE or any device (e.g., chipset). Figure 16 Software components that execute and run on the processor 1610 or other processor. Furthermore, the UE may be enabled to transmit and receive signals in process 1400, for example, via one or more antennas and / or one or more transceivers (e.g., wireless transceivers).

[0125] At box 1402, the UE may determine capability information associated with at least one feature group, at least one identifier associated with one or more ML models, and at least one set of the UE's CSI-RS capabilities. The at least one identifier is associated with the one or more ML models and includes at least one paired identifier associated with the UE's ML-based model (e.g., an ML-based encoder) and the network entity's ML-based model (e.g., an ML-based decoder). In some aspects, the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limits. For example, the feature group may have high complexity, medium complexity, and low complexity based on the number of resources to be configured (e.g., rank, number of subbands, etc.). According to some aspects, the at least one set of CSI-RS capabilities includes the maximum number of ports, the maximum number of resources, and the maximum number of ports per resource.

[0126] For each of the at least one pairing identifiers, examples of capability information include a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities. Each configuration identifier of the capability information consists of the pairing identifier, feature group, and CSI-RS capability supported by the UE.

[0127] For each of the at least one pairing identifiers, another example of capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities. Each configuration identifier consists of the corresponding feature group supported by the UE, the CSI-RS capabilities, and the pairing identifier.

[0128] At box 1404, the UE can send capability information to network entities. For example, the UE can send capability information to the gNB.

[0129] At box 1406, the UE may receive a CSI report configuration that includes an identifier from at least one identifier (e.g., an identifier from the identifiers of at least one identifier). For example, the identifier may identify an ML-based encoder for the UE to encode the CSI.

[0130] In some aspects, the CSI report configuration may include explicit information corresponding to the maximum payload. In one aspect, the CSI report configuration includes payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier. In a non-limiting example, the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or rank or rank groups. In another example, the payload information is based on a predetermined number of subbands and the number of subbands configured for the UE. In yet another example, the payload information is based on a predetermined number of ports and the number of ports configured for the UE. In some aspects, a scaling factor may also be used to determine the maximum payload, and the scaling factor may be predetermined, as defined by the standard. In some cases, the scaling factor may be determined based on the identifier or based on offline model development.

[0131] In some aspects, the CSI report configuration may include at least one parameter associated with the potential message. The parameter associated with the potential message may include the total dimension (e.g., d_z) of the CSI feature representation of the CSI report output by one or more ML encoders of the UE, the codeword length (e.g., cw_len) of the subset of values ​​used to quantize the CSI feature representation, or the number of bits (e.g., Q) of the subset of values ​​used to quantize the CSI feature representation. In some aspects, the parameter may scale with the number of subbands or subband ranges, the number of ports or port ranges, or the rank or rank group.

[0132] In some aspects, the UE may transmit a CSI feature representation output by the UE's ML-based encoder. This CSI feature representation may be transmitted in a potential message. In some cases, the CSI feature representation includes information identifying the number of non-zero coefficients and the position of that number of non-zero coefficients. In one example, the UE may identify the number of non-zero coefficients and the position of that number of non-zero coefficients. In another case, the CSI feature representation includes an index identifying the position of each of the plurality of non-zero coefficients in the CSI feature representation. In yet another example, the CSI feature representation includes the number of non-zero coefficients in the CSI feature representation, wherein the non-zero coefficients precede the zero-value coefficients in the CSI feature representation.

[0133] Figure 15This is a flowchart illustrating an example of a process or method 1500 for wireless communication. Process 1500 may be performed by a network entity such as a base station (e.g., by...). Figure 7 The operation of process 1500 can be implemented in one or more processors (e.g., BS 753 or gNB) or a portion thereof (e.g., CU, DU, RU, etc. of a base station). Figure 16 Software components that execute and run on the processor 1610 or other processor. Furthermore, the UE may be enabled to transmit and receive signals in process 1500, for example, via one or more antennas and / or one or more transceivers (e.g., wireless transceivers).

[0134] At box 1502, the network entity may receive capability information associated with at least one feature group, at least one identifier associated with one or more ML models, and at least one set of the UE's CSI-RS capabilities. In one aspect, the capability information includes at least one identifier associated with one or more ML models and at least one set of the UE's CSI-RS capabilities. The at least one identifier is associated with the one or more ML models and includes at least one pairing identifier associated with the UE's ML-based model (e.g., an ML-based encoder) and the network entity's ML-based model (e.g., an ML-based decoder). In some aspects, the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limits. For example, the feature group may have high complexity, medium complexity, and low complexity based on the number of resources to be configured (e.g., rank, number of subbands, etc.). According to some aspects, the at least one set of CSI-RS capabilities includes the maximum number of ports, the maximum number of resources, and the maximum number of ports per resource.

[0135] For each of the at least one pairing identifiers, examples of capability information include a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities. Each configuration identifier of the capability information consists of the pairing identifier, feature group, and CSI-RS capability supported by the UE.

[0136] For each of the at least one pairing identifiers, another example of capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities. Each configuration identifier consists of the corresponding feature group supported by the UE, the CSI-RS capabilities, and the pairing identifier.

[0137] In some respects, the network entity may select an identifier from the form of the capability information, which identifies the ML-based encoder used by the UE and the ML-based decoder used by the network entity to decode messages.

[0138] At box 1504, the network entity may send a CSI report configuration to the UE including an identifier from at least one identifier (e.g., an identifier from at least one identifier). The UE may then begin reporting potential messages encoded by an ML-based encoder corresponding to that identifier, and the network entity may decode the CSI.

[0139] In some examples, the processes described herein (e.g., method 1400, method 1500, and / or other processes described herein) may be performed by a computing device or apparatus. In one example, methods 1400 and 1500 may be performed by a device having Figure 16 The computing architecture of the computing system 1600 shown is a computing device (e.g., Figure 4 The computing system 470 in the middle is used to execute it.

[0140] Processes 1400 and 1500 are illustrated as logic flowcharts, whose operations represent sequences of operations that can be implemented by hardware, computer instructions, or combinations thereof. In the context of computer instructions, each operation represents a computer-executable instruction stored on one or more computer-readable storage media that, when executed by one or more processors, performs the described operation. Generally, computer-executable instructions include routines, programs, objects, components, data structures, etc., that perform a specific function or implement a specific data type. The order in which the operations are described is not intended to be construed as limiting, and any number of described operations can be combined in any order and / or in parallel to implement the method.

[0141] Processes 1400, 1500, and / or other methods or processes described herein may be executed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that executes jointly on one or more processors, implemented in hardware, or implemented in a combination thereof. As noted above, the code may be stored on a computer-readable or machine-readable storage medium, for example, in the form of a computer program comprising multiple instructions executable by one or more processors. The computer-readable or machine-readable storage medium may be non-transitory.

[0142] Figure 16 This is a diagram illustrating an example of a system used to implement certain aspects of this technology. Specifically, Figure 16An example of computing system 1600 is provided, which can be any computing device, such as constituting an internal computing system, a remote computing system, a camera, or any component thereof, wherein the components of the system communicate with each other using connection 1605. Connection 1605 can be a physical connection using a bus, or a direct connection to processor 1610, such as in a chipset architecture. Connection 1605 can also be a virtual connection, a networking connection, or a logical connection.

[0143] In some aspects, computing system 1600 is a distributed system, wherein the functions described in this disclosure can be distributed across a data center, multiple data centers, a peer-to-peer network, etc. In some aspects, one or more of the described system components represent a plurality of such components, each of which performs some or all of the functions of the described components. In some aspects, the components can be physical or virtual devices.

[0144] Example computing system 1600 includes at least one processing unit (CPU or processor) 1610 and a connection 1605 that couples various system components, including system memory 1615 (such as ROM 1620 and RAM 1625), to processor 1610. Computing system 1600 may include a cache 1612 of high-speed memory that is directly connected to, closely adjacent to, or integrated into processor 1610.

[0145] Processor 1610 may include any general-purpose processor and hardware or software services, such as services 1632, 1634, and 1636 stored in storage device 1630, which are configured to control processor 1610 and dedicated processors in which software instructions are incorporated into the actual processor design. Processor 1610 may be a substantially completely independent computing system containing multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.

[0146] To enable user interaction, the computing system 1600 includes an input device 1645 that can represent any number of input mechanisms, such as a microphone for voice, a touch-sensitive screen for gesture or graphical input, a keyboard, a mouse, motion input, voice input, etc. The computing system 1600 may also include an output device 1635 that can be one or more of a plurality of output mechanisms. In some instances, a multi-mode system allows a user to provide multiple types of input / output to communicate with the computing system 1600. The computing system 1600 may include a communication interface 1640, which typically controls and manages user input and system output. The communication interface can perform or facilitate the receipt and / or transmission of wired or wireless communications using wired and / or wireless transceivers, including utilizing audio jacks / plugs, microphone jacks / plugs, Universal Serial Bus (USB) ports / plugs, etc. Ports / plugs, Ethernet ports / plugs, fiber optic ports / plugs, dedicated wired ports / plugs Wireless signal transmission, BLE wireless signal transmission Wireless signal transmission, RFID wireless signal transmission, Near Field Communication (NFC) wireless signal transmission, Dedicated Short Range Communication (DSRC) wireless signal transmission, 802.11 WiFi wireless signal transmission, WLAN signal transmission, Visible Light Communication (VLC), Microwave Access Global Interoperability (WiMAX), IR communication wireless signal transmission, Public Switched Telephone Network (PSTN) signal transmission, Integrated Services Digital Network (ISDN) signal transmission, 3G / 4G / 5G / LTE cellular data network wireless signal transmission, ad hoc network signal transmission, radio wave signal transmission, microwave signal transmission, infrared signal transmission, visible light signal transmission, ultraviolet light signal transmission, wireless signal transmission along the electromagnetic spectrum, or combinations thereof. The communication interface 1640 may also include one or more Global Navigation Satellite System (GNSS) receivers or transceivers for determining the location of the computing system 1600 based on one or more signals received from one or more satellites associated with one or more GNSS systems. GNSS systems include, but are not limited to, the US GPS, Russia's GLONASS, China's BeiDou Navigation Satellite System (BDS), and Europe's Galileo GNSS. There are no limitations on operation on any particular hardware configuration, and therefore the underlying features can be easily replaced to obtain improved hardware or firmware configurations as they are developed.

[0147] Storage device 1630 may be a non-volatile and / or non-transitory and / or computer-readable storage device, and may be a hard disk or other type of computer-readable medium capable of storing data accessible by a computer, such as magnetic tape, flash memory cards, solid-state storage devices, digital multifunction discs, cartridges, floppy disks, hard disks, magnetic tapes, magnetic stripes, any other magnetic storage media, flash memory, memristor memory, any other solid-state storage, CD-ROM discs, rewritable CD discs, DVD discs, Blu-ray discs (BDD discs), holographic discs, another optical medium, secure digital storage (SD) cards, micro-secure digital storage (microSD) cards, etc. Cards, smart card chips, EMV chips, Subscriber Identity Module (SIM) cards, mini / micro / nano / micro SIM cards, another integrated circuit (IC) chip / card, RAM, static RAM (SRAM), dynamic RAM (DRAM), ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash EPROM, cache memory (L1 / L2 / L3 / L4 / L5 / L#), resistive random access memory (RRAM / ReRAM), phase-change memory (PCM), spin-transfer torque RAM (STT-RAM), another memory chip or cassette and / or combinations thereof.

[0148] Storage device 1630 may include software services, servers, services, etc., which enable the system to perform functions when the code defining such software is executed by processor 1610. In some aspects, hardware services performing specific functions may include software components for performing functions stored in a computer-readable medium connected to necessary hardware components such as processor 1610, connection 1605, output device 1635, etc. The term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing, or carrying instructions and / or data. Computer-readable media may include non-transitory media in which data may be stored and which do not include carrier waves and / or transient electronic signals propagating wirelessly or over a wired connection. Examples of non-transitory media include, but are not limited to, magnetic disks or magnetic tapes, optical storage media (such as CDs or DVDs), flash memory, memory, or memory devices. Computer-readable media may store code and / or machine-executable instructions thereon, which may represent procedures, functions, subroutines, programs, routines, subroutines, modules, software packages, classes, or any combination of instructions, data structures, or program statements. Code segments may be coupled to other code segments or hardware circuitry by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc., may be passed, forwarded, or transmitted via any suitable means, including memory sharing, message passing, token passing, network transmission, etc.

[0149] In some cases, a computing device or apparatus may include various components such as one or more input devices, one or more output devices, one or more processors, one or more microprocessors, one or more microcomputers, one or more cameras, one or more sensors, and / or other components configured to perform the steps of the processes described herein. In some examples, a computing device may include a display, one or more network interfaces configured to transmit and / or receive data, any combination thereof, and / or other components. One or more network interfaces may be configured to transmit and / or receive wired and / or wireless data, including data according to 3G, 4G, 5G, and / or other cellular standards, data according to the Wi-Fi (802.11x) standard, and data according to Bluetooth. TM Standard data, data according to IP standards, and / or other types of data.

[0150] Components that enable the implementation of a computing device in a circuit. For example, each component may include and / or may be implemented using electronic circuits or other electronic hardware (which may include one or more programmable electronic circuits (e.g., microprocessors, GPUs, DSPs, CPUs, and / or other suitable electronic circuits)), and / or may include and / or may be implemented using computer software, firmware, or any combination thereof to perform the various operations described herein.

[0151] In some respects, computer-readable storage devices, media, and memories may include cables or wireless signals containing bit streams, etc. However, when referred to, non-transitory computer-readable storage media explicitly exclude media such as power consumption, carrier signals, electromagnetic waves, and the signals themselves.

[0152] Specific details are provided in the foregoing description to provide a thorough understanding of the aspects and examples presented herein. However, those skilled in the art will understand that these aspects can be practiced without these specific details. For clarity, in some cases, the technology may be presented as comprising individual functional blocks, including functional blocks containing devices, device components, steps or routines in methods embodied in software or a combination of hardware and software. Additional components may be used in addition to those shown in the figures and / or described herein. For example, circuits, systems, networks, processes and other components may be shown as components in block diagram form to avoid obscuring these aspects in unnecessary detail. In other cases, well-known circuits, processes, algorithms, structures and techniques may be shown without unnecessary detail to avoid obscuring the aspects.

[0153] The various aspects described above can be presented as a process or method, depicted as a flowchart, diagrammatic flowchart, data flow diagram, structural diagram, or block diagram. Although a flowchart can describe operations as a sequential process, many operations within an operation can be executed in parallel or concurrently. Furthermore, the order of operations can be rearranged. A process terminates when its operations are completed, but a process may have additional steps not included in the accompanying diagram. A process can correspond to a method, function, procedure, subroutine, subroutine, etc. When a process corresponds to a function, the termination of that process can correspond to the function returning to the calling function or the main function.

[0154] The processes and methods described in the examples above can be implemented using stored computer-executable instructions or computer-executable instructions otherwise obtainable from a computer-readable medium. Such instructions may include, for example, instructions and data that configure a general-purpose computer, special-purpose computer, or processing device to perform a function or group of functions. The portion may be accessible via a network of the computer resources used. The computer-executable instructions may be, for example, binary, intermediate format instructions, such as assembly language, firmware, source code, etc. Examples of computer-readable media that can be used to store instructions, information used, and / or information created during the methods according to the described examples include disks or optical discs, flash memory, USB devices with non-volatile memory, networked storage devices, etc.

[0155] Devices implementing the processes and methods according to these disclosures may include hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof, and may take any of a variety of form factors. When implemented as software, firmware, middleware, or microcode, program code or code segments (e.g., computer program products) for performing necessary tasks may be stored in a computer-readable or machine-readable medium. A processor performs the necessary tasks. Typical examples of form factors include laptop computers, smartphones, mobile phones, tablet devices, or other small form factor personal computers, personal digital assistants, rack-mounted devices, standalone devices, etc. The functionality described herein may also be embodied in peripheral devices or interlocking cards. By further example, such functionality may also be implemented on circuit boards of different chips or different processes executed on a single device.

[0156] Instructions, media for delivering such instructions, computing resources for executing them, and other structures for supporting such computing resources are example components for providing the functionality described in this disclosure.

[0157] In the foregoing description, aspects of this application have been described with reference to their specific aspects, but those skilled in the art will recognize that this application is not limited thereto. Therefore, although illustrative aspects of this application have been described in detail herein, it is to be understood that the various inventive concepts can be implemented and employed in a variety of other ways, and the appended claims are not intended to be construed as including these variations unless limited by prior art. The various features and aspects of the applications described above can be used individually or in combination. Furthermore, aspects can be utilized in any number of environments and applications beyond those described herein without departing from the broader spirit and scope of this specification. Therefore, the specification and drawings should be considered illustrative rather than restrictive. For illustrative purposes, the methods are described in a particular order. It should be understood that, in alternative aspects, the methods may be performed in a different order than described.

[0158] Those skilled in the art will understand that, without departing from the scope of this description, the less than (“<”) and greater than (“>”) symbols or terms used herein may be replaced by the less than or equal to (“≤”) and greater than or equal to (“≥”) symbols, respectively.

[0159] When a component is described as being “configured” to perform certain operations, such a configuration can be achieved, for example, by designing electronic circuits or other hardware to perform the operations, by programming programmable electronic circuits (e.g., microprocessors or other suitable electronic circuits) to perform the operations, or any combination thereof.

[0160] The phrase “coupled to” means any component is physically connected directly or indirectly to another component, and / or any component communicates directly or indirectly with another component (e.g., connected to another component via a wired or wireless connection and / or other suitable communication interface).

[0161] The claim language or other language that states "at least one of" and / or "one or more of" in a set indicates that one member of the set or multiple members of the set (in any combination) satisfies the claim. For example, the claim language stating "at least one of A and B" or "at least one of A or B" means A, B, or A and B. In another example, the claim language stating "at least one of A, B, and C" or "at least one of A, B, or C" means A, B, C, or A and B, or A and C, or B and C, or A and B and C. The language "at least one of" and / or "one or more of" in a set does not limit the set to the items listed in the set. For example, the claim language stating "at least one of A and B" or "at least one of A or B" may mean A, B, or A and B, and may additionally include items not listed in the set of A and B.

[0162] The various exemplary logic blocks, modules, circuits, and algorithm steps described in conjunction with the aspects disclosed herein can be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been broadly described above in terms of their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this application.

[0163] The techniques described herein can also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques can be implemented in any of a variety of devices, such as general-purpose computers, wireless communication devices (mobile phones), or integrated circuit devices with multiple uses, including applications in wireless communication devices (mobile phones) and other devices. Any feature described as a module or component can be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, these techniques can be implemented at least in part by a computer-readable data storage medium comprising program code including instructions that, when executed, perform one or more of the methods described above. The computer-readable data storage medium can form part of a computer program product, which may include packaging material. The computer-readable medium can include memory or data storage media, such as RAM (e.g., Synchronous Dynamic Random Access Memory (SDRAM)), ROM, non-volatile random access memory (NVRAM), EEPROM, flash memory, magnetic or optical data storage media, etc. Additionally or alternatively, the technology may be implemented at least in part by a computer-readable communication medium that carries or conveys program code in the form of instructions or data structures that can be accessed, read and / or executed by a computer, such as propagated signals or waves.

[0164] The program code can be executed by a processor, which may include one or more processors, such as one or more DSPs, general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such a processor can be configured to perform any of the techniques described in this disclosure. A general-purpose processor may be a microprocessor; however, in alternatives, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration. Therefore, as used herein, the term "processor" may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or means suitable for implementing the techniques described herein.

[0165] The exemplary aspects of this disclosure include:

[0166] Aspect 1. A method for wireless communication at a user equipment (UE), the method comprising: determining capability information associated with at least one set of features, at least one identifier associated with one or more machine learning (ML) models, and at least one set of channel state information reference signal (CSI-RS) capabilities of the UE; transmitting the capability information to a network entity; and receiving a CSI report configuration including the identifier among the at least one identifier.

[0167] Aspect 2. The method according to aspect 1, wherein the at least one identifier associated with the one or more ML models includes at least one paired identifier associated with the ML-based model of the UE and the ML-based model of the network entity.

[0168] Aspect 3. The method according to any one of Aspects 1 to 2, wherein the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limit.

[0169] Aspect 4. The method according to any one of Aspects 1 to 3, wherein the at least one set of CSI-RS capabilities includes a maximum number of ports, a maximum number of resources, and a maximum number of ports per resource.

[0170] Aspect 5. The method according to any one of Aspects 1 to 4, wherein for each of the at least one pairing identifier, the capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities.

[0171] Aspect 6. The method according to any one of Aspects 1 to 5, wherein for each of the at least one feature group, the capability information includes a corresponding pairing identifier among the at least one pairing identifier and a corresponding set of CSI-RS capabilities from the at least one set of CSI-RS capabilities corresponding to the corresponding pairing identifier.

[0172] Aspect 7. The method according to any one of Aspects 1 to 6, wherein the CSI report configuration further includes payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier.

[0173] Aspect 8. The method according to any one of Aspects 1 to 7, wherein the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or rank or rank group.

[0174] Aspect 9. The method according to any one of Aspects 1 to 8, wherein the payload information is based on a predetermined number of subbands and the number of subbands configured for the UE.

[0175] Aspect 10. The method according to any one of Aspects 1 to 9, wherein the payload information is based on a predetermined number of ports and the number of ports configured for the UE.

[0176] Aspect 11. The method according to any one of Aspects 1 to 10, the method further comprising: determining, based on at least one parameter, payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier.

[0177] Aspect 12. The method according to any one of Aspects 1 to 11, wherein the at least one parameter includes at least one of the following: the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the UE, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

[0178] Aspect 13. The method according to any one of Aspects 1 to 12, the method further comprising: transmitting a CSI feature representation output by the ML-based encoder of the UE.

[0179] Aspect 14. The method according to any one of Aspects 1 to 13, wherein the CSI feature representation includes information identifying the number of non-zero coefficients and the location of the number of non-zero coefficients.

[0180] Aspect 15. The method according to any one of Aspects 1 to 14, wherein the CSI feature representation includes an index identifying the position of each of the plurality of non-zero coefficients in the CSI feature representation.

[0181] Aspect 16. The method according to any one of Aspects 1 to 15, wherein the CSI feature representation includes the number of non-zero coefficients in the CSI feature representation, wherein the non-zero coefficients are preceding the zero-value coefficients in the CSI feature representation.

[0182] Aspect 17. The method according to aspect 16, wherein the number of said non-zero coefficients is reported in the first part of the CSI report, while others related to the potential message are reported in the second part.

[0183] Aspect 18. A method for wireless communication at a network entity, the method comprising: receiving capability information associated with at least one set of features, at least one identifier associated with one or more machine learning (ML) models, and at least one set of Channel State Information Reference Signal (CSI-RS) capabilities of the UE; and sending a CSI report configuration to the UE including the identifier among the at least one identifier.

[0184] Aspect 19. The method according to aspect 18, wherein the at least one identifier associated with the one or more ML models includes at least one paired identifier associated with the ML-based model of the UE and the ML-based model of the network entity.

[0185] Aspect 20. The method according to any one of Aspects 18 to 19, wherein the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limit.

[0186] Aspect 21. The method according to any one of Aspects 18 to 20, wherein the at least one set of CSI-RS capabilities includes a maximum number of ports, a maximum number of resources, and a maximum number of ports per resource.

[0187] Aspect 22. The method according to any one of aspects 18 to 21, wherein for each of the at least one pairing identifier, the capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities.

[0188] Aspect 23. The method according to any one of Aspects 18 to 22, wherein for each of the at least one feature group, the capability information includes a corresponding pairing identifier among the at least one pairing identifier and a corresponding set of CSI-RS capabilities from the at least one set of CSI-RS capabilities corresponding to the corresponding pairing identifier.

[0189] Aspect 24. The method according to any one of Aspects 18 to 23, wherein the CSI report configuration further includes payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier.

[0190] Aspect 25. The method according to any one of Aspects 18 to 24, wherein the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or rank or rank group.

[0191] Aspect 26. The method according to any one of Aspects 18 to 25, wherein the payload information is based on a predetermined number of subbands and the number of subbands configured for the UE.

[0192] Aspect 27. The method according to any one of Aspects 18 to 26, wherein the payload information is based on a predetermined number of ports and the number of ports configured for the UE.

[0193] Aspect 28. The method according to any one of Aspects 18 to 27, wherein the payload information identifies at least one parameter, wherein the UE determines the maximum payload of the CSI report generated by the ML model indicated by the identifier based on the at least one parameter.

[0194] Aspect 29. The method according to any one of Aspects 18 to 28, wherein the at least one parameter includes at least one of the following: the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the UE, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

[0195] Aspect 30. The method according to any one of aspects 18 to 29, the method further comprising: receiving a CSI feature representation output by an ML-based encoder of the UE.

[0196] Aspect 31. The method according to any one of Aspects 18 to 30, wherein the CSI feature representation includes information identifying the number of non-zero coefficients and the location of the number of non-zero coefficients.

[0197] Aspect 32. The method according to any one of Aspects 18 to 31, wherein the CSI feature representation includes an index identifying the position of each of the plurality of non-zero coefficients in the CSI feature representation.

[0198] Aspect 33. The method according to any one of Aspects 18 to 32, wherein the CSI feature representation includes the number of non-zero coefficients in the CSI feature representation, wherein the non-zero coefficients are preceding the zero-value coefficients in the CSI feature representation.

[0199] Aspect 34. The method according to aspect 33, wherein the number of said non-zero coefficients is reported in the first part of the CSI report, while others related to the potential message are reported in the second part.

[0200] Aspect 35. An apparatus for wireless communication, the apparatus comprising at least one memory and at least one processor coupled to said at least one memory. The at least one processor is configured to: determine capability information associated with at least one set of features, at least one identifier associated with one or more machine learning (ML) models, and at least one set of Channel State Information Reference Signal (CSI-RS) capabilities of the apparatus; transmit said capability information to a network entity; and receive a CSI report configuration including the identifier from said at least one identifier.

[0201] Aspect 36. The apparatus according to aspect 35, wherein the at least one identifier associated with the one or more ML models includes at least one paired identifier associated with the ML-based encoder of the apparatus and the ML-based decoder of the network entity.

[0202] Aspect 37. The apparatus according to any one of Aspects 35 to 36, wherein the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limit.

[0203] Aspect 38. The apparatus according to any one of Aspects 35 to 37, wherein the at least one set of CSI-RS capabilities includes a maximum number of ports, a maximum number of resources, and a maximum number of ports per resource.

[0204] Aspect 39. The apparatus according to any one of aspects 35 to 38, wherein for each of the at least one pairing identifier, the capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities.

[0205] Aspect 40. The apparatus according to any one of aspects 35 to 39, wherein for each of the at least one feature group, the capability information includes a corresponding pairing identifier among the at least one pairing identifier and a corresponding set of CSI-RS capabilities from the at least one set of CSI-RS capabilities corresponding to the corresponding pairing identifier.

[0206] Aspect 41. The apparatus according to any one of Aspects 35 to 40, wherein the CSI report configuration further includes payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier.

[0207] Aspect 42. The apparatus according to any one of aspects 35 to 41, wherein the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or rank or rank group.

[0208] Aspect 43. The apparatus according to any one of Aspects 35 to 42, wherein the payload information is based on a predetermined number of sub-bands and the number of sub-bands configured for the apparatus.

[0209] Aspect 44. The apparatus according to any one of Aspects 35 to 43, wherein the payload information is based on a predetermined number of ports and the number of ports configured for the apparatus.

[0210] Aspect 45. The apparatus according to any one of Aspects 35 to 44, wherein the at least one processor is configured to: determine payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier based on at least one parameter.

[0211] Aspect 46. The apparatus according to any one of aspects 35 to 45, wherein the at least one parameter includes at least one of the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the apparatus, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

[0212] Aspect 47. The apparatus according to any one of Aspects 35 to 46, wherein the at least one processor is configured to: transmit a CSI feature representation output by the ML-based encoder of the apparatus.

[0213] Aspect 48. The apparatus according to any one of Aspects 35 to 47, wherein the CSI feature representation includes information identifying the number of non-zero coefficients and the location of the number of non-zero coefficients.

[0214] Aspect 49. The apparatus according to any one of Aspects 35 to 48, wherein the CSI feature representation includes an index identifying the position of each of the plurality of non-zero coefficients in the CSI feature representation.

[0215] Aspect 50. The apparatus according to any one of Aspects 35 to 49, wherein the CSI feature representation includes the number of non-zero coefficients in the CSI feature representation, wherein the non-zero coefficients are preceding the zero-value coefficients in the CSI feature representation.

[0216] Aspect 51. The apparatus according to aspect 50, wherein the number of said non-zero coefficients is reported in a first part of the CSI report, while others related to the potential message are reported in a second part.

[0217] Aspect 52. An apparatus for wireless communication, the apparatus comprising at least one memory and at least one processor coupled to said at least one memory. The at least one processor is configured to: receive capability information associated with at least one feature set, at least one identifier associated with one or more machine learning (ML) models, and at least one set of Channel State Information Reference Signal (CSI-RS) capabilities of a UE; and transmit a CSI report configuration including the identifier among the at least one identifier to the UE.

[0218] Aspect 53. The apparatus according to aspect 52, wherein the at least one identifier associated with the one or more ML models includes at least one paired identifier associated with the ML-based model of the UE and the ML-based model of the apparatus.

[0219] Aspect 54. The apparatus according to any one of Aspects 52 to 53, wherein the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limit.

[0220] Aspect 55. The apparatus according to any one of Aspects 52 to 54, wherein the at least one set of CSI-RS capabilities includes a maximum number of ports, a maximum number of resources, and a maximum number of ports per resource.

[0221] Aspect 56. The apparatus according to any one of aspects 52 to 55, wherein for each of the at least one pairing identifier, the capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities.

[0222] Aspect 57. The apparatus according to any one of aspects 52 to 56, wherein for each of the at least one feature group, the capability information includes a corresponding pairing identifier among the at least one pairing identifier and a corresponding set of CSI-RS capabilities from the at least one set of CSI-RS capabilities corresponding to the corresponding pairing identifier.

[0223] Aspect 58. The apparatus according to any one of Aspects 52 to 57, wherein the CSI report configuration further includes payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier.

[0224] Aspect 59. The apparatus according to any one of Aspects 52 to 58, wherein the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or rank or rank group.

[0225] Aspect 60. The apparatus according to any one of Aspects 52 to 59, wherein the payload information is based on a predetermined number of subbands and the number of subbands configured for the UE.

[0226] Aspect 61. The apparatus according to any one of Aspects 52 to 60, wherein the payload information is based on a predetermined number of ports and the number of ports configured for the UE.

[0227] Aspect 62. The apparatus according to any one of Aspects 52 to 61, wherein the payload information identifies at least one parameter, wherein the UE determines the maximum payload of the CSI report generated by the ML model indicated by the identifier based on the at least one parameter.

[0228] Aspect 63. The apparatus according to any one of aspects 52 to 62, wherein the at least one parameter includes at least one of the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the UE, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

[0229] Aspect 64. The apparatus according to any one of aspects 52 to 63, wherein the at least one processor is configured to: receive a CSI feature representation output by an ML-based encoder of the UE.

[0230] Aspect 65. The apparatus according to any one of aspects 52 to 64, wherein the CSI feature representation includes information identifying the number of non-zero coefficients and the location of the number of non-zero coefficients.

[0231] Aspect 66. The apparatus according to any one of aspects 52 to 65, wherein the CSI feature representation includes an index identifying the position of each of the plurality of non-zero coefficients in the CSI feature representation.

[0232] Aspect 67. The apparatus according to any one of Aspects 52 to 66, wherein the CSI feature representation includes the number of non-zero coefficients in the CSI feature representation, wherein the non-zero coefficients are preceding the zero-value coefficients in the CSI feature representation.

[0233] Aspect 68. The apparatus according to aspect 67, wherein the number of said non-zero coefficients is reported in a first part of the CSI report, while others related to the potential message are reported in a second part.

[0234] Aspect 69. A method for wireless communication at a user equipment (UE), the method comprising: receiving a channel state information (CSI) report configuration including an identifier associated with at least one machine learning (ML) model of the UE; and determining, based on the CSI report configuration, a maximum payload of one or more CSI reports generated using the ML model.

[0235] Aspect 70. The method according to aspect 69, wherein the CSI reporting configuration further includes payload information associated with the maximum payload.

[0236] Aspect 71. The method according to aspect 70, wherein the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or rank or rank group.

[0237] Aspect 72. The method according to any one of Aspects 70 or 71, wherein the payload information is based on a predetermined number of subbands and the number of subbands configured for the UE.

[0238] Aspect 73. The method according to any one of Aspects 70 to 72, wherein the payload information is based on a predetermined number of ports and the number of ports configured for the UE.

[0239] Aspect 74. The method according to aspect 69, the method further comprising: determining payload information associated with the maximum payload based on at least one parameter included in the CSI report configuration.

[0240] Aspect 75. The method according to aspect 74, wherein the at least one parameter includes at least one of the following: the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the UE, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

[0241] Aspect 76. An apparatus for wireless communication, the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and configured to: receive a channel state information (CSI) report configuration including an identifier associated with at least one machine learning (ML) model of the apparatus; and determine, based on the CSI report configuration, a maximum payload of one or more CSI reports generated using the ML model.

[0242] Aspect 77. The apparatus according to aspect 76, wherein the CSI reporting configuration further includes payload information associated with the maximum payload.

[0243] Aspect 78. The apparatus according to aspect 77, wherein the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or rank or rank group.

[0244] Aspect 79. The apparatus according to any one of Aspects 77 or 78, wherein the payload information is based on a predetermined number of sub-bands and the number of sub-bands configured for use in the apparatus.

[0245] Aspect 80. The apparatus according to any one of Aspects 77 to 79, wherein the payload information is based on a predetermined number of ports and the number of ports configured for the apparatus.

[0246] Aspect 81. The apparatus according to any one of Aspects 76 to 80, wherein the at least one processor is configured to determine payload information associated with the maximum payload based on at least one parameter included in the CSI report configuration.

[0247] Aspect 82. The apparatus according to aspect 81, wherein the at least one parameter includes at least one of the following: the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the apparatus, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

[0248] Aspect 83. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform any one of aspects 1 to 17.

[0249] Aspect 84. An apparatus for processing one or more images, the apparatus comprising one or more components for performing operations according to any one of aspects 1 to 17.

[0250] Aspect 85. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform any one of aspects 18 to 34.

[0251] Aspect 86. An apparatus for processing one or more images, the apparatus comprising one or more components for performing operations according to any one of aspects 18 to 34.

[0252] Aspect 87. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform any one of aspects 69 to 75.

[0253] Aspect 88. An apparatus for processing one or more images, the apparatus comprising one or more components for performing operations according to any one of aspects 69 to 75.

Claims

1. An apparatus for wireless communication, the apparatus comprising: At least one memory; and At least one processor, said at least one processor being coupled to at least one memory and configured to: Determine at least one set of capability information associated with at least one feature group, at least one identifier associated with one or more machine learning (ML) models, and at least one set of channel state information reference signal (CSI-RS) capabilities of the device; Send the capability information to the network entity; as well as Receive CSI report configuration including the identifier from the at least one of the identifiers.

2. The apparatus of claim 1, wherein the at least one identifier associated with the one or more ML models includes at least one paired identifier associated with the ML-based model of the apparatus and the ML-based model of the network entity.

3. The apparatus of claim 2, wherein the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limit.

4. The apparatus of claim 2, wherein the at least one set of CSI-RS capabilities includes a maximum number of ports, a maximum number of resources, and a maximum number of ports per resource.

5. The apparatus of claim 2, wherein for each of the at least one pairing identifier, the capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities.

6. The apparatus of claim 2, wherein for each of the at least one set of features, the capability information includes a corresponding pairing identifier among the at least one pairing identifier and a corresponding set of CSI-RS capabilities from the at least one set of CSI-RS capabilities corresponding to the corresponding pairing identifier.

7. The apparatus of claim 2, wherein the CSI report configuration further includes payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier.

8. The apparatus of claim 7, wherein the payload information is based on at least one of the following: the number of subbands or subband ranges, the number of ports or port ranges, or a rank or a group of rank.

9. The apparatus of claim 7, wherein the payload information is based on a predetermined number of sub-bands and the number of sub-bands configured for use in the apparatus.

10. The apparatus of claim 7, wherein the payload information is based on a predetermined number of ports and the number of ports configured for use in the apparatus.

11. The apparatus of claim 2, wherein the at least one processor is configured to: Payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier is determined based on at least one parameter.

12. The apparatus of claim 11, wherein the at least one parameter includes at least one of the following: the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the apparatus, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

13. The apparatus of claim 1, wherein the CSI feature representation output by the ML-based encoder of the apparatus includes information identifying the number of non-zero coefficients and the location of the number of non-zero coefficients.

14. The apparatus of claim 1, wherein the CSI feature representation output by the ML-based encoder of the apparatus includes an index identifying the position of each of the plurality of non-zero coefficients in the CSI feature representation.

15. The apparatus of claim 1, wherein the CSI feature representation output by the ML-based encoder of the apparatus includes the number of non-zero coefficients in the CSI feature representation, wherein the non-zero coefficients are preceding the zero-value coefficients in the CSI feature representation.

16. The apparatus of claim 15, wherein the number of said non-zero coefficients is reported in a first part of the CSI report, while others related to the potential message are reported in a second part.

17. A method for conducting wireless communication at a user equipment (UE), the method comprising: Determine at least one set of capability information associated with at least one feature group, at least one identifier associated with one or more machine learning (ML) models, and at least one set of the UE's channel state information reference signal (CSI-RS) capabilities; Send the capability information to the network entity; as well as Receive CSI report configuration including the identifier from the at least one of the identifiers.

18. An apparatus for wireless communication, the apparatus comprising: At least one memory; and At least one processor, said at least one processor being coupled to at least one memory and configured to: Receive capability information associated with at least one feature group, at least one identifier associated with one or more machine learning (ML) models, and at least one set of channel state information reference signals (CSI-RS) capabilities of the user equipment (UE). as well as Send a CSI report configuration, including the identifier from the at least one identifier, to the UE.

19. The apparatus of claim 18, wherein the at least one identifier associated with the one or more ML models includes at least one paired identifier associated with the ML-based model of the UE and the ML-based model of the apparatus.

20. The apparatus of claim 19, wherein the at least one feature group corresponds to at least one of rank, number of subbands, payload, number of pre-decoding matrices per subband, or pre-decoding limit.

21. The apparatus of claim 19, wherein the at least one set of CSI-RS capabilities includes a maximum number of ports, a maximum number of resources, and a maximum number of ports per resource.

22. The apparatus of claim 19, wherein for each of the at least one pairing identifier, the capability information includes a corresponding feature group from the at least one feature group and a corresponding set of CSI-RS capabilities corresponding to the corresponding feature group from the at least one set of CSI-RS capabilities.

23. The apparatus of claim 19, wherein for each of the at least one set of features, the capability information includes a corresponding pairing identifier among the at least one pairing identifier and a corresponding set of CSI-RS capabilities from the at least one set of CSI-RS capabilities corresponding to the corresponding pairing identifier.

24. The apparatus of claim 19, wherein the CSI report configuration further includes payload information associated with the maximum payload of the CSI report generated by the ML model indicated by the identifier.

25. The apparatus of claim 24, wherein the payload information is based on at least one of the number of subbands or subband ranges, the number of ports or port ranges, or a rank or a group of rank.

26. The apparatus of claim 24, wherein the payload information is based on a predetermined number of subbands and the number of subbands configured for the UE.

27. The apparatus of claim 24, wherein the payload information is based on a predetermined number of ports and the number of ports configured for the UE.

28. The apparatus of claim 24, wherein the payload information identifies at least one parameter, wherein the UE determines the maximum payload of the CSI report generated by the ML model indicated by the identifier based on the at least one parameter.

29. The apparatus of claim 28, wherein the at least one parameter includes at least one of the following: the total dimension of the CSI feature representation of the CSI report output by one or more ML encoders of the UE, the codeword length of a subset of the values ​​of the CSI feature representation, or the number of bits of the subset of the values ​​of the CSI feature representation.

30. The apparatus of claim 18, wherein the CSI feature representation output by the ML-based encoder of the UE includes information identifying the number of non-zero coefficients and the location of the number of non-zero coefficients.

31. The apparatus of claim 18, wherein the CSI feature representation output by the ML-based encoder of the UE includes an index identifying the position of each of the plurality of non-zero coefficients in the CSI feature representation.

32. The apparatus of claim 18, wherein the CSI feature representation output by the ML-based encoder of the UE includes the number of non-zero coefficients in the CSI feature representation, wherein the non-zero coefficients are preceding the zero-value coefficients in the CSI feature representation.

33. The apparatus of claim 32, wherein the number of said non-zero coefficients is reported in a first part of the CSI report, while others related to the potential message are reported in a second part.

34. A method for wireless communication at a network entity, the method comprising: Receive capability information associated with at least one feature group, at least one identifier associated with one or more machine learning (ML) models, and at least one set of channel state information reference signals (CSI-RS) capabilities of the user equipment (UE). as well as Send a CSI report configuration, including the identifier from the at least one identifier, to the UE.

35. An apparatus for wireless communication, the apparatus comprising: At least one memory; and At least one processor, said at least one processor being coupled to at least one memory and configured to: Receive channel state information (CSI) report configuration including an identifier associated with at least one machine learning (ML) model of the device; as well as The maximum payload of one or more CSI reports generated using the ML model is determined based on the CSI report configuration.

Images