Variable configuration of artificial intelligence channel state feedback with common backbone and multi-branch front and back ends

Abstract

Apparatuses, methods, and computer-readable media are disclosed for providing a generic structure for supporting various configurations, such as various antenna configurations and subband configurations. For example, a process may include receiving a channel state information (CSI) reporting configuration, the channel state information (CSI) reporting configuration including at least one of a CSI reporting subband mode configuration, an antenna configuration, a limit of a possible rank to report, or a payload configuration. The process may include determining, based on the CSI reporting configuration, a CSI reporting dimension associated with an output of a machine learning model used by the user equipment to generate a CSI report. The process may also include generating the CSI report using the machine learning model based on the CSI report dimension.

Description

Technical Field

[0001] The present disclosure as a whole relates to machine learning (ML) systems for wireless communications. For example, aspects of the present disclosure relate to systems and techniques for providing a general structure for supporting various configurations such as various antenna configurations and subband configurations. The general structure may include a machine learning-based encoder deployed on a user equipment (UE) and a machine learning-based decoder deployed at a network device or node (e.g., a base station such as a gNodeB (gNB) or a portion thereof), and the encoder and the decoder include a front-end multi-branch layer and a back-end multi-branch layer for processing various configurations. Background Art

[0002] Wireless communication systems are deployed to provide a variety of telecommunication and data services including telephone, video, data, messaging, and broadcasting. Broadband wireless communication systems have evolved over several generations, including first generation analog wireless telephone service (1G), second generation (2G) digital wireless telephone service (including transitional 2.5G networks), third generation (3G) high-speed data wireless devices with Internet capabilities, and fourth generation (4G) services (e.g., Long Term Evolution (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, global system for mobile communications (GSM) systems, and the like. Other wireless communication technologies include 802.11 Wi-Fi, Bluetooth, and the like.

[0003] The fifth generation (5G) mobile standard calls for higher data transfer speeds, a greater number of connections, and better coverage, among other improvements. According to the Next Generation Mobile Network Alliance, the 5G standard (also known as "new radio" or "NR") is designed to provide data rates of tens of megabits per second to each of tens of thousands of users, and 1 gigabit per second to dozens of employees on an office floor. To support large sensor deployments, hundreds of thousands of simultaneous connections should be supported. Algorithms based on artificial intelligence (AI) and ML can be incorporated into 5G and future standards to improve telecommunications and data services. Summary of the invention

[0004] The following presents a simplified summary of the invention related to one or more aspects disclosed herein. Therefore, the following summary of the invention should neither be considered as an exhaustive overview related to all conceived aspects, nor should it be considered to identify key or decisive elements related to all conceived aspects or to delineate the scope associated with any particular aspect. Accordingly, the following summary of the invention presents certain concepts related to one or more aspects of the mechanisms disclosed herein in a simplified form before the detailed embodiments presented below.

[0005] Systems and techniques are described herein for training a machine learning model that includes a front-end multi-branch layer that receives an antenna setting or antenna setting group and determines a selected branch among a plurality of branches in the front-end multi-branch layer for performing a linear embedding or transformation of an input from a first domain, such as a transmit domain, to a second domain, such as a feature domain, to generate a first output. The model can be deployed as an encoder on a UE or a decoder on a network device or node (e.g., a base station, such as a gNodeB (gNB) or a portion thereof).

[0006] The common backbone of the machine learning model may receive the first output and extract deep features with position encoding to generate a second output, and a back-end multi-branch layer of the machine learning model uses selected branches based on one or more of a subband configuration, a rank, an antenna configuration (which may include the antenna setting or the antenna setting group), or a payload configuration. The selected branches compress the second output to generate a potential message having dimensions for transmission to a receiving device, such as a base station or gNB.

[0007] In an illustrative example, a device for wireless communication is provided, the device comprising: at least one memory storing instructions for operating a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration. The device also includes at least one processor coupled to the at least one memory and configured to: obtain an input of a front-end multi-branch layer of the machine learning model; process the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through a common trunk of the machine learning model to produce a second output; provide the second output to a back-end multi-branch layer of the machine learning model; and process the second output via a selected branch of a plurality of branches in the back-end multi-branch layer to generate a potential message having a dimension.

[0008] In another illustrative example, a method for wireless communication is provided, the method comprising: obtaining an input of a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; processing the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; processing the first output through a common trunk of the machine learning model to produce a second output; providing the second output to a back-end multi-branch layer of the machine learning model; and processing the second output via a selected branch among a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension.

[0009] In another illustrative example, a non-transitory computer-readable medium having instructions is provided that, when executed by one or more processors, causes the one or more processors to: obtain an input to a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; process the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through a common trunk of the machine learning model to produce a second output; provide the second output to a back-end multi-branch layer of the machine learning model; and process the second output via a selected branch among a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension.

[0010] In another illustrative example, an apparatus for wireless communication is provided, the apparatus comprising: a component for obtaining an input of a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; a component for processing the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; a component for processing the first output through a common trunk of the machine learning model to produce a second output; a component for providing the second output to a back-end multi-branch layer of the machine learning model; and a component for processing the second output via a selected branch among a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension.

[0011] In another illustrative example, a device for wireless communication is provided, the device comprising: a machine learning model, the machine learning model is trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; a front-end multi-branch layer of the machine learning model; a common backbone of the machine learning model; a back-end multi-branch layer of the machine learning model; at least one memory, the at least one memory storing instructions for operating the machine learning model; and at least one processor coupled to the at least one memory. The at least one processor is configured to: receive an input of the front-end multi-branch layer of the machine learning model; process the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through the common backbone of the machine learning model to produce a second output; provide the second output to the back-end multi-branch layer of the machine learning model; process the second output via a selected branch of a plurality of branches in the back-end multi-branch layer to generate a potential message having a dimension; and send the potential message having the dimension to a communication device via a wireless interface.

[0012] In another illustrative example, a method for wireless communication is provided, the method comprising: receiving an input of a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; processing the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; processing the first output through the common trunk of the machine learning model to produce a second output; providing the second output to a back-end multi-branch layer of the machine learning model; processing the second output via a selected branch among a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension; and sending the potential message having the dimension to a communication device via a wireless interface.

[0013] In another illustrative example, a non-transitory computer-readable medium having instructions is provided that, when executed by one or more processors, causes the one or more processors to: receive an input of a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; process the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through the common trunk of the machine learning model to produce a second output; provide the second output to a back-end multi-branch layer of the machine learning model; process the second output via a selected branch among a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension; and send the potential message having the dimension to a communication device via a wireless interface.

[0014] In another illustrative example, an apparatus for wireless communication is provided, the apparatus comprising: a component for receiving an input of a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; a component for processing the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; a component for processing the first output through the common trunk of the machine learning model to produce a second output; a component for providing the second output to a back-end multi-branch layer of the machine learning model; a component for processing the second output via a selected branch among a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension; and a component for sending the potential message having the dimension to a communication device via a wireless interface.

[0015] In another illustrative example, an apparatus for wireless communication is provided, the apparatus comprising at least one memory and at least one processor, the at least one processor being coupled to the at least one memory and configured to: receive a channel state information (CSI) report configuration, the channel state information (CSI) report configuration comprising at least one of a CSI report subband mode configuration, an antenna configuration, a restriction on possible ranks to be reported, or a payload configuration; determine a CSI report dimension associated with an output of a machine learning model used by a user equipment to generate a CSI report based on the CSI report configuration; and generate the CSI report using the machine learning model based on the CSI report dimension.

[0016] In another illustrative example, a method for wireless communication is provided, the method comprising: receiving a channel state information (CSI) reporting configuration, the channel state information (CSI) reporting configuration comprising at least one of a CSI reporting subband mode configuration, an antenna configuration, a restriction on possible ranks to be reported, or a payload configuration; determining a CSI reporting dimension associated with an output of a machine learning model used by a user equipment to generate a CSI report based on the CSI reporting configuration; and generating the CSI report using the machine learning model based on the CSI reporting dimension.

[0017] In another illustrative example, a non-transitory computer-readable medium having instructions is provided that, when executed by one or more processors, causes the one or more processors to: receive a channel state information (CSI) report configuration, the channel state information (CSI) report configuration comprising at least one of a CSI report subband mode configuration, an antenna configuration, a restriction on possible ranks to be reported, or a payload configuration; determine, based on the CSI report configuration, a CSI report dimension associated with an output of a machine learning model used by a user equipment to generate a CSI report; and generate the CSI report using the machine learning model based on the CSI report dimension.

[0018] In another illustrative example, an apparatus for wireless communication is provided, the apparatus comprising: a component for receiving a channel state information (CSI) report configuration, the channel state information (CSI) report configuration comprising at least one of a CSI report subband mode configuration, an antenna configuration, a restriction on possible ranks to be reported, or a payload configuration; a component for determining, based on the CSI report configuration, a CSI report dimension associated with an output of a machine learning model used by a user equipment to generate a CSI report; and a component for generating the CSI report using the machine learning model based on the CSI report dimension.

[0019] In another illustrative example, a device for wireless communication is provided, the device comprising: at least one memory storing instructions for operating a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration. The device also includes at least one processor coupled to the at least one memory and configured to: obtain an input of a front-end multi-branch layer of the machine learning model; process the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through a common trunk of the machine learning model to produce a second output; and generate a potential message having a dimension based on the second output.

[0020] In another illustrative example, a method for wireless communication is provided, the method comprising: obtaining an input of a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; processing the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; processing the first output through a common trunk of the machine learning model to produce a second output; and generating a potential message having a dimension based on the second output.

[0021] In another illustrative example, a non-transitory computer-readable medium having instructions is provided that, when executed by one or more processors, causes the one or more processors to: obtain an input to a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; process the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through a common backbone of the machine learning model to produce a second output; and generate a potential message having a dimension based on the second output.

[0022] In another illustrative example, an apparatus for wireless communication is provided, the apparatus comprising: a component for obtaining an input of a front-end multi-branch layer of a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; a component for processing the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; a component for processing the first output through a common backbone of the machine learning model to produce a second output; and a component for generating a potential message having a dimension based on the second output.

[0023] In another illustrative example, a device for wireless communication is provided, the device comprising: at least one memory storing instructions for operating a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration. The device also includes at least one processor coupled to the at least one memory and configured to: process an input of a common backbone of the machine learning model to produce an output; provide the output to a back-end multi-branch layer of the machine learning model; process the output via a selected branch of a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension.

[0024] In another illustrative example, a method for wireless communication is provided, the method comprising: processing an input of a common backbone of a machine learning model to produce an output, wherein the machine learning model is trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; providing the output to a backend multi-branch layer of the machine learning model; and processing the output via a selected branch of a plurality of branches of the backend multi-branch layer to generate a potential message having a dimension.

[0025] In another illustrative example, a non-transitory computer-readable medium having instructions is provided that, when executed by one or more processors, causes the one or more processors to: process an input to a common backbone of a machine learning model to produce an output, wherein the machine learning model is trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; provide the output to a backend multi-branch layer of the machine learning model; and process the output via a selected branch of a plurality of branches of the backend multi-branch layer to generate a potential message having a dimension.

[0026] In another illustrative example, an apparatus for wireless communication is provided, the apparatus comprising: a component for processing an input of a common backbone of a machine learning model to produce an output, wherein the machine learning model is trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; a component for providing the output to a back-end multi-branch layer of the machine learning model; and a component for processing the output via a selected branch of a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension.

[0027] A non-transitory computer-readable storage medium includes instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to any one of the processes, methods, or operations disclosed herein.

[0028] An apparatus for wireless communication, the apparatus comprising one or more components for performing operations according to any of the processes, methods, or operations disclosed herein.

[0029] 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 and as illustrated by the accompanying drawings and description.

[0030] The features and technical advantages of examples according to the present disclosure have been outlined quite extensively above so that the following specific embodiments may be better understood. Additional features and advantages will be described below. The disclosed concepts and specific examples may be easily used as a basis for modifying or designing other structures for achieving the same purpose of the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, both in terms of their organization and method of operation, and the associated advantages will be better understood by considering the following description in conjunction with the accompanying drawings. Each of the figures in the accompanying drawings is provided for the purpose of illustration and description, and not as a definition of limitations to the claims.

[0031] Although various aspects are described in the present disclosure by illustrating some examples, it will be understood by those skilled in the art that such aspects can be implemented in many different arrangements and scenarios. The technology described herein can be implemented using different platform types, devices, systems, shapes, sizes and / or packaging arrangements. For example, some aspects can be implemented via integrated chip implementations or other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / shopping equipment, medical equipment and / or artificial intelligence devices). Various 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. The equipment incorporating the various aspects and features described may include additional components and features for implementing and practicing the various aspects claimed and described. 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 various aspects described herein are intended to be practiced in various devices, components, systems, distributed arrangements and / or end-user devices of various sizes, shapes and configurations.

[0032] Other objects and advantages associated with the various aspects disclosed herein will be apparent to those skilled in the art based on the drawings and detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Examples of various specific implementations are described in detail below with reference to the following drawings:

[0034] Figure 1 is a block diagram illustrating an example of a wireless communication network according to some examples;

[0035] Figure 2 is a diagram illustrating a design of a base station and a user equipment (UE) device according to some examples, which enables sending and processing of signals exchanged between the UE and the base station;

[0036] Figure 3 is a diagram illustrating an example of a decomposed base station according to some examples;

[0037] Figure 4 is a block diagram illustrating components of user equipment according to some examples;

[0038] Figure 5 illustrates an example architecture of a neural network that may be used in accordance with some aspects of the present disclosure;

[0039] Figure 6 is a block diagram illustrating an ML engine according to aspects of the present disclosure;

[0040] Fig. 7A illustrates a block diagram showing an encoder encoding an input to generate a potential message sent to a decoder at a gNB, the decoder generating an output based on the potential message, in accordance with aspects of the present disclosure;

[0041] Figure 7B illustrates a block diagram associated with an encoder on a user equipment having a common backbone and front-end and back-end multi-branch layers for generating a latent message having dimensions in accordance with aspects of the present disclosure;

[0042] Figure 7C illustrates a block diagram associated with a decoder on a gNB having a common backbone and a front-end multi-branch layer and a back-end multi-branch layer for receiving and decompressing a potential message having dimensions in accordance with aspects of the present disclosure;

[0043] FIG. 8A to FIG. 8B illustrates flowcharts associated with different aspects of a machine learning model having a common backbone and front-end and back-end multi-branch layers according to aspects of the present disclosure; and

[0044] Fig. 9 is a diagram illustrating an example of a system for implementing certain aspects of the present technology. DETAILED DESCRIPTION

[0045] Some aspects and embodiments of the present disclosure are provided below. Some of these aspects and embodiments can be applied independently, and some of them can be applied in combination, which is obvious to those skilled in the art. In the following description, specific details are set forth for explanation purposes in order to provide a thorough understanding of each embodiment of the application. However, it will be apparent that each embodiment can be put into practice without these specific details. Each drawing and description are not intended to be restrictive.

[0046] The following description only provides example embodiments, and is not intended to limit the scope, applicability or configuration of the present disclosure. On the contrary, the following description of the exemplary embodiments will provide an enabling description for realizing the exemplary embodiments to those skilled in the art. It should be understood that various changes can be made to the function and arrangement of elements without departing from the essence and scope of the present application as set forth in the appended claims.

[0047] Various techniques are provided with reference to wireless technologies (e.g., third generation partnership project (3GPP) 5G / new radio (NR) standards) to provide improvements to wireless communications. The present disclosure focuses on a machine learning model that can be implemented as an encoder on a UE and a decoder on a network device, and the encoder and the decoder include a front-end multi-branch layer and a back-end multi-branch layer that enable the machine learning model to support a variable antenna configuration, a variable subband configuration, or a variable rank or a variable payload configuration.

[0048] Additional aspects of the disclosure are described in more detail below with reference to the accompanying drawings.

[0049] Wireless networks are deployed to provide various communication services, such as voice, video, packet data, messaging, broadcast, etc. Wireless networks may support access links for communication between wireless devices. An access link may refer to any communication link between a client device (e.g., user equipment (UE), station (STA), or other client device) and a base station (e.g., 3GPP gNodeB (gNB) for 5G / NR, 3GPP eNodeB (eNB) for LTE, Wi-Fi access point (AP), or other base station) or a decomposed base station (e.g., a central unit, a distributed unit, and / or a radio unit). In one example, the access link between the UE and the 3GPP gNB may be through the Uu interface. In some cases, the access link may support uplink signaling, downlink signaling, connection procedures, etc.

[0050] In some aspects, the wireless communication network may be implemented using one or more modulation schemes. For example, the wireless communication network may be implemented using a quadrature amplitude modulation (QAM) scheme such as 16QAM, 32QAM, 64QAM, etc.

[0051] As used herein, the terms "user equipment" (UE) and "network entity" are not intended to be dedicated 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., a mobile phone, a router, a tablet computer, a laptop computer, and / or a tracking device, etc.), a wearable device (e.g., a smart watch, smart glasses, a wearable ring, and / or an extended reality (XR) device (such as a virtual reality (VR) headset, an augmented reality (AR) headset or glasses, or a mixed reality (MR) headset)), a vehicle (e.g., a car, a motorcycle, a bicycle, etc.), and / or an Internet of Things (IoT) device, etc., for a user to communicate on a wireless communication network. A UE can be mobile or can be stationary (e.g., at certain times) and can communicate with a radio access network (RAN). As used herein, the term "UE" may be interchangeably referred to as an "access terminal" or "AT," "client device," "wireless device," "subscriber equipment," "subscriber terminal," "subscriber station," "user terminal" or "UT," "mobile device," "mobile terminal," "mobile station," or variations thereof. Generally speaking, a UE may communicate with a core network via a RAN, and through the core network, the UE may connect to external networks such as the Internet and to 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 a wired access network, a wireless local area network (WLAN) network (e.g., based on IEEE 802.11 communication standards, etc.), and the like.

[0052] The network entity may be implemented in a converged or monolithic base station architecture, or alternatively, in a disaggregated 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 base station architecture or a disaggregated base station architecture) may operate in communication with a UE according to one of several RATs depending on the network in which the base station is deployed, and may alternatively be referred to as an access point (AP), a network node, a NodeB (NB), an evolved NodeB (eNB), a next generation eNB (ng-eNB), a new radio (NR) NodeB (also referred to as a gNB or gNodeB), etc. A base station may be primarily used to support wireless access for UEs, including supporting data, voice, and / or signaling connections for the supported UEs. In some systems, a base station may provide edge node signaling functionality, while in other systems, a base station may provide additional control and / or network management functionality. The communication link through which the UE can transmit signals to the base station can be called an uplink (UL) channel (e.g., a reverse traffic channel, a reverse control channel, an access channel, etc.). The communication link through which the base station can transmit signals to the UE can be called a downlink (DL) or forward link channel (e.g., a paging channel, a control channel, a broadcast channel, or a forward traffic channel, etc.). As used herein, the term traffic channel (TCH) can refer to an uplink, a reverse or downlink, and / or a forward traffic channel.

[0053] The term "network entity" or "base station" (e.g., having an aggregated / monolithic base station architecture or a decomposed base station architecture) may refer to a single physical transmit receive point (TRP) or multiple physical TRPs that may or may not be co-located. For example, where 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. Where 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). Where the term "base station" refers to multiple non-co-located physical TRPs, the physical TRP may be a distributed antenna system (DAS) (a network of spatially separated antennas connected to a common source via a transmission medium) or a remote radio head (RRH) (a remote base station connected to a serving base station). Alternatively, the non-co-located physical TRPs may be a serving base station that receives measurement reports from a UE and a neighboring base station whose reference radio frequency (RF) signal (or "reference signal" for short) the UE is measuring. Because, as used herein, a TRP is the point through which a base station transmits and receives wireless signals, references to transmitting from or receiving at a base station should be understood to refer to the specific TRP of a base station.

[0054] In some specific implementations of supporting UE positioning, a network entity or base station may not support wireless access by the UE (e.g., may not support data, voice, and / or signaling connections with respect to the UE), but may instead send a reference signal to be measured by the UE to the UE, and / or may receive and measure a signal sent by the UE. Such a base station may be referred to as a positioning beacon (e.g., in the case of sending a signal to the UE) and / or as a position measurement unit (e.g., in the case of receiving and measuring a signal from the UE).

[0055] RF signals include electromagnetic waves of a given frequency that transmit information through the space between a transmitter and a receiver. As used herein, a transmitter may transmit 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 a transmitter and a receiver may be referred to as a "multipath" RF signal. As used herein, an RF signal may also be referred to as a "wireless signal" or simply a "signal" where it is clear from the context that the term "signal" refers to a wireless signal or an RF signal.

[0056] Various aspects of the systems and techniques described herein are discussed below with respect to the accompanying drawings. According to various 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, the base station 102 may also be referred to as a "network entity" or a "network node". One or more of the base stations 102 may be implemented in an aggregated or monolithic base station architecture. Additionally or alternatively, one or more of the base stations 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. The base station 102 may include a macro cell base station (a high-power cellular base station) and / or a small cell base station (a low-power cellular base station). In one aspect, the macro cell base station may include an eNB and / or an ng-eNB (where the wireless communication system 100 corresponds to a long-term evolution (LTE) network), or a gNB (where the wireless communication system 100 corresponds to an NR network), or a combination of both, and the small cell base station may include a femto cell, a pico cell, a micro cell, etc.

[0057] The base stations 102 may collectively form a RAN and interface with a core network 170 (e.g., an evolved packet core (EPC) or a 5G core (5GC)) through a backhaul link 122, and interface to one or more location servers 172 (which may be part of the core network 170 or may be external to the core network 170) through the core network 170. Among other functions, the base stations 102 may 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, positioning, and delivery of warning messages. The base stations 102 may communicate with each other directly or indirectly (e.g., through the EPC or 5GC) through a backhaul link 134 (which may be wired and / or wireless).

[0058] Base station 102 can communicate wirelessly with UE 104. Each of base stations 102 can provide communication coverage for a corresponding geographic 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 certain frequency resource, referred to as a carrier frequency, component carrier, carrier, frequency band, etc.), and can be associated with an identifier (e.g., a physical cell identifier (PCI), a virtual cell identifier (VCI), a 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 (e.g., machine type communication (MTC), narrowband IoT (NB-IoT), enhanced mobile broadband (eMBB) or other protocol types) that can provide access to different types of UEs. 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 it, depending on the context. In addition, since a TRP is typically a physical transmission point of a cell, the terms "cell" and "TRP" can be used interchangeably. In some cases, the term "cell" may also refer to a geographic coverage area (eg, a sector) of a base station, as long as a carrier frequency can be detected within some portion of the geographic coverage area 110 and is used for communications within that portion.

[0059] Although the geographic coverage areas 110 of neighboring macrocell base stations 102 may partially overlap (e.g., in a handover area), some of the geographic coverage areas 110 may substantially overlap with the larger geographic coverage area 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 macrocell base stations 102. A network that includes both small cell base stations and macrocell base stations may be referred to as a heterogeneous network. A heterogeneous network may also include a home eNB (HeNB), which may provide services to a restricted group called a closed subscriber group (CSG).

[0060] The communication link 120 between the base station 102 and the UE 104 may include uplink (also known as reverse link) transmissions from the UE 104 to the base station 102 and / or downlink (also known as forward link) transmissions from the base station 102 to the UE 104. The communication link 120 may use MIMO antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link 120 may be over one or more carrier frequencies. The allocation of carriers may be asymmetric for the downlink and uplink (e.g., more or fewer carriers may be allocated to the downlink than to the uplink).

[0061] The wireless communication system 100 may further include a WLAN AP 150 in communication with a WLAN station (STA) 152 via a communication link 154 in an unlicensed spectrum (e.g., 5 gigahertz (GHz)). When communicating in the unlicensed spectrum, the WLAN STA 152 and / or the WLAN AP 150 may perform a clear channel assessment (CCA) or a listen-before-talk (LBT) procedure before communicating to determine whether a channel is available. In some examples, the wireless communication system 100 may include a device (e.g., UE, etc.) that communicates with one or more UEs 104, base stations 102, APs 150, etc. using an ultra-wideband (UWB) spectrum. The UWB spectrum may range from 3.1 GHz to 10.5 GHz.

[0062] The small cell base station 102' can operate in licensed and / or unlicensed spectrum. When operating in the unlicensed spectrum, the small cell base station 102' can adopt LTE or NR technology and use the same 5GHz unlicensed spectrum used by the WLAN AP 150. The small cell base station 102' using LTE and / or 5G in the unlicensed spectrum can boost the coverage of the access network and / or increase the capacity of the access network. NR in the unlicensed spectrum can be referred to as NR-U. LTE in the unlicensed spectrum can be referred to as LTE-U, Licensed Assisted Access (LAA) or MulteFire.

[0063] The wireless communication system 100 may also include a millimeter wave (mmW) base station 180, which may operate at mmW frequencies and / or near mmW frequencies to communicate with UE 182. The mmW base station 180 may be implemented in an aggregated or monolithic base station architecture, or alternatively, in a decomposed base station architecture (e.g., including one or more of CU, DU, RU, near RT RIC, or non-RT RIC). Extremely high frequency (EHF) is part of the RF in the electromagnetic spectrum. EHF has a range of 30 GHz to 300 GHz, with a wavelength between 1 mm and 10 mm. The radio waves in this band may be referred to as millimeter waves. Near mmW may extend down to a frequency of 3 GHz, with a wavelength of 100 mm. The super high frequency (SHF) band extends between 3 GHz and 30 GHz, which is also referred to as centimeter waves. Communications using mmW and / or near mmW radio frequency bands have high path loss and relatively short range. The mmW base station 180 and the UE 182 may utilize beamforming (transmit and / or receive) on the mmW communication link 184 to compensate for the extremely high path loss and short range. In addition, it should be understood that in alternative configurations, one or more base stations 102 may also transmit using mmW or near-mmW and beamforming. Therefore, it should be understood that the foregoing illustrations are merely examples and should not be construed as limiting the various aspects disclosed herein.

[0064] In some aspects related to 5G, the spectrum in which a wireless network node or entity (e.g., base station 102 / 180, UE 104 / 182) operates is divided into multiple frequency ranges: FR1 (from 450 megahertz (MHz) to 6000 MHz), FR2 (from 24250 MHz to 52600 MHz), FR3 (above 52600 MHz), and FR4 (between FR1 and FR2). In a multi-carrier system (such as 5G), one of the carrier frequencies is referred to as a "primary carrier" or "anchor carrier" or "primary serving cell" or "PCell", and the remaining carrier frequencies are referred to as "secondary carriers" or "secondary serving cells" or "SCells". In carrier aggregation, the anchor carrier is a carrier operating on the primary frequency (e.g., FR1) used by the UE 104 / 182 and the cell in which the UE 104 / 182 performs an initial radio resource control (RRC) connection establishment procedure or initiates an RRC connection re-establishment procedure. The primary carrier carries all common control channels as well as UE-specific control channels and can be a carrier in a licensed frequency (however, this is not always the case). A secondary carrier is a carrier operating on a second frequency (e.g., FR2), which can be configured and used to provide additional radio resources once an RRC connection is established between the UE 104 and the anchor carrier. In some cases, the secondary carrier may be a carrier in an unlicensed frequency. The secondary carrier may contain only necessary signaling information and signals, for example, since the primary uplink carrier and the primary downlink carrier are typically UE-specific, those signaling information and signals specific to the UE may not be present in the secondary carrier. This means that different UEs 104 / 182 in a cell may have different downlink primary carriers. This also holds true for the uplink primary carrier. The network is able to 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 a carrier frequency and / or component carrier through which some base stations are communicating, the terms "cell", "serving cell", "component carrier", "carrier frequency", etc. may be used interchangeably.

[0065] For example, still refer to Figure 1, one of the frequencies used by the macrocell base station 102 may be an anchor carrier (or "PCell"), and the other frequencies used by the macrocell base station 102 and / or the mmW base station 180 may be secondary carriers ("SCells"). In carrier aggregation, the base station 102 and / or the UE 104 may use a spectrum of up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz) bandwidth per carrier, with up to a total of Yx MHz (x component carriers) in each direction for transmission. The component carriers may be adjacent to each other or may not be adjacent to each other in the spectrum. The allocation of carriers may be asymmetric with respect to the downlink and uplink (e.g., more or fewer carriers may be allocated to the downlink compared to the uplink). The simultaneous transmission and / or reception of multiple carriers enables the UE 104 / 182 to significantly increase its data transmission and / or reception rate. For example, two 20 MHz aggregated 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 with a single 20 MHz carrier.

[0066] In order to operate on multiple carrier frequencies, the base station 102 and / or the UE 104 may be equipped with multiple receivers and / or transmitters. For example, the 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 the UE 104 is being served in band "X", the band "X" will be referred to as the PCell or active carrier frequency, and "receiver 1" may need to tune from band "X" to band "Y" (SCell) to measure band "Y" (and vice versa). In contrast, regardless of whether the UE 104 is being served in band "X" or band "Y", due to the separate "receiver 2", the UE 104 can measure band "Z" without interrupting the service on band "X" or band "Y".

[0067] The wireless communication system 100 may further include a UE 164, which may communicate with the macrocell base station 102 over the communication link 120 and / or communicate with the mmW base station 180 over the mmW communication link 184. For example, the macrocell base station 102 may support a PCell 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.

[0068] 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 of FIG. 1 , UE 190 has a D2D P2P link 192 with one of UEs 104 connected to one of base stations 102 (e.g., UE 190 can indirectly obtain cellular connectivity through the D2D P2P link), and has a D2D P2P link 194 with WLAN STA 152 connected to WLAN AP 150 (UE 190 can indirectly obtain WLAN-based Internet connectivity through the D2D P2P link). In an example, D2D P2P links 192 and 194 can use any well-known D2D RAT (such as LTE Direct (LTE-D), WiFi Direct (WiFi-D), etc.) to support.

[0069] Figure 2 A block diagram of a design of a base station 102 and a UE 104 is shown that enables sending and processing of signals exchanged between the UE and the base station according to some aspects of the present disclosure. Design 200 includes components of the base station 102 and the UE 104, which may be Figure 1 1. A base station in base station 102 and a UE in UE 104. Base station 102 may be equipped with T antennas 234a through 234t, and UE 104 may be equipped with R antennas 252a through 252r, where in general T≥1 and R≥1.

[0070] At the base station 102, the transmit processor 220 may receive data for one or more UEs from the data source 212, select one or more modulation and coding schemes (MCS) for each UE based at least in part on a channel quality indicator (CQI) received from the UE, process (e.g., encode and modulate) the data for the UE based at least in part on the MCS selected for each UE, and provide data symbols for all UEs. The transmit processor 220 may also process system information (e.g., for semi-static resource partitioning 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. The transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS)) and synchronization signals (e.g., primary synchronization signals (PSS) and secondary synchronization signals (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., pre-decoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols where applicable, and may provide T output symbol streams to T modulators (MOD) 232a to 232t. The modulators 232a to 232t are shown as combined modulator-demodulators (MOD-DEMOD). In some cases, the modulator and demodulator may be separate components. Each modulator in the modulators 232a to 232t may 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 the modulators 232a to 232t may 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 may be sent from the modulators 232a to 232t via T antennas 234a to 234t, respectively. According to certain aspects described in greater detail below, position encoding may be utilized to generate a synchronization signal to convey additional information.

[0071] At UE 104, antennas 252a to 252r may receive downlink signals from base station 102 and / or other base stations, and may provide received signals to demodulators (DEMOD) 254a to 254r, respectively. Demodulators 254a to 254r are shown as combined modulator-demodulators (MOD-DEMOD). In some cases, the modulator and demodulator may be separate components. Each demodulator in demodulators 254a to 254r may condition (e.g., filter, amplify, downconvert, and digitize) received signals to obtain input samples. Each demodulator in demodulators 254a to 254r may further process input samples (e.g., for OFDM, etc.) to obtain received symbols. MIMO detector 256 may obtain received symbols from all R demodulators 254a to 254r, perform MIMO detection (if applicable) on the received symbols, and provide detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, provide decoded data for the UE 104 to a data sink 260, and provide decoded control information and system information to a controller / processor 280. The channel processor may determine a reference signal received power (RSRP), a received signal strength indicator (RSSI), a reference signal received quality (RSRQ), a channel quality indicator (CQI), etc.

[0072] On the uplink, at the UE 104, a transmit processor 264 may receive and process data from a data source 262 and control information from a controller / processor 280 (e.g., for reports including RSRP, RSSI, RSRQ, CQI, channel state information, channel state feedback, etc.). The transmit processor 264 may also generate reference symbols for one or more reference signals (e.g., based at least in part on a beta value or set of beta values ​​associated with the one or more reference signals). The symbols from the transmit processor 264 may be pre-decoded by the TX MIMO processor 266, if applicable, further processed by the modulators 254a through 254r (e.g., for DFT-s-OFDM, CP-OFDM, etc.), and transmitted to the base station 102. At the base station 102, uplink signals from the UE 104 and other UEs may be received by antennas 234a to 234t, processed by demodulators 232a to 232t, detected by a MIMO detector 236 where applicable, and further processed by a receive processor 238 to obtain decoded data and control information transmitted by the UE 104. The receive processor 238 may provide the decoded data to a data sink 239 and the decoded control information to a controller (processor) 240. The base station 102 may include a communication unit 244 and communicate with the network controller 231 via the communication unit 244. The network controller 231 may include a communication unit 294, a controller / processor 290, and a memory 292.

[0073] In some aspects, one or more components of the UE 104 may be included in a housing. The controller 240 of the base station 102, the controller / processor 280 of the UE 104, and / or Figure 2 Any other component of may perform one or more techniques associated with implicit UCI β value determination for NR.

[0074] Memories 242 and 282 may store data and program codes for base station 102 and UE 104, respectively. A scheduler 246 may schedule UEs for data transmission on the downlink, uplink, and / or sidelink.

[0075] In some aspects, the deployment of a communication system such as a 5G / new radio (NR) system can be arranged with various components or constituent parts in a variety of ways. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element, or a network equipment (such as a base station (BS), or one or more units (or one or more components) that perform base station functionality) can be implemented in an aggregated or decomposed architecture. For example, a BS (such as a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmit receive point (TRP), or a cell, etc.) can be implemented as an aggregated base station (also referred to as a standalone BS or a monolithic BS) or a decomposed base station.

[0076] A converged base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. A decomposed base station may be configured to utilize a protocol stack physically or logically distributed between 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 aspects, a CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. A DU may be implemented to communicate with one or more RUs. Each of a CU, a DU, and a RU may also be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0077] Base station type operations or network designs may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configurations such as those initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Individual units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0078] Figure 3A diagram illustrating an example decomposed base station 300 architecture is shown. The decomposed base station 300 architecture may include one or more central units (CUs) 310 that may communicate directly with a core network 320 via a backhaul link, or indirectly with the core network 320 through 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. The CU 310 may communicate with one or more distributed units (DUs) 330 via respective midhaul links, such as an F1 interface. The DU 330 may communicate with one or more radio units (RUs) 340 via respective fronthaul links. The RU 340 may communicate with respective UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served simultaneously by multiple RUs 340.

[0079] Each of the units (e.g., CU 310, DU 330, RU 340, and near-RT RIC 325, non-RT RIC 315, and SMO framework 305) may include one or more interfaces or be coupled to one or more interfaces that are configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of these units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface that is configured to receive a signal or send a signal to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) that is configured to receive a signal or send a signal to one or more of the other units via a wireless transmission medium, or both.

[0080] In some aspects, CU 310 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented with an interface configured to communicate signals with other control functions hosted by CU 310. CU 310 may 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, CU 310 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface such as an E1 interface. As needed, CU 310 may be implemented to communicate with DU 330 for network control and signaling.

[0081] DU 330 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RU 340. In some aspects, DU 330 may host one or more of a radio link control (RLC) layer, a medium 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.) at least in part according to a functional split such as that defined by the Third Generation Partnership Project (3GPP). In some aspects, DU 330 may further host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 330 or with control functions hosted by CU 310.

[0082] The lower layer functionality may be implemented by one or more RUs 340. In some deployments, a RU 340 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, etc.), or both, based at least in part on a functional split (such as a lower layer functional split). In such an architecture, the RU 340 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some implementations, real-time and non-real-time aspects of control and user plane communications with the RU 340 may be controlled by the corresponding DU 330. In some scenarios, this configuration may enable the DU 330 and the CU 310 to be implemented in a cloud-based RAN architecture (such as a vRAN architecture).

[0083] The SMO framework 305 may be configured to support RAN deployment and configuration of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 305 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 305 may be configured to interact with a cloud computing platform (such as an 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 an 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 specific implementations, the SMO framework 305 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 311) via the O1 interface. Additionally, in some specific implementations, the SMO framework 305 may communicate directly with one or more RUs 340 via the O1 interface. The SMO framework 305 may also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305 .

[0084] The non-RT RIC 315 may be configured to include logic functions that implement non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 325. The non-RT RIC 315 may be coupled to or communicate with the near-RT RIC 325 (such as via an A1 interface). The near-RT RIC 325 may be configured to include logic functions that implement near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 310, one or more DUs 330, or both, and the O-eNB with the near-RT RIC 325.

[0085] In some implementations, in order to generate an AI / ML model 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. Such information may be utilized by the near-RT RIC 325 and may be received from a non-network data source or from a network function at the SMO framework 305 or the non-RT RIC 315. In some examples, the non-RT RIC 315 or the 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 of performance and employ AI / ML models to perform corrective actions through the SMO framework 305 (such as via reconfiguration of O1) or via the creation of RAN management policies (such as A1 policies).

[0086] Figure 4 An example of a computing system 470 of a wireless device 407 is illustrated. The wireless device 407 may include a client device such as a UE (e.g., UE 104, UE 152, UE 190) or other type of device that can be used by an end user (e.g., a station (STA) configured to communicate using a Wi-Fi interface). For example, the wireless device 407 may include a mobile phone, a router, a tablet computer, a laptop computer, a tracking device, a wearable device (e.g., a smart watch, glasses, an extended reality (XR) device (such as a virtual reality (VR), augmented reality (AR) or mixed reality (MR) device), etc.), an Internet of Things (IoT) device, an access point, and / or another device configured to communicate via a wireless communication network. The computing system 470 includes software and hardware components that can be electrically coupled or communicatively coupled via a bus 489 (or can communicate in other ways, as the case may be). For example, the 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, dedicated hardware, any combination thereof, and / or other processing devices or systems. One or more processors 484 may use a bus 489 to communicate between cores and / or with one or more memory devices 486.

[0087] 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., a camera, a mouse, a keyboard, a touch-sensitive screen, a touchpad, a keypad, a microphone, and / or the like), and one or more output devices 480 (e.g., a display, a speaker, a printer, and / or the like).

[0088] In some aspects, computing system 470 may include one or more RF interfaces configured to send 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 send and receive wireless signals (e.g., signal 488) from one or more other devices via antenna 487, such as other wireless devices, network devices (e.g., base stations such as eNBs and / or gNBs, Wi-Fi access points (APs) such as routers, range extenders, etc.), cloud networks, etc. In some examples, computing system 470 may include multiple antennas or antenna arrays that can facilitate simultaneous transmission and reception functionality. Antenna 487 may be an omnidirectional antenna so that radio frequency (RF) signals can be received from all directions and transmitted in all directions. Wireless signal 488 may be sent via a wireless network. The wireless network may be any wireless network, such as a cellular or telecommunications network (e.g., 3G, 4G, 5G, etc.), a wireless local area network (e.g., a WiFi network), a Bluetooth TM network and / or other networks.

[0089] In some examples, wireless signals 488 may be transmitted directly to other wireless devices using sidelink communications (e.g., using a PC5 interface, using a DSRC interface, etc.). Wireless transceiver 478 may be configured to transmit RF signals via antenna 487 for performing sidelink communications according to one or more transmit power parameters that may be associated with one or more regulatory modes. Wireless transceiver 478 may also be configured to receive sidelink communication signals having different signal parameters from other wireless devices.

[0090] In some examples, one or more wireless transceivers 478 may include an RF front end that includes one or more components such as an amplifier, a mixer for down-converting a signal (also known as a signal multiplier), a frequency synthesizer (also known as an oscillator) that provides a signal to the mixer, a baseband filter, an analog-to-digital converter (ADC), one or more power amplifiers, and other components. The RF front end may generally handle the selection of wireless signals 488 and the conversion of the wireless signals to baseband frequencies or intermediate frequencies, and may convert the RF signals to the digital domain.

[0091] In some cases, computing system 470 may include a coding-decoding 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 to encrypt and / or decrypt data transmitted and / or received by one or more wireless transceivers 478 (e.g., according to the AES and / or DES standards).

[0092] One or more SIMs 474 may each securely store an International Mobile Subscriber Identity (IMSI) number and associated keys assigned to a user of the wireless device 407. The IMSI and keys may be used to identify and authenticate a subscriber when accessing a network provided by a network service provider or operator associated with the one or more SIMs 474. One or more modems 476 may modulate one or more signals to encode information for transmission using one or more wireless transceivers 478. One or more modems 476 may also demodulate signals received by one or more wireless transceivers 478 in order 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 communicate data of one or more SIMs 474.

[0093] The computing system 470 may also include (and / or be in communication with) one or more non-transitory machine-readable storage media or storage devices (e.g., one or more memory devices 486), which may include, but are not limited to, local and / or network accessible storage, disk drives, drive arrays, optical storage devices, solid-state storage devices such as RAM and / or ROM, which may be programmable, flash-updatable, etc. Such storage devices may be configured to implement any suitable data storage, including, but not limited to, various file systems, database structures, etc.

[0094] In various embodiments, the functionality may be stored as one or more computer program products (e.g., instructions or code) in the memory device 486 and executed by the one or more processors 484 and / or the one or more DSPs 482. The computing system 470 may also include software elements (e.g., located within the one or more memory devices 486) including, for example, an operating system, device drivers, executable libraries, and / or other code, such as one or more applications, which may include computer programs that implement the functionality provided by the various embodiments and / or may be designed to implement methods and / or configure systems, as described herein.

[0095] Figure 5An example architecture of a neural network 500 that may be used according to some aspects of the present disclosure is illustrated. The example architecture of the neural network 500 may be defined by an example neural network description 502 in a neural controller 501. The neural network 500 is an example of a machine learning model that may be deployed and implemented at a base station 102, a central unit (CU) 310, a distributed unit (DU) 330, a radio unit (RU) 340, and / or a UE 104. The neural network 500 may be a feed-forward neural network or any other known or to be developed neural network or machine learning model.

[0096] Neural network description 502 may include a complete specification of neural network 500, including Figure 5 . 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 inputs and outputs are formed or processed; indications of activation functions in the neural network, operations or filters in the neural network, etc.; neural network parameters such as weights, biases, etc.; and the like.

[0097] 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 recursive neural network, which may have a loop that allows information to be carried across nodes when reading input. Neural network 500 may include any other suitable neural network or machine learning model. An example includes a convolutional neural network (CNN), which includes an input layer and an output layer, with multiple hidden layers between the input layer and the output layer. The hidden layers of the 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 recursive neural network (RNN), etc.

[0098] exist Figure 5In a non-limiting example, the neural network 500 includes an input layer 503 that can receive one or more input data sets. The input data can be any type of data (e.g., image data, video data, network parameter data, user data, etc.). The neural network 500 may include hidden layers 504A to 504N (hereinafter collectively referred to as "504"). The hidden layer 504 may include n number of hidden layers, where n is an integer greater than or equal to one. The n number of hidden layers may include as many layers as desired for processing results and / or presentation intent. In an illustrative example, any of the hidden layers 504 may include data representing one or more of the data provided at the input layer 503. The neural network 500 also includes an output layer 506 that provides an output resulting from the processing performed by the hidden layer 504. The output layer 506 may provide output data based on the input data.

[0099] exist Figure 5 In the example of , the neural network 500 is a multi-layer neural network of 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 when processing the information. Information can be exchanged between the nodes through node-to-node interconnections between the layers. The nodes of the input layer 503 can activate a set of nodes in the first hidden layer 504A. For example, as shown in the figure, each input node of the input layer 503 is connected to each node of the first hidden layer 504A. The nodes of the hidden layer 504A can transform the information by applying an activation function to the information of each input node. Then, the information derived from the transformation can be passed to the nodes of the next hidden layer (e.g., 504B) and these nodes can be activated, and these nodes 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 the nodes of the next hidden layer (e.g., 504N), and so on. The output of the last hidden layer can activate one or more nodes of the output layer 506, providing an output at this point. In some cases, although nodes in neural network 500 (e.g., nodes 508A, 508B, 508C) are shown as having multiple output lines, the node can have a single output and all lines shown as output from the node can represent the same output value.

[0100] In some cases, each node or the interconnections between nodes may have a weight that is a set of parameters derived from training neural network 500. For example, an interconnection between nodes may represent a piece of information learned about the interconnected nodes. The interconnections may have numerical weights that may be tuned (e.g., based on a training data set), thereby allowing neural network 500 to adapt to inputs and learn as more data is processed.

[0101] The neural network 500 may be pre-trained to process features of the data from the input layer 503 using different hidden layers 504 in order to provide an output through the output layer 506. For example, in some cases, the neural network 500 may use a training process known as back propagation to adjust the weights of the nodes. Back propagation may include a forward pass, a loss function, a backward pass, and a weight update. The forward pass, loss function, backward pass, and parameter update may be performed for one training iteration. The process may be repeated for each training data set for a certain number of iterations until the weights of the layers are accurately tuned (e.g., to meet a configurable threshold determined based on experiments and / or empirical studies).

[0102] More and more ML (eg, AI) algorithms (eg, models) are being incorporated into a variety of technologies including wireless telecommunications standards. Figure 6 6 is a block diagram illustrating an ML engine 600 that can be trained as part of the framework disclosed herein to provide the ability to support at least one of variable antenna configurations, variable subband configurations, variable rank, and variable payload configurations. 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 be similar to the neural network 500. In this example, the ML engine 600 includes three parts: an input 602 to the ML engine 600, the 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 may use to make predictions or otherwise operate on it, such as making a prediction based on variable data about which branch of a multi-branch front-end layer of the ML engine 600 will be used for linear embedding. As an example, the ML engine 600 configured to determine how to process variable data may receive data about one or more of an antenna configuration of a network entity, a subband configuration from the network entity, a rank or payload configuration, etc. as input 602. In some cases, the output 604 may be a prediction or other information generated by the ML engine 600, and the output 604 may be used to configure the wireless device, select a specific branch for processing data at the front end or back end of the encoder or decoder. Continuing with the previous example, the ML engine 600 configured as described herein may determine, for example, the dimensions of the potential message based on at least one of the antenna configuration of the network entity, the subband configuration from the network entity, the rank, or the payload configuration. Similarly, the ML engine 600 configured as disclosed herein may determine which branch of the back end multi-branch layer to use based on the number of dimensions associated with the potential message or other data provided to the encoder. The potential message may be channel state information (CSI) reporting the payload or CSI compressed as described herein and sent from the UE to the network entity. The process and framework are also used for the front end multi-branch layer of the decoder and the back end multi-branch layer of the decoder in a mirrored manner with the encoder.

[0103] 7A to 7C Various aspects of implementing a common backbone with a front end and a back end to support variable antenna configurations, variable subband configurations, variable rank, and variable payload configurations are illustrated. In some aspects, a dual-sided artificial intelligence or machine learning AI / ML model has been adopted as a representative use case. Typically, the AI / ML model is trained for a specific configuration in terms of antenna port configuration, subband configuration, and payload configuration. However, in some cases, variable antenna configurations and subband configurations are supported for features such as, for example, channel state information. In one example, there are 13 antenna configurations and any subband mode of up to 19 subbands. What is needed is a new framework for supporting these variable configurations. The present disclosure provides a general structure that supports variable configurations. The general framework may include an AI / ML model with a common backbone (e.g., via a transformer or other AI / ML or neural network (NN) model). The general framework may use multiple parallel branches in the front end and the back end to support variable configurations. The first family in the front end is used to support variable antenna configurations, while the second family of branches at the back end can be used to handle multiple subband configurations, payload configurations, or variable ranks. In terms of signaling, the UE may report the supported antenna configurations and subband configurations, since the UE may only implement a reasonable number of branches in its generic framework.

[0104] In terms of reporting dimensionality, the framework is scalable with the number of subbands or subband span. For a larger number of antenna ports, the UE may support high, medium, and low dimensions. For a small number of antenna ports, the UE may support low dimension. For variable rank, higher dimensions are considered for low rank, while lower dimensions are considered for high rank to maintain similar payload as low rank.

[0105] The data communicated through the general framework described herein can be any type of data. However, one specific example of a type of data that can be processed is channel state information feedback (CSI feedback or CSF). The CSI reporting configuration in the wireless protocol may include a codebook that is used as a precoding matrix indicator (PMI) dictionary from which the UE will generate a report of the best PMI codeword that can describe the PMI, and report the PMI using a bit sequence. The gNB receives the bit sequence that it will look up which PMI codeword is reported.

[0106] The following is a brief discussion of CSF or channel state information (CSI). The UE can report CSI to the base station using one of two types of spatial information feedback: Type I CSI feedback and Type IICSI feedback. Type I CSI feedback is a CSI feedback scheme that includes codebook-based precoding matrix indicator (PMI) feedback with normal spatial resolution in beamforming, while Type IICSI feedback is an enhanced CSI feedback scheme that enables codebook-based feedback with higher spatial resolution than Type I CSI feedback in beamforming. Although Type IICSI feedback only allows the UE to report a rank indication (RI) of up to 2, compared to Type I CSI feedback, this feedback scheme can provide higher throughput through improved beamforming and resource allocation by bringing more beamforming gain and separating users at a higher granularity. Therefore, Type IICSI feedback may be useful for multi-user multiple input multiple output (MU-MIMO) deployment scenarios, for scenarios where signals may be scattered (e.g., multipath), for situations where interference from other UEs may require highly granular beamforming directed to the UE, for UEs located at the edge of the cell, and the like.

[0107] However, the complexity of the UE in calculating the PMI for the type II codebook may be significantly higher than that of the type I codebook. While the PMI for type I CSI feedback is generally calculated based on a single beam, the PMI for type IICSI feedback is generally calculated based on the weighted sum of multiple discrete Fourier transform (DFT) beams, whose value includes the sum of the products of different wideband amplitudes, subband amplitudes, and co-phases for each beam on multiple beams L. Such CSI feedback uses significant computational power of the UE. In addition, compared with type I CSI feedback, type IICSI feedback may have a large overhead because a UE using type IICSI feedback must report the index of L DFT beams for each layer, polarization, and beam, as well as the wideband amplitude scale, subband amplitude scale, and co-phase for each beam to the base station. In the case of such a relatively large payload size, the UE may spend a lot of transmit power and computational power when reporting type IICSI feedback to the base station. Therefore, it is challenging for the UE to determine the best parameters for precoding based on the size of the codebook allowed for Type IICSI feedback.

[0108] Therefore, while type IICSI feedback may be beneficial in the presence of many other users or when the UE is at the cell edge, the feedback scheme may be less efficient in scenarios where higher spatial resolution may not be required. For example, type IICSI feedback may have a small performance gain when the UE is located close to the base station, when there is not much interference from other UEs, or in a single-user multiple-input multiple-output (SU-MIMO) deployment. In this case, the gain may not outweigh the burden of the relatively large overhead and significant UE computational complexity. Therefore, when performing CSI feedback procedures and PMI selection, it is desirable to allow the UE to determine whether to use the type II codebook or revert to the type I codebook based on channel conditions. In addition, when the base station allocates uplink resources for the UE to send precoding information in the uplink control information (UCI) based on type IICSI feedback, it is desirable to allow the UE to signal the type I precoding information in a format suitable for the allocated resources (e.g., container) for type IICSI feedback when the UE has determined to revert to the type I codebook. In Rel-16, enhanced type II (eT2 or eType II) CSI feedback is introduced. Similar to Type II, the enhanced Type II codebook is also based on a linear combination of spatial bases (DFT). The difference compared to Type II is frequency domain reduction and support up to rank 4. This enables eType II to report CSI with spatial and frequency compression more efficiently, and with the same CSI report payload, eType II achieves higher throughput than Type II.

[0109] The method disclosed herein provides AI-based CSI feedback, which can replace the PMI codebook by the CSI encoder and decoder. Fig. 7AA block diagram 700 is illustrated including an encoder 702 at a UE that receives an input, encodes the input, and produces a potential message that is sent to a decoder on a gNB 704 to generate an output. The encoder 702 is similar to the PMI search algorithm in current systems (implementation specific issues). The encoder input can be a downlink channel matrix (H), a downlink pre-decoder vector (V), or an inferred covariance matrix Rnn. The input may include labels or auxiliary information for selecting branches of a front-end multi-branch layer as described below. The decoder 704 can be similar to or replace the PMI codebook used to convert CSI report bits to PMI codewords. The decoder 704 output can be: a downlink channel matrix (H); an original whitened downlink channel; a transmit covariance matrix; a downlink pre-decoder vector (V); a value SV, which can be a pre-decoder vector multiplied by an eigenvalue S; or an interference covariance matrix (Rnn). A whitened downlink channel is a channel that has been processed and interference removed using a filter at the UE. H or V may correspond to the original channel or a channel pre-whitened by the UE based on its demodulation filter. In general, the output of the decoder 704 is restored to the input of the encoder 702. The "latent message" can represent a compressed version of the encoder 702 input in any form, and it is sent to the decoder 704 for decoding and obtaining the original input. In some cases, the output of the decoder 704 is an eigenvector or a downlink pre-decoder V, and the input of the encoder 702 is a channel (original channel or whitened channel) H. In this case, the "latent message" can represent compressed channel state information, and the decoder 704 can obtain the desired output based on the compressed channel state information.

[0110] As mentioned above, since the variability that can be addressed by the disclosed machine learning model includes variable subband configurations in the network, the following provides background on subband configurations.

[0111] In the first step, given a bandwidth part (BWP) bandwidth (BW), there are two possible total numbers of subbands depending on two possible subband sizes. In one protocol, the minimum (total or maximum) number of subbands in one BWP is 3, and the highest (total or maximum) number of subbands in one BWP is 19. This is because the BWP starting point can be any resource block (RB), but the subbands are counted from common resource block (CRB) 0. For example, if BWP = {2, 3, ..., 73} and Sbsize = 4, then SB1 = {2, 3}, SB2 = {4-7}, SB3 = {8-11}, ..., SB18 = {68-71}, SB19 = {72, 73}. For PMI codebooks eType2, eType2-Port-Selection, and further enhanced Type2-Port-Selection, each subband can be further divided into two subbands for PMI. Table 1 shows various configured subband sizes associated with bandwidth parts and associated sets of possible subband sizes.

[0112] Bandwidth Part (PRB) Subband size (PRB) 24-72 4,8 73-144 8,16 145-275 16,32

[0113] Table 1

[0114] In the second step, the size-#SB bitmap is used to configure the subbands for which CSI is reported. Based on the bitmap size, the UE can know the total number of subbands in the BWP and the subband size. The actual number of subbands can be 1 to 19. Based on the position of the "1" and "0" in the bitmap, the UE knows the actual configured subbands. The actual subbands can be in any pattern. In one example, a bitmap of subband 19 may indicate that there may be up to 19 subbands, but because the bitmap may have both 1 and 0, the actual number of subbands may still be in the range from 1 to 19 and may be continuous or non-contiguous.

[0115] In one example, in the RRC signaling CSI-reportingBand, the bitmap may show via bitmapsubband3 that there are 3 subbands, which may be mapped to a bit string of size (3). In another example, the bitmap may show via bitmapsubband7 that there are 7 subbands, which may indicate to the UE that the bit string subband size may be size (7). In one case, the maximum number of subbands may be from 3 to 19 (inclusive), and each number of subbands identified in the bitmap may have a corresponding bit string subband size.

[0116] Regarding multiple antenna configurations, a protocol includes a CSI codebook that supports variable antenna configurations. For example, Table 2 shows the number of total ports in the left column, which can be, for example, 4, 8, 12, 16, 24, 32. The right column can show possible dual-polarized antenna configurations (N1, N2). Different numbers such as (2, 1) or (4, 2) in the second column represent the number of antennas or transceiver units (TXRU) per dimension. Each TXRU has its own independent amplitude and phase control and is mapped to a set of physical antenna elements. The values ​​N1, N2 indicate how many TXRUs are configured in the first dimension for N1 and the second dimension for N2.

[0117]

[0118]

[0119] Table 2

[0120] For example, for an 8-port configuration, there may be a (2,2) dual polarization configuration or a (4,1) dual polarization configuration. These variations can be handled by the common backbone disclosed herein.

[0121] The UE may generate the W1 matrix (hereinafter v_{l,m} DFT vector) for spatial compression based on the configured antenna settings (N1, N2) according to the following equation:

[0122]

[0123] The W1 matrix is ​​used for spatial compression. For example, the W1 matrix can convert a 32-port channel into 8 dimensions depending on its settings (if 4 DFT beams are configured and the UE will select 4 DFT beams and apply them to two polarizations). The final PMI in Type I and Type II is W1*W2. W2 represents the coefficients of the basis in the combination W1. The final PMI in Type II is W1*W2*Wf, where W2 is the coefficient matrix and Wf is the frequency compression.

[0124] CSI compression is a frequency-space compression of eigenvectors (e.g., 4 eigenvectors of 4 layers, each with a 32x1 vector, 12 subbands, so a total of 32*4*12). The old CSI method can support variable Tx numbers (i.e., up to 32 port numbers) and variable subband configurations (up to 19 subbands with arbitrary modes). For AI / ML-based CSF, the question is how to support variable antenna configurations, variable subband configurations. For AI / ML-based CSF, the question is also how to determine the payload for each variable configuration. For example, for high or low resolution of CSI compression, there may be a high or low payload. The configured payload can therefore also vary. The goal of the present disclosure is how to design and / or train an AI / ML model to handle variable configurations, because training of different models per configuration is too complex, will require too much memory, and in practice requires too much switching between models. Therefore, the present disclosure provides a single AI / ML model that is trained to handle the variable configurations disclosed herein.

[0125] Figure 7B An encoder 710 is illustrated having a front-end multi-branch layer 712 of a machine learning model, a common backbone 714 of the machine learning model, and a back-end multi-branch layer 716 of the machine learning model. The input to the model or neural network may be, for example, a downlink channel matrix H or a downlink pre-decoder V. The data may include, for example, data associated with a row indicating the number of ports and / or antenna configurations or settings from Table 2. There may also be groupings of different antenna configurations, and the front-end multi-branch layer may be trained to map antenna configurations or settings or other data in the input to selected branches based on the antenna configuration or a group associated with the antenna configuration. The front-end multi-branch layer may be trained offline to perform this operation. Various training methods are described below. The mapping may be based on the gNG configuration of antennas and subbands. The mapping may also involve different antenna configurations or settings for different UEs from different vendors. Thus, the input data may involve a variable configuration for a gNB or a variable configuration for a UE. Based on the input and / or auxiliary information or a label associated with the input, the UE may determine which branch of the front-end multi-branch layer to use. Each branch in the front-end multi-branch layer can perform a corresponding linear embedding on a different branch that transforms the input data from the transmission domain to the feature domain, or more generally from one domain to another.

[0126] When the UE interacts with different gNBs via wireless communication and moves from gtNB to gNB, or when the machine learning model 710 is deployed on different UEs with different configurations, the input can be a CSI-RS based channel measurement, and the input auxiliary information can be a variable antenna configuration and / or antenna setting group, the machine learning model 710 can receive the auxiliary information based on the gNB configuration, determine which branch of the front-end multi-branch layer to use for linear embedding or perform a transformation of the input from one domain to another, which generates a first output. The first output is further processed by the position embedding layer and another neural network as part of the common backbone 714, which shows as an example a transformer that processes the output data six times to generate a second output. Here, the weights in the position embedding layer to be used are also selected based on the subband and rank configuration. The second output is passed to one of the back-end multi-branch layers. The selected branch can be based on one or more of the subband configuration, rank, antenna configuration, or payload configuration. These branches are configured to compress features across frequencies and layers and generate a signal that is sent over the air interface to a UE having a configuration such as Figure 7C The potential messages of the network entity corresponding to or complementary to the decoder 720 are shown. The potential messages as dimensions denoted as d_z are discussed more fully below.

[0127] Figure 7C A decoder 720 including a front-end multi-branch layer 722 is illustrated, which receives a potential message having a dimension d_z and determines which layer or branch of the multi-branch layer should process the potential message. The potential message may include auxiliary information or tags, such as subband configuration information, rank, antenna configuration, and / or payload configuration. The auxiliary information or tags enable the decoder to select which branch to use to process the potential message. Each branch of the front-end multi-branch layer of the machine learning model on the decoder 720 performs a different type or different aspect of linear decompression to decompress features across frequencies and layers and provides the output to the position embedding layer of the common backbone 724 of the machine learning model. The common backbone 724 recovers the initial features with position encoding and processes the output of the position embedding layer six times through the transformer. Here, the weights in the position embedding layer to be used are also selected based on the subband and rank configuration. Figure 7B The position embedding layer shown as part of the common backbone 714 receives the outputs from the branches of the front-end multi-branch layer 712. A linear embedding is similar to a W1 matrix in that it transforms the input from the Tx domain to a feature domain that describes what is happening in the neural network. Nt*d_model is the dimension of each linear embedding layer of the front-end multi-branch layer 712. In one example, d_model is a value selected as the dimension of the feature domain, such as 256, and Nt can correspond to the number of ports and can therefore have a value like 32. Each patch is an Nt*1 vector. Each layer of the front-end multi-branch layer 712 transforms each patch from the Tx domain to the feature domain based on these values.

[0128] The front-end multi-branch layer 712 can be, for example, a fully connected neural network layer. The position embedding method has some bias on its input. Depending on the feature domain, it can be large and can include, for example, 48 patches (generated by 12 subbands and 4 layers), where each patch can have 256 values, and the position embedding stores the position of each patch. If there is an arbitrary subband configuration, the position embedding can remember the position of the configured subband. Each patch (which can refer to a patch antenna) is a d_model*1 vector.

[0129] The use of a "transformer" as part of the machine learning model as a common backbone 714 and the number of times the data is processed is exemplary only. The output of the common backbone 724 is provided to the back-end multi-branch layer 726 of the machine learning model, where different linear embedding processes can be used to generate antenna settings or antenna group settings outputs or transform the data from the feature domain to the transmit domain and produce a decoder output Hhat or Vhat.

[0130] The potential message has a potential dimension d_z that depends on at least one of the subband mode, antenna configuration, rank, and payload configuration. The dimension d_z is related to the number of layers of linear compression output. In one example, the output of the back-end multi-branch layer 716 has a value of (d_model*N_patch)*d_z that is commonly applied to all spatial layers. Here, for example, there are 48 patches that can be N_patch, where d_model is 256 times the d_z value. This is a very large linear compression layer applied to all layers. Within each layer of the back-end multi-branch layer 716. In another case, the linear layer compression layer size is (d_model*Nsb)*d_z applied to each spatial layer. Here, Nsb represents the number of subbands.

[0131] For example, with respect to subband mode, d_z may scale with the number of configured subbands, e.g., d_z=ceil(d_z_max*p), where p increases with Nsb, e.g., Nsb / 19. Alternatively, d_z_1 may apply to the 1st set of Nsb, and d_z_2 may apply to the 2nd set of Nsb. In this case, if Nsb_set1 is greater than Nsb_set2, then d_z_1 may be greater than d_z_2. For example, d_z=32 is the total number of subbands <= 6, and if the total number of subbands > 6 but <= 12, then d_z=64.

[0132] On the other hand, d_z may scale with the subband span, i.e., d_z=ceil(d_z_max*p), where p increases with the subband span defined by (sb_max-sb_min) (e.g., (sb_max-sb_min) / 19), where sb_max and sb_min are the highest subband index and the smallest subband index, respectively. Each d_z value may be implemented by a specific linear compression layer at the back-end multi-branch layer 716 of the encoder 710 or the front-end multi-branch layer 722 of the decoder 720.

[0133] Subband configurations with the same d_z value may use the same linear compression layer at the back-end multi-branch layer 716 of the encoder 710 or the front-end multi-branch layer 722 of the decoder 720. Grouping of different or similar d_z values ​​may occur so that the same linear compression layer 716 in the encoder (or decompression layer 722 in the decoder) processes all d_z values ​​in the group. For example, all subband modes with <= 6 subbands or subband spans are grouped and a first linear compression layer with d_z=32 is used in the back-end multi-branch layer, while all subband modes with > 6 subbands or subband spans are grouped and a second linear compression layer with d_z=64 is used.

[0134] During the training phase, the data are labeled with their respective subband configurations, antenna configurations, ranks, or payload configurations. Data that can share the same linear compression layer or linear embedding layer are grouped using the corresponding layer during training. In some other cases, the training of the machine learning model can cause the common trunk 714 to not only generate labels, but also provide outputs, dimensions d_z, or group numbers, which will cause the output of the common trunk 714 to be compressed by specific branches of the back-end multi-branch layer 716.

[0135] With respect to payload configuration and antenna configuration, multiple d_z_max values ​​(e.g., d_z_max1>d_z_max2>d_z_max3, etc.) may be predefined in the standard or reported by the UE as an additional capability. In one aspect, whether some or all of the d_z maximum values ​​are applied may depend on the payload configuration and / or antenna configuration. The UE may report multiple d_z_max values, such as one value for high payload, a second value for medium payload, and a third value for low payload. For example, the UE may report its capabilities to the network entity, such as the supported antenna configurations or the limited number of front-end multi-branch layer 712 branches supported. The UE may support multiple antenna configurations for each branch and report the data to the network entity. The UE may also report supported subband modes, such as the number of subbands, the number of subband spans, or the range between the minimum subband index and the highest subband index and whether the subbands are continuous. The same logic may be applied to the actual reporting dimension d_z. That is, the machine learning model supports multiple d_z values, and all dimension values ​​or a subset thereof depend on the antenna configuration. For example, the actual reported dimension is generated by d_z = ceil(d_z_max*p), where p depends on the subband configuration and d_z_max is determined per antenna configuration. The allowed d_z values ​​are determined by determining the allowed d_z_max per antenna configuration.

[0136] In one example, when the total number of antenna ports is greater than or equal to threshold 1 (e.g., 32 ports), the UE may support all d_z_max values. In another example, when the total number of antenna ports is less than threshold 1 but greater than or equal to threshold 2, the UE may support a first subset of d_z_max other than the maximum d_z_max, such as (d_z_max2, d_z_max3).

[0137] In another example, when the total number of antenna ports is less than a threshold value 2, the UE may support a second subset of d_z_max, wherein the second subset is a subset of the first set except for the second largest d_z_max, for example, d_z_max3. Each d_z_max value may be implemented by a specific linear compression layer at the back-end multi-branch layer 716 of the encoder 710 or the front-end multi-branch layer 722 of the decoder 720.

[0138] Antenna configurations with the same d_z value can use the same linear compression layer at the back-end multi-branch layer 716 of the encoder 710 or the front-end multi-branch layer 722 of the decoder 720.

[0139] Different antenna configurations or antenna configuration groups may use different linear embeddings at the front-end multi-branch layer 712 of the encoder or the back-end multi-branch layer of the decoder 726 .

[0140] Regarding rank, the first d_z_max_set1={d_z_max1_1, d_z_max2_1, d_z_max3_1} may be applied to (each layer) rank 1 and rank 2. In another example, the second d_z_max_set2={d_z_max1_2, d_z_max2_2, d_z_max3_2} may be applied to (each layer) rank 3 and rank 4. Alternatively, the second d_z_max_set2 may be used for rank 3, and the third d_z_max_set3 may be used for rank 4. In yet another example, the dimensions of rank 3 and rank 4 may be comparable to rank 2, for example d_z_max1_2=d_z_max1_1*1 / 2, or d_z_max1_2=d_z_max1_1*2 / 3, d_z_max1_3=d_z_max1_1*1 / 2. The first set of linear compression layers (corresponding to d_z_max_set1) can be applied to each spatial layer of rank 1 and rank 2. The second set of linear compression layers (corresponding to d_z_max2) can be applied to each spatial layer of rank 3 or rank 3+rank 4. The same logic can be applied to the actual reported dimension d_z. That is, the machine learning model supports multiple sets of d_z values, while lower ranks (e.g., rank 1 and rank 2) support larger sets of dimensional values, while higher ranks (e.g., rank 3 and rank 4) support smaller sets of dimensional values. For example, the actual reported dimension is generated by d_z=ceil(d_z_max*p), where p depends on the subband configuration and d_z_max is determined by the rank assumption. The allowed d_z values ​​are determined by determining the d_z_max allowed for each rank assumption.

[0141] In order to align or train the machine learning model on the supported antenna and / or subband configurations, various options may be applied. In a first option related to the offline training alignment context, a centralized training method may include an entity, such as a server associated with a UE vendor, a server associated with a network node or a gNB vendor, or a third-party training server, that can train the model (e.g., encoder 710 and decoder 720) and deliver the corresponding model to each UE and network node. In this method, the UE vendor exposes its neural network or model architecture to the training entity and gives the input samples and true values ​​to the training entity. The data (samples, true values) include variably supported antenna / subband / payload configurations and include variable rank assumptions. The UE may also provide the corresponding antenna / subband / payload configuration and rank assumption as a label or auxiliary information for each provided data.

[0142] Another method is distributed training, in which training at the network entity server and the UE server occurs concurrently. In this method, neither party exposes the model architecture to each other, but exchanges data that can be used to train the corresponding models. In this way, the UE server and the network server share data at each iteration of the training process. The UE server gives the true value (target) and activation (between the encoder and the decoder) to the network entity server. For each iteration, the data {target, activation} should include variable supported antenna / subband / payload configurations and variable rank assumptions. The UE can also provide the corresponding antenna / subband / payload configuration and rank assumptions for each provided data as labels or auxiliary information. The network entity server provides backward gradients to the UE server. In the distributed training method, encoders for deployment on UEs and decoders for deployment on one or more network entities such as gNBs can be trained without exposing proprietary data from either party.

[0143] In the separated training method, the UE server first trains its encoder and gives the potential message (z) and the true value or expected decoder output (v or vhat) to the network entity server for the network entity server to train the decoder. The data {z, v} or {z, vhat} may include variable supported antenna / subband / payload configurations and may include variable rank assumptions. The UE may also provide the corresponding antenna / subband / payload configuration and rank assumption as labels or auxiliary information for each provided data {z, v} or {z, vhat}.

[0144] In some aspects, in some or all of the above training methods, in order to train a neural network with a common backbone and a multi-branch structure, the following situations may exist in the data set generation: (1) for subband configuration generalization, N>=1 random patterns (continuous or non-continuous) are generated for each data sample in the training set. In some cases, the full subband pattern may be used in addition; and / or (2) for antenna configuration generalization, data samples generated based on M antenna configurations are mixed in equal proportions.

[0145] In one example, for variable antenna configurations, a UE, UE vendor, or training entity (e.g., a server owned by a UE vendor or other vendor) may train an AI / ML model using a mixed data set with equal proportions of 2x8 antenna configurations and 2x4 antenna configurations. In one example, for each sample in the training set, the training entity, UE vendor, or UE may generate a random subband pattern (assuming a total of 12 subbands) in addition to the full subband case. Any pattern may also be considered, such as randomly selecting N3 subbands from a total of 12 subbands, where N3 ranges between 3 and 11. In another example, a continuous pattern may be considered and the number of subbands may be randomly generated between 3 and 12. In this case, if Nsb>6, an encoder output dimension = 64 may be considered, and if Nsb<=6, 32 may be considered. In another example, a discontinuous pattern may be considered, and the number of subbands may be randomly generated between 3 and 12. In this case, if Nsb>6, an encoder output dimension = 64 may be considered, and if Nsb<=6, 32 may be considered. For all these configurations, the UE may generate N random patterns per data sample, where N may depend on the number of epochs. For centralized and distributed training, each random pattern may be generated per epoch; for split training, N random patterns may be generated after the UE vendor side training is completed, and N different versions of potential message z are provided to the gNB vendor side.

[0146] In another option, the UE may be able to signal a report for each model ID. After training, testing, compiling the model, its ID will be registered at the radio access network, which means that the gNB can configure the model ID for the UE to use. The corresponding UE can download the corresponding compiled runtime image from the model server. The UE can report the supported antenna configurations to the gNB, as it may only support a limited number of front-end branches in, for example, the front-end multi-branch layer 712. The UE may support multiple antenna configurations per branch. On the other hand, the UE may report the supported subband modes, such as the number of supported subbands, the number of subband spans as the range between the minimum subband index and the highest subband index, and whether the mode is continuous.

[0147] The machine learning models described herein can also be trained in a variety of different ways, such as in the full subband case with d_z=64 and d_z=32, or based on a continuous subband mask with Nsb=[3,12], if Nsb>6, then d_z=64, otherwise d_z=32. In another example, the model can be trained on an arbitrary subband mask with Nsb[3,12], if Nsb>6, then d_z=64, otherwise d_z=32.

[0148] Fig. 8Ais a flow chart illustrating an example of a process 800 for wireless communication utilizing a reference signal for joint communication and sensing. Process 800 may be performed by a network device or by a component or system (e.g., a chipset) of a network device. The network device may include a UE (e.g., a mobile device such as a mobile phone, a network-connected watch, an extended reality (XR) device such as a virtual reality (VR) device or an augmented reality (AR) device, a vehicle or a computing device or system of a vehicle, or other device), a base station (e.g., an eNB, a gNB, or other base station), a portion of a base station (e.g., a CU, DU, RU, or other portion of a base station), or other device. The operations of process 800 may be implemented as a processor (e.g., Fig. 9 The software components executed and run on the processor 910 or other processors of the wireless communication device. In addition, the wireless communication device can be enabled to send and receive signals in the process 800, for example, through one or more antennas and / or one or more transceivers (e.g., wireless transceivers).

[0149] At block 802, a network device (or a component thereof) may obtain an input to a front-end multi-branch layer of a machine learning model that is trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration. An illustrative example of a machine learning model is described in Figure 7B Shown in.

[0150] At block 804, the network device (or a component thereof) may process an input via a selected branch of a plurality of branches in a front-end multi-branch layer to generate a first output.

[0151] At box 806, the network device (or a component thereof) may process the first output through a common backbone of the machine learning model to produce a second output.

[0152] At box 808, the network device (or a component thereof) may provide the second output to a backend multi-branch layer of the machine learning model.

[0153] At block 810 , the network device (or a component thereof) may process the second output via a selected branch of a plurality of branches of a backend multi-branch layer to generate a potential message having dimensions.

[0154] In some aspects, the back-end multi-branch layer includes a plurality of linear compression branches. For example, as described above, each of the plurality of linear compression branches can be configured to compress the second output according to features across frequency and spatial layers.

[0155] In some cases, the dimension of the potential message is implemented by the selected branch of the backend multi-branch of the machine learning model.

[0156] In some examples, different sub-band configurations having the same dimension for the potential message use the same compression layer associated with corresponding branches of the plurality of branches of the backend multi-branch layer.

[0157] In some aspects, the machine learning model is trained to group multiple antenna configurations into groups that map to corresponding branches in the multiple branches in the front-end multi-branch layer.

[0158] In some cases, the variable antenna configuration is used by the base station to configure the CSI report associated with the machine learning model, and wherein the variable subband configuration is the subband associated with the CSI report.

[0159] In some examples, the dimension of the potential message is determined based on at least one of a subband mode, antenna configuration, rank, or payload configuration associated with the input.

[0160] In some aspects, the machine learning model is trained to determine the dimension of the potential message based on at least one of the subband mode, the antenna configuration, the rank, or the payload configuration associated with the input.

[0161] In some cases, the machine learning model is trained to group multiple sub-band configurations into groups that map to corresponding branches in the multiple branches in the back-end multi-branch layer.

[0162] In some examples, when the dimension of the potential message is determined based on the subband mode, the dimension of the potential message scales with the number of configured subbands or with a subband span.

[0163] In some aspects, when the dimension of the potential message is determined based on the antenna configuration or the payload configuration, the backend multi-branch layer implements a maximum dimension value of the potential message at a corresponding compression layer associated with a corresponding branch of the backend multi-branch layer.

[0164] In some cases, various antenna configurations that map to the same dimensionality value of the underlying message use the same linear compression layer associated with corresponding branches of the back-end multi-branch layer.

[0165] In some examples, when the dimension of the potential message is determined based on the rank, at least one of the following is performed: a first set of dimensions is applied to each layer associated with a corresponding branch of the back-end multi-branch layer for a first rank or a second rank, and a second set of dimensions is applied to each layer associated with a corresponding branch of the back-end multi-branch layer for a third rank and a fourth rank.

[0166] In some aspects, the machine learning model is trained according to at least one of a centralized training method, a distributed training method, or a separate training method.

[0167] In some cases, when the machine learning model is trained according to a centralized training method, an entity associated with the device exposes the machine learning model architecture to the training entity and provides input samples and true values ​​to the training entity, wherein the input samples and the true values ​​include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

[0168] In some examples, when the machine learning model is trained according to the distributed training method, an entity associated with the device communicates with a network entity, and for each iteration of communicating training data, the entity associated with the device provides a true value and an activation to the network entity, wherein the true value and the activation include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

[0169] In some aspects, when the machine learning model is trained according to the separate training method, an entity associated with the device first trains an encoder and sends a potential message and a true value or an expected decoder output to a network entity, wherein the potential message and the true value or the expected decoder output include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

[0170] In some cases, the device supports only a limited number of branches in the front-end multi-branch layer.

[0171] In some aspects, the device supports only certain subband modes. In some cases, the certain subband modes include one or more of a number of subbands, a number of subband spans, and whether the subbands are contiguous or non-contiguous.

[0172] In some cases, the front-end multi-branch layer of the machine learning model utilizes the antenna setting data in the input to select the selected branch among the multiple branches of the front-end layer.

[0173] In some aspects, the front-end multi-branch layer of the machine learning model transforms the input from a transmission domain to a feature domain. In some cases, the common trunk of the machine learning model extracts deep features with position encoding from the first output and generates the second output.

[0174] In some cases, the common backbone of the machine learning model includes a position embedding layer and multiple machine learning layers.

[0175] In some examples, the backend multi-branch layer of the machine learning model compresses features of the second output across frequencies and layers to generate the potential message having the dimension.

[0176] In some aspects, each respective branch of the plurality of branches of the back-end multi-branch layer is associated with one or more of a respective subband configuration, a respective rank, a respective antenna configuration, or a respective payload configuration.

[0177] In some cases, the machine learning model is trained to select the selected branch among the multiple branches of the backend multi-branch layer based on at least one of a subband mode, antenna configuration, rank, or payload configuration associated with the input.

[0178] A non-transitory computer-readable storage medium may include instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform any method, process, or set of operations disclosed above.

[0179] An apparatus for wireless communication may include one or more components for performing operations according to any method, process or set of operations disclosed above.

[0180] In some examples, the processes described herein (e.g., processes 800, 810, 820 and / or other processes described herein) may be performed by a computing device or apparatus (e.g., a UE or a base station). In another example, processes 800, 810, 820 may be performed by Figure 1 In another example, processes 800, 810, and 820 may be performed by UE 104. Figure 1 The base station 102 is used to execute.

[0181] Figure 8B is a flow chart illustrating an example of process 811 for wireless communication utilizing reference signals for joint communication and sensing. Process 811 may be performed by a network device or by a component or system (e.g., a chipset) of a network device. The network device may include a UE (e.g., a mobile device such as a mobile phone, a network-connected watch, an extended reality (XR) device such as a virtual reality (VR) device or an augmented reality (AR) device, a vehicle or a computing device or system of a vehicle, or other device), a base station (e.g., an eNB, a gNB, or other base station), a portion of a base station (e.g., a CU, DU, RU, or other portion of a base station), or other device. The operations of process 811 may be implemented as a processor (e.g., Fig. 9 The software components executed and run on the processor 910 or other processors of the wireless communication device. In addition, the wireless communication device can be enabled to send and receive signals in the process 811, for example, through one or more antennas and / or one or more transceivers (e.g., wireless transceivers).

[0182] At box 812, the network device (or a component thereof) may receive a channel state information (CSI) reporting configuration, which includes at least one of a CSI reporting subband mode configuration, an antenna configuration, a restriction on possible ranks to be reported, or a payload configuration.

[0183] At block 814, the network device (or a component thereof) may determine, based on the CSI reporting configuration, CSI reporting dimensions associated with outputs of a machine learning model used by the user equipment to generate CSI reports.

[0184] At block 816, the network device (or a component thereof) may generate a CSI report using a machine learning model based on the CSI reporting dimensions.

[0185] In some aspects, the machine learning model is trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration, and the machine learning model includes a front-end multi-branch layer, a common backbone, and a back-end multi-branch layer, wherein the corresponding layers of the back-end multi-branch layer are selected based on the CSI reporting dimension.

[0186] In some cases, a corresponding layer of the front-end multi-branch layer is selected based on at least one of the antenna configuration or a grouping associated with multiple antenna configurations.

[0187] In some examples, the CSI report dimension associated with the output of the machine learning model is scaled relative to one or more of the number of configured subbands or the subband span.

[0188] In some aspects, the CSI reporting dimension is determined based on the product of the CSI reporting dimension maximum value and the number of configured subbands or the subband span, or based on the product of the CSI reporting dimension maximum value and the ratio of the number of configured subbands to the total number of subbands or the ratio of the configured subband span to the total subband span.

[0189] In some cases, the network device (or a component thereof) may report at least one of a limited number of front-end branches associated with the machine learning model, a number of antenna configurations supported by each of the front-end branches, or supported subband modes.

[0190] In some examples, the machine learning model associated with the configured CSI report supports multiple CSI reporting dimension maximum values ​​or multiple CSI reporting dimension values ​​for each antenna configuration or subband configuration.

[0191] In some aspects, the network device (or a component thereof) may receive a payload configuration indicating a CSI reporting dimension maximum value among the plurality of CSI reporting dimension maximum values ​​or a CSI reporting dimension value among the plurality of CSI reporting dimension values.

[0192] In some cases, the multiple CSI reporting dimension maximum values ​​or a subset of different CSI reporting dimension maximum values ​​or the multiple CSI reporting dimension values ​​or a subset of different CSI reporting dimension values ​​are supported by the machine learning model based on the total number of antenna ports being above or below a threshold.

[0193] In some examples, the machine learning model associated with the configured CSI report supports a first plurality of CSI reporting dimension maximum values ​​or a first plurality of CSI reporting dimension values ​​for a first set of rank values; and supports a second plurality of CSI reporting dimension maximum values ​​or a second plurality of CSI reporting dimension values ​​for a second set of rank values.

[0194] In some aspects, when the first set of rank values ​​is less than the second set of rank values, the first plurality of CSI reporting dimension maximum values ​​or the first plurality of CSI reporting dimension values ​​are greater than the second plurality of CSI reporting dimension maximum values ​​or the second plurality of CSI reporting dimension values.

[0195] In some cases, different antenna configurations or different groups of antenna configurations use different branches of the front-end multi-branch layer of the machine learning model for different linear embedding processes.

[0196] In some examples, the variable ranks correspond to respective different layers of the backend multi-branch layer of the machine learning model.

[0197] Fig. 9 is a diagram illustrating an example of a system for implementing certain aspects of the present technology. Specifically, Fig. 9 An example of a computing system 900 is illustrated, which may be any computing device, for example, constituting an internal computing system, a remote computing system, a camera, or any layer thereof, wherein the components of the system communicate with each other using a connection 905. The connection 905 may be a physical connection using a bus, or a direct connection into the processor 910, such as in a chipset architecture. The connection 905 may also be a virtual connection, a networked connection, or a logical connection.

[0198] In some embodiments, computing system 900 is a distributed system, where the functionality described in the present disclosure may be distributed within a data center, multiple data centers, a peer-to-peer network, etc. In some embodiments, one or more of the described system components represent a number of such components that each perform some or all of the functionality for which the component is described. In some embodiments, a component may be a physical device or a virtual device.

[0199] The example system 900 includes at least one processing unit (CPU or processor) 910 and connections 905 that communicatively couple various system components including system memory 915, such as read only memory (ROM) 920 and random access memory (RAM) 925, to the processor 910. The computing system 900 may include a cache 912 of high-speed memory directly connected to the processor 910, in close proximity to the processor, or integrated as part of the processor.

[0200] Processor 910 may include any general purpose processor and hardware or software services such as services 932, 934, and 936 stored in storage device 930 configured to control processor 910, as well as special purpose processors where software instructions are incorporated into the actual processor design. Processor 910 may essentially be a completely independent computing system containing multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.

[0201] To enable user interaction, the computing system 900 includes an input device 945 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, etc. The computing system 900 may also include an output device 935, which may be one or more of a plurality of output mechanisms. In some cases, a multimodal system may enable a user to provide multiple types of input / output to communicate with the computing system 900.

[0202] The computing system 900 may include a communication interface 940, which may generally govern and manage user input and system output. The communication interface may perform or facilitate receiving and / or sending wired or wireless communications using wired and / or wireless transceivers, including using an audio jack / plug, a microphone jack / plug, a Universal Serial Bus (USB) port / plug, an Apple TM Lightning TM Ports / plugs, Ethernet ports / plugs, Fiber optic ports / plugs, Dedicated wired ports / plugs, 3G, 4G, 5G and / or other cellular data network wireless signal delivery, Bluetooth TM Wireless signal transmission, Bluetooth TM Low energy (BLE) wireless signal transmission, IBEACON TMThe communication interface 940 may also include one or more global navigation satellite system (GNSS) receivers or transceivers for determining the location of the computing system 900 based on receiving one or more signals from one or more satellites associated with one or more GNSS systems. GNSS systems include, but are not limited to, the United States' Global Positioning System (GPS), Russia's Global Navigation Satellite System (GLONASS), China's BeiDou Navigation Satellite System (BDS), and Europe's Galileo GNSS. There is no restriction to operating on any particular hardware arrangement, and thus the base features herein may be easily substituted for improved hardware or firmware arrangements as they are developed.

[0203] The storage device 930 may be a non-volatile and / or non-transitory and / or computer-readable memory device and may be a hard disk or other type of computer-readable medium that can store data accessible by a computer, such as a magnetic cassette, a flash memory card, a solid-state memory device, a digital versatile disk, a cassette, a floppy disk, a floppy disk, a hard disk, a magnetic tape, a magnetic stripe / magnetic stripe, any other magnetic storage medium, a flash memory, a memristor memory, any other solid-state memory, a compact disk-read only memory (CD-ROM) optical disk, a rewritable compact disk (CD) optical disk, a digital video disk (DVD) optical disk, a Blu-ray disc (BDD) optical disk, a holographic optical disk, another optical medium, a secure digital (SD) card, a micro secure digital (microSD) card, a memory card, or a memory card. card, a smart card chip, an EMV chip, a subscriber identity module (SIM) card, a mini / micro / nano / pico SIM card, another integrated circuit (IC) chip / card, a random access memory (RAM), a static RAM (SRAM), a dynamic RAM (DRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash EPROM (FLASH EPROM), a cache memory (e.g., a layer 1 (L1) cache, a layer 2 (L2) cache, a layer 3 (L3) cache, a layer 4 (L4) cache, a layer 5 (L5) cache, other (L#) cache), a resistive random access memory (RRAM / ReRAM), a phase change memory (PCM), a spin transfer torque RAM (STT-RAM), another memory chip or box, and / or a combination thereof.

[0204] The storage device 930 may include software services, servers, services, etc., which, when the code defining such software is executed by the processor 910, causes the system to perform functions. In some embodiments, hardware services that perform specific functions may include software components for performing functions stored in a computer-readable medium connected to necessary hardware components such as the processor 910, connection 905, output device 935, 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-transient media in which data may be stored and does not include carrier waves and / or transient electronic signals propagated wirelessly or through wired connections. Examples of non-transient media may include, but are not limited to, disks or tapes, optical storage media (such as compact discs (CDs) or digital versatile discs (DVDs)), flash memory, memory, or memory devices. Computer readable media may store thereon code and / or machine executable instructions, which may represent a procedure, function, subprogram, program, routine, subroutine, module, software package, category, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, independent variables, parameters, or memory contents. Information, independent variables, parameters, data, etc. may be passed, forwarded, or sent via any suitable means, including memory sharing, message passing, token passing, network sending, etc.

[0205] Specific details are provided in the above description to provide a thorough understanding of each embodiment and each example provided herein, but those skilled in the art will recognize that the present application is not limited thereto. Thus, although the exemplary embodiments of the present application have been described in detail herein, it is to be understood that the inventive concept can be embodied and adopted in various other ways, and the appended claims are intended to be interpreted as including such variations, unless limited by the prior art. Various features and aspects of the above-mentioned applications can be used individually or in combination. In addition, without departing from the broader scope of this specification, the embodiments can be used in any number of environments and applications beyond the environment and application described herein. Therefore, the description and the accompanying drawings should be considered as illustrative rather than restrictive. For the purpose of illustration, each method is described in a specific order. It should be understood that in an alternative embodiment, each method can be performed in a different order than described.

[0206] For clarity of explanation, in some cases, the present technology may be presented as including separate functional blocks, which include devices, device components, steps or routines in the method embodied in software or a combination of hardware and software. Additional components other than those components shown in the drawings and / or described herein may be used. For example, circuits, systems, networks, processes and other components may be shown as components in block diagram form to avoid burying these embodiments in unnecessary details. In other cases, known circuits, processes, algorithms, structures and techniques may be shown without necessary details to avoid confusing various embodiments.

[0207] In addition, it will be appreciated by those skilled in the art that the various exemplary logic blocks, modules, circuits and algorithmic steps described in conjunction with the various aspects disclosed herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, various exemplary components, blocks, modules, circuits and steps have been generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints proposed to the entire system. Those skilled in the art can implement the described functions in different ways for each specific application, but such specific implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0208] Individual embodiments may be described above as processes or methods depicted as flow charts, flow diagrams, data flow diagrams, structure diagrams, or block diagrams. Although a flow chart may describe an operation as a sequential process, many of the operations may be performed in parallel or concurrently. In addition, the order of the operations may be rearranged. The process is terminated when the operations of the process are completed, but the process may have additional steps not included in the accompanying drawings. A process may correspond to a method, function, procedure, subroutine, subprogram, etc. When a process corresponds to a function, the termination of the process may correspond to the function returning to the calling function or main function.

[0209] The processes and methods according to the above examples can be implemented using stored computer executable instructions or otherwise available computer executable instructions from a computer readable medium. Such instructions may include, for example, instructions and data that configure a general-purpose computer, a special-purpose computer, or a processing device to perform a certain function or group of functions. Portions of the computer resources used may be accessed via a network. Computer executable instructions may be, for example, binary, intermediate format instructions such as assembly language, firmware, source code. 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 disks, flash memories, USB devices with non-volatile memory, networked storage devices, etc.

[0210] In some embodiments, computer readable storage devices, media, and memories may include wired or wireless signals containing bit streams, etc. However, when referred to, non-transitory computer readable storage media explicitly excludes media such as power consumption, carrier signals, electromagnetic waves, and signals themselves.

[0211] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof in some cases, depending in part on the specific application, in part on the desired design, in part on the corresponding technology, etc.

[0212] Various illustrative logic blocks, modules, and circuits described in conjunction with the various aspects disclosed herein may be implemented or executed using hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof, and may be implemented in any of a variety of form factors. When implemented in 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. The processor may perform the necessary tasks. Examples of form factors include: laptops, smartphones, mobile phones, tablet devices, or other small form factor personal computers, personal digital assistants, rack-mounted devices, stand-alone devices, etc. The functions described herein may also be embodied in peripheral devices or add-in cards. By way of further example, such functionality may also be implemented on circuit boards in different chips or different processes executed on a single device.

[0213] The instructions, the media for conveying such instructions, the computing resources for executing them, and other structures for supporting such computing resources are example means for providing the functionality described in this disclosure.

[0214] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as general-purpose computers, wireless communication device mobile phones, or integrated circuit devices with multiple uses, including applications in wireless communication device mobile phones and other devices. Any features described as modules or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be implemented at least in part by a computer-readable data storage medium including a program code, which includes instructions for executing one or more of the methods, algorithms, and / or operations described above when executed. A computer-readable data storage medium may form part of a computer program product, which may include packaging materials. A computer-readable medium may include a memory or data storage medium, such as a random access memory (RAM) (such as a synchronous dynamic random access memory (SDRAM)), a read-only memory (ROM), a non-volatile random access memory (NVRAM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic or optical data storage medium, and the like. Additionally or alternatively, the techniques may be implemented at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and that can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.

[0215] The program code may be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such processors may be configured to perform any of the techniques described in this disclosure. A general-purpose processor may be a microprocessor; however, in an alternative, 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, the term "processor" as used herein may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or device suitable for implementing the techniques described herein.

[0216] It should be understood by those of ordinary skill in the art that the less than ("<") and greater than (">") symbols or terms used herein may be replaced by less than or equal to ("≤") and greater than or equal to ("≥") symbols, respectively, without departing from the scope of the present specification.

[0217] Where a component is described as being “configured to” perform certain operations, such configuration may be achieved, for example, by designing electronic circuits or other hardware to perform the operations, by programming programmable electronic circuits (e.g., a microprocessor or other suitable electronic circuits) to perform the operations, or any combination thereof.

[0218] The phrases “coupled to” or “communicatively coupled to” refer to any component being physically connected directly or indirectly to another component, and / or any component being in communication with another component directly or indirectly (e.g., connected to the other component via a wired or wireless connection and / or other suitable communication interface).

[0219] Claim language or other language stating "at least one of" a set and / or "one or more of" a set indicates that one member of the set or multiple members of the set (in any combination) satisfies the claim. For example, 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, 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, A and B and C, or any repetition is information or data (e.g., A and A, B and B, C and C, A and A and B, etc.), or any other ordering, repetition, or combination of A, B, and C. The language "at least one of" a set and / or "one or more of" a set does not limit the set to the items listed in the set. For example, 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.

[0220] Illustrative aspects of the present disclosure include:

[0221] Aspect 1. A device for wireless communication, the device comprising: at least one memory storing instructions for operating a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; and at least one processor coupled to the at least one memory and configured to: obtain an input of a front-end multi-branch layer of the machine learning model; process the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through a common trunk of the machine learning model to produce a second output; provide the second output to a back-end multi-branch layer of the machine learning model; and process the second output via a selected branch among a plurality of branches in the back-end multi-branch layer to generate a potential message having a dimension.

[0222] Aspect 2. The apparatus according to claim 1, wherein the back-end multi-branch layer comprises a plurality of linear compression branches, each of the plurality of linear compression branches being configured to compress the second output according to characteristics across frequency layers and spatial layers.

[0223] Aspect 3. An apparatus according to claim 1, wherein the dimension of the potential message is implemented by the selected branch of the backend multi-branch of the machine learning model.

[0224] Aspect 4. The apparatus of claim 1, wherein different sub-band configurations of the same dimension for the potential messages use the same compression layer associated with corresponding ones of the plurality of branches of the backend multi-branch layer.

[0225] Aspect 5. An apparatus according to claim 1, wherein the machine learning model is trained to group multiple antenna configurations into groups that map to corresponding branches among the multiple branches in the front-end multi-branch layer.

[0226] Aspect 6. An apparatus according to claim 1, wherein the variable antenna configuration is used by a base station to configure the CSI report associated with the machine learning model, and wherein the variable subband configuration is the subband associated with the CSI report.

[0227] Aspect 7. The apparatus of claim 1, wherein the dimension of the potential message is determined based on at least one of a subband mode, antenna configuration, rank, or payload configuration associated with the input.

[0228] Aspect 8. An apparatus according to claim 7, wherein the machine learning model is trained to determine the dimension of the potential message based on at least one of the subband mode, the antenna configuration, the rank, or the payload configuration associated with the input.

[0229] Aspect 9. An apparatus according to claim 8, wherein the machine learning model is trained to group multiple sub-band configurations into groups that map to corresponding branches among the multiple branches in the back-end multi-branch layer.

[0230] Aspect 10. The apparatus of claim 8, wherein, when the dimension of the potential message is determined based on the subband mode, the dimension of the potential message scales with the number of configured subbands or with a subband span.

[0231] Aspect 11. An apparatus according to claim 8, wherein, when the dimension of the potential message is determined based on the antenna configuration or the payload configuration, the back-end multi-branch layer realizes the maximum dimension value of the potential message at the corresponding compression layer associated with the corresponding branch of the back-end multi-branch layer.

[0232] Aspect 12. The apparatus of claim 8, wherein various antenna configurations mapped to the same dimension value of the potential message use the same linear compression layer associated with corresponding branches of the back-end multi-branch layer.

[0233] Aspect 13. An apparatus according to claim 8, wherein, when the dimension of the potential message is determined based on the rank, at least one of the following is performed: a first dimension set is applied to each layer associated with a corresponding branch of the back-end multi-branch layer for a first rank or a second rank, and a second dimension set is applied to each layer associated with a corresponding branch of the back-end multi-branch layer for a third rank and a fourth rank.

[0234] Aspect 14. An apparatus according to claim 1, wherein the machine learning model is trained according to at least one of a centralized training method, a distributed training method, or a separate training method.

[0235] Aspect 15. An apparatus according to claim 14, wherein, when the machine learning model is trained according to the centralized training method, an entity associated with the apparatus exposes the machine learning model architecture to a training entity and provides input samples and true values ​​to the training entity, wherein the input samples and the true values ​​include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

[0236] Aspect 16. An apparatus according to claim 14, wherein, when the machine learning model is trained according to the distributed training method, an entity associated with the apparatus communicates with a network entity, and for each iteration of communicating training data, the entity associated with the apparatus provides a true value and an activation to the network entity, wherein the true value and the activation include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

[0237] Aspect 17. An apparatus according to claim 14, wherein, when the machine learning model is trained according to the separate training method, an entity associated with the apparatus first trains an encoder and sends a potential message and a true value or an expected decoder output to a network entity, wherein the potential message and the true value or the expected decoder output include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

[0238] Aspect 18. The apparatus according to claim 1, wherein the apparatus supports only a limited number of branches in the front-end multi-branch layer.

[0239] Aspect 19. The apparatus of claim 1, wherein the apparatus supports only certain sub-band modes.

[0240] Aspect 20. The apparatus of claim 19, wherein the certain subband modes include one or more of a number of subbands, a number of subband spans, and whether the subbands are contiguous or non-contiguous.

[0241] Aspect 21. An apparatus according to claim 1, wherein the front-end multi-branch layer of the machine learning model utilizes antenna setting data in the input to select the selected branch among the multiple branches of the front-end layer.

[0242] Aspect 22. An apparatus according to claim 1, wherein the front-end multi-branch layer of the machine learning model transforms the input from a transmission domain to a feature domain.

[0243] Aspect 23. An apparatus according to claim 22, wherein the common backbone of the machine learning model extracts deep features with position encoding from the first output and generates the second output.

[0244] Aspect 24. An apparatus according to claim 1, wherein the common backbone of the machine learning model includes a position embedding layer and multiple machine learning layers.

[0245] Aspect 25. An apparatus according to claim 1, wherein the back-end multi-branch layer of the machine learning model compresses features of the second output across frequencies and layers to generate the potential message having the dimension.

[0246] Aspect 26. An apparatus according to claim 1, wherein each respective branch of the multiple branches of the back-end multi-branch layer is associated with one or more of a respective subband configuration, a respective rank, a respective antenna configuration, or a respective payload configuration.

[0247] Aspect 27. An apparatus according to claim 25, wherein the machine learning model is trained to select the selected branch among the multiple branches of the back-end multi-branch layer based on at least one of a subband mode, antenna configuration, rank, or payload configuration associated with the input.

[0248] Aspect 28. A device for wireless communication, the device comprising: a machine learning model, the machine learning model being trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; a front-end multi-branch layer of the machine learning model; a common backbone of the machine learning model; a back-end multi-branch layer of the machine learning model; at least one memory, the at least one memory storing instructions for operating the machine learning model; and at least one processor, the at least one processor being coupled to the at least one memory and configured to: receive an input of the front-end multi-branch layer of the machine learning model; process the input via a selected branch among a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through the common backbone of the machine learning model to produce a second output; provide the second output to the back-end multi-branch layer of the machine learning model; process the second output via a selected branch among a plurality of branches in the back-end multi-branch layer to generate a potential message having a dimension; and send the potential message having the dimension to a communication device via a wireless interface.

[0249] Aspect 29. A device for wireless communication, the device comprising: at least one memory; and at least one processor, the at least one processor coupled to the at least one memory and configured to: receive a channel state information (CSI) report configuration, the channel state information (CSI) report configuration comprising at least one of a CSI report subband mode configuration, an antenna configuration, a restriction on possible ranks to be reported, or a payload configuration; determine a CSI report dimension associated with an output of a machine learning model used by a user equipment to generate a CSI report based on the CSI report configuration; and generate the CSI report using the machine learning model based on the CSI report dimension.

[0250] Aspect 30. An apparatus according to claim 29, wherein the machine learning model is trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration, and the machine learning model includes a front-end multi-branch layer, a common backbone, and a back-end multi-branch layer, wherein the corresponding layers of the back-end multi-branch layer are selected based on the CSI reporting dimension.

[0251] Aspect 31. The apparatus of claim 30, wherein a corresponding layer of the front-end multi-branch layer is selected based on at least one of the antenna configuration or a grouping associated with a plurality of antenna configurations.

[0252] Aspect 32. An apparatus according to claim 29, wherein the CSI reporting dimension associated with the output of the machine learning model is scaled relative to one or more of the number of configured subbands or a subband span.

[0253] Aspect 33. An apparatus according to claim 32, wherein the CSI reporting dimension is determined based on the product of the maximum value of the CSI reporting dimension and the number of configured subbands or the subband span, or based on the product of the maximum value of the CSI reporting dimension and the ratio of the number of configured subbands to the total number of subbands or the ratio of the configured subband span to the total subband span.

[0254] Aspect 34. An apparatus according to claim 29, wherein the at least one processor is configured to: report a limited number of front-end branches associated with the machine learning model, the number of antenna configurations supported by each of the front-end branches, or at least one of supported subband modes.

[0255] Aspect 35. An apparatus according to claim 29, wherein the machine learning model associated with the configured CSI report supports multiple CSI reporting dimension maximum values ​​or multiple CSI reporting dimension values ​​for each antenna configuration or subband configuration.

[0256] Aspect 36. An apparatus according to claim 35, wherein the at least one processor is configured to: receive a payload configuration indicating a CSI reporting dimension maximum value among the multiple CSI reporting dimension maximum values ​​or a CSI reporting dimension value among the multiple CSI reporting dimension values.

[0257] Aspect 37. An apparatus according to claim 36, wherein the multiple CSI reporting dimension maximum values ​​or a subset of different CSI reporting dimension maximum values ​​or the multiple CSI reporting dimension values ​​or a subset of different CSI reporting dimension values ​​are supported by the machine learning model based on the total number of antenna ports being above or below a threshold.

[0258] Aspect 38. An apparatus according to claim 29, wherein the machine learning model associated with the configured CSI report supports a first plurality of CSI report dimension maximum values ​​or a first plurality of CSI report dimension values ​​for a first set of rank values; and supports a second plurality of CSI report dimension maximum values ​​or a second plurality of CSI report dimension values ​​for a second set of rank values.

[0259] Aspect 39. An apparatus according to claim 38, wherein, when the first set of rank values ​​is smaller than the second set of rank values, the first plurality of CSI reporting dimension maximum values ​​or the first plurality of CSI reporting dimension values ​​are greater than the second plurality of CSI reporting dimension maximum values ​​or the second plurality of CSI reporting dimension values.

[0260] Aspect 40. An apparatus according to claim 29, wherein different antenna configurations or different antenna configuration groups use different branches of the front-end multi-branch layer of the machine learning model for different linear embedding processes.

[0261] Aspect 41. An apparatus according to claim 29, wherein the variable ranks correspond to corresponding different layers of the back-end multi-branch layer of the machine learning model.

[0262] Aspect 42. An apparatus for wireless communication, the apparatus comprising: at least one memory storing instructions for operating a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; and at least one processor coupled to the at least one memory and configured to: obtain an input of a front-end multi-branch layer of the machine learning model; process the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; process the first output through a common trunk of the machine learning model to produce a second output; and generate a potential message having a dimension based on the second output.

[0263] Aspect 43. A device for wireless communication, the device comprising: at least one memory storing instructions for operating a machine learning model, the machine learning model being trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; and at least one processor coupled to the at least one memory and configured to: process an input of a common backbone of the machine learning model to produce an output; provide the output to a back-end multi-branch layer of the machine learning model; process the output via a selected branch of a plurality of branches of the back-end multi-branch layer to generate a potential message having a dimension.

[0264] Aspect 44. A method of wireless communication, the method comprising the operations according to any one of aspects 1 to 27.

[0265] Aspect 45. A non-transitory computer-readable storage medium, comprising instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to any one of Aspects 1 to 27.

[0266] Aspect 46. An apparatus for wireless communication, the apparatus comprising one or more components for performing the operations according to any one of aspects 1 to 27.

[0267] Aspect 44. A method of wireless communication, the method comprising the operations according to aspect 28 and in some aspects in combination with any one of aspects 2 to 27.

[0268] Aspect 45. A non-transitory computer-readable storage medium comprising instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to Aspect 28 and in some aspects in combination with any one of Aspects 2 to 27.

[0269] Aspect 46. An apparatus for wireless communication, the apparatus comprising one or more components for performing the operations according to Aspect 28 and in some aspects in combination with any one of Aspects 2 to 27.

[0270] Aspect 44. A method of wireless communication, the method comprising the operations according to any one of aspects 29 to 41.

[0271] Aspect 45. A non-transitory computer-readable storage medium comprising instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to any one of Aspects 29 to 41.

[0272] Aspect 46. An apparatus for wireless communication, the apparatus comprising one or more components for performing the operations of any one of aspects 29 to 41.

[0273] Aspect 44. A method of wireless communication, the method comprising the operations according to aspect 42 and in some aspects in combination with any one of aspects 2 to 27.

[0274] Aspect 45. A non-transitory computer-readable storage medium, comprising instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to Aspect 42 and in some aspects in combination with any one of Aspects 2 to 27.

[0275] Aspect 46. An apparatus for wireless communication, the apparatus comprising one or more components for performing the operations according to Aspect 42 and in some aspects in combination with any one of Aspects 2 to 27.

[0276] Aspect 44. A method of wireless communication, the method comprising the operations according to aspect 43 and in some aspects in combination with any one of aspects 2 to 27.

[0277] Aspect 45. A non-transitory computer-readable storage medium, comprising instructions stored thereon, which, when executed by at least one processor, cause the at least one processor to perform operations according to Aspect 43 and in some aspects in combination with any one of Aspects 2 to 27.

[0278] Aspect 46. An apparatus for wireless communication, the apparatus comprising one or more components for performing the operations according to Aspect 43 and in some aspects in combination with any one of Aspects 2 to 27.

Claims

1. A device for wireless communication, the device comprising: at least one memory storing instructions for operating a machine learning model trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; as well as at least one processor coupled to the at least one memory and configured to: Obtaining input of a front-end multi-branch layer of the machine learning model; Processing the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; processing the first output through a common backbone of the machine learning model to produce a second output; Providing the second output to a backend multi-branch layer of the machine learning model; and The second output is processed via a selected branch of a plurality of branches of the back-end multi-branch layer to generate a latent message having a dimension.

2. The apparatus according to claim 1, wherein the back-end multi-branch layer comprises a plurality of linear compression branches, each of the plurality of linear compression branches being configured to compress the second output according to features across frequency layers and spatial layers.

3. An apparatus according to claim 1, wherein the dimension of the potential message is implemented by the selected branch of the backend multi-branch of the machine learning model.

4. The apparatus of claim 1, wherein different sub-band configurations of the same dimension for the potential message use the same compression layer associated with corresponding ones of the plurality of branches of the backend multi-branch layer.

5. The apparatus of claim 1, wherein the machine learning model is trained to group multiple antenna configurations into groups that map to corresponding ones of the multiple branches in the front-end multi-branch layer.

6. The apparatus of claim 1 , wherein the variable antenna configuration is used by a base station to configure the CSI report associated with the machine learning model, and wherein the variable subband configuration is the subband associated with the CSI report.

7. The apparatus of claim 1, wherein the dimension of the potential message is determined based on at least one of a subband mode, an antenna configuration, a rank, or a payload configuration associated with the input.

8. An apparatus according to claim 7, wherein the machine learning model is trained to determine the dimension of the potential message based on at least one of the subband mode, the antenna configuration, the rank, or the payload configuration associated with the input.

9. The apparatus of claim 8, wherein the machine learning model is trained to group a plurality of sub-band configurations into groups that map to corresponding ones of the plurality of branches in the back-end multi-branch layer.

10. The device according to claim 8, wherein: When the dimension of the potential message is determined based on the subband mode, the dimension of the potential message scales with the number of configured subbands or with a subband span.

11. The device according to claim 8, wherein: When the dimension of the potential message is determined based on the antenna configuration or the payload configuration, the backend multi-branch layer implements a maximum dimension value of the potential message at a corresponding compression layer associated with a corresponding branch of the backend multi-branch layer.

12. The apparatus of claim 8, wherein various antenna configurations mapped to the same dimension value of the potential message use the same linear compression layer associated with corresponding branches of the back-end multi-branch layer.

13. The device according to claim 8, wherein: When the dimensions of the potential message are determined based on the rank, at least one of the following is performed: a first set of dimensions is applied to each layer associated with a corresponding branch of the back-end multi-branch layer for a first rank or a second rank, and a second set of dimensions is applied to each layer associated with a corresponding branch of the back-end multi-branch layer for a third rank and a fourth rank.

14. The apparatus of claim 1, wherein the machine learning model is trained according to at least one of a centralized training method, a distributed training method, or a separate training method.

15. The device according to claim 14, wherein: When the machine learning model is trained according to the centralized training method, an entity associated with the device exposes the machine learning model architecture to the training entity and provides input samples and true values ​​to the training entity, wherein the input samples and the true values ​​include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

16. The device according to claim 14, wherein: When the machine learning model is trained according to the distributed training method, an entity associated with the device communicates with a network entity, and for each iteration of communicating training data, the entity associated with the device provides a true value and an activation to the network entity, wherein the true value and the activation include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

17. The device according to claim 14, wherein: When the machine learning model is trained according to the separate training method, an entity associated with the device first trains an encoder and sends a potential message and a true value or an expected decoder output to a network entity, wherein the potential message and the true value or the expected decoder output include at least one of a variable supported antenna configuration, a variable supported subband configuration, a variable supported payload configuration, or a variable rank hypothesis.

18. The apparatus of claim 1, wherein the apparatus supports only a limited number of branches in the front-end multi-branch layer.

19. The apparatus of claim 1, wherein the apparatus supports only certain sub-band modes.

20. The apparatus of claim 19, wherein the certain subband modes include one or more of a number of subbands, a number of subband spans, and whether the subbands are contiguous or non-contiguous.

21. The apparatus of claim 1, wherein the front-end multi-branch layer of the machine learning model utilizes antenna setting data in the input to select the selected branch among the plurality of branches of the front-end layer.

22. The apparatus of claim 1, wherein the front-end multi-branch layer of the machine learning model transforms the input from a transmission domain to a feature domain.

23. An apparatus according to claim 22, wherein the common backbone of the machine learning model extracts deep features with position encoding from the first output and generates the second output.

24. An apparatus according to claim 1, wherein the common backbone of the machine learning model includes a position embedding layer and multiple machine learning layers.

25. The apparatus of claim 1, wherein the back-end multi-branch layer of the machine learning model compresses features of the second output across frequencies and layers to generate the potential message having the dimension.

26. The apparatus of claim 1, wherein each respective branch of the plurality of branches of the back-end multi-branch layer is associated with one or more of a respective subband configuration, a respective rank, a respective antenna configuration, or a respective payload configuration.

27. An apparatus according to claim 25, wherein the machine learning model is trained to select the selected branch among the multiple branches of the back-end multi-branch layer based on at least one of a subband mode, antenna configuration, rank, or payload configuration associated with the input.

28. An apparatus for wireless communication, the apparatus comprising: a machine learning model trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; A front-end multi-branch layer of the machine learning model; a common backbone of the machine learning model; A backend multi-branch layer of the machine learning model; at least one memory storing instructions for operating the machine learning model; as well as at least one processor coupled to the at least one memory and configured to: Receiving input of the front-end multi-branch layer of the machine learning model; Processing the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; processing the first output through the common backbone of the machine learning model to produce a second output; providing the second output to the backend multi-branch layer of the machine learning model; processing the second output via a selected branch of a plurality of branches of the backend multi-branch layer to generate a latent message having a dimension; as well as The potential message having the dimensions is sent to a communication device via a wireless interface.

29. An apparatus for wireless communication, the apparatus comprising: at least one memory; as well as at least one processor coupled to the at least one memory and configured to: receiving a channel state information (CSI) reporting configuration, the channel state information (CSI) reporting configuration comprising at least one of a CSI reporting subband mode configuration, an antenna configuration, a restriction on possible ranks to be reported, or a payload configuration; determining, based on the CSI reporting configuration, a CSI reporting dimension associated with an output of a machine learning model used by a user equipment to generate a CSI report; as well as The CSI report is generated using the machine learning model based on the CSI report dimensions.

30. An apparatus according to claim 29, wherein the machine learning model is trained to support at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration, and the machine learning model includes a front-end multi-branch layer, a common backbone, and a back-end multi-branch layer, wherein the corresponding layers of the back-end multi-branch layer are selected based on the CSI reporting dimension.

31. The apparatus of claim 30, wherein a corresponding layer of the front-end multi-branch layer is selected based on at least one of the antenna configuration or a grouping associated with a plurality of antenna configurations.

32. The apparatus of claim 29, wherein the CSI reporting dimensions associated with the output of the machine learning model are scaled relative to one or more of a number of configured subbands or a subband span.

33. An apparatus according to claim 32, wherein the CSI reporting dimension is determined based on the product of a maximum value of the CSI reporting dimension and the number of configured subbands or a subband span, or is determined based on the product of a maximum value of the CSI reporting dimension and a ratio of the number of configured subbands to the total number of subbands or a ratio of the configured subband span to the total subband span.

34. The apparatus of claim 29, wherein the at least one processor is configured to: Report at least one of a limited number of front-end branches associated with the machine learning model, a number of antenna configurations supported by each of the front-end branches, or supported sub-band modes.

35. The apparatus of claim 29, wherein the machine learning model associated with the configured CSI report supports multiple CSI reporting dimension maximum values ​​or multiple CSI reporting dimension values ​​for each antenna configuration or subband configuration.

36. The apparatus of claim 35, wherein the at least one processor is configured to: A payload configuration indicating a CSI reporting dimension maximum value among the plurality of CSI reporting dimension maximum values ​​or a CSI reporting dimension value among the plurality of CSI reporting dimension values ​​is received.

37. An apparatus according to claim 36, wherein the multiple CSI reporting dimension maximum values ​​or a subset of different CSI reporting dimension maximum values ​​or the multiple CSI reporting dimension values ​​or a subset of different CSI reporting dimension values ​​are supported by the machine learning model based on the total number of antenna ports being above or below a threshold.

38. An apparatus according to claim 29, wherein the machine learning model associated with the configured CSI report supports a first plurality of CSI report dimension maximum values ​​or a first plurality of CSI report dimension values ​​for a first set of rank values; and supports a second plurality of CSI report dimension maximum values ​​or a second plurality of CSI report dimension values ​​for a second set of rank values.

39. An apparatus according to claim 38, wherein, when the first set of rank values ​​is smaller than the second set of rank values, the first plurality of CSI reporting dimension maximum values ​​or the first plurality of CSI reporting dimension values ​​are greater than the second plurality of CSI reporting dimension maximum values ​​or the second plurality of CSI reporting dimension values.

40. An apparatus according to claim 29, wherein different antenna configurations or different antenna configuration groups use different branches of the front-end multi-branch layer of the machine learning model for different linear embedding processes.

41. An apparatus according to claim 29, wherein the variable ranks correspond to corresponding different layers of the back-end multi-branch layer of the machine learning model.

42. An apparatus for wireless communication, the apparatus comprising: at least one memory storing instructions for operating a machine learning model trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; as well as at least one processor coupled to the at least one memory and configured to: Obtaining input of a front-end multi-branch layer of the machine learning model; Processing the input via a selected branch of a plurality of branches in the front-end multi-branch layer to generate a first output; processing the first output through a common backbone of the machine learning model to produce a second output; as well as A potential message having dimensions is generated based on the second output.

43. An apparatus for wireless communication, the apparatus comprising: at least one memory storing instructions for operating a machine learning model trained to support channel state information (CSI) reporting with at least one of a variable antenna configuration, a variable subband configuration, a variable rank, or a variable payload configuration; as well as at least one processor coupled to the at least one memory and configured to: processing an input of a common backbone of the machine learning model to produce an output; Providing the output to a backend multi-branch layer of the machine learning model; The output is processed via a selected branch of a plurality of branches of the back-end multi-branch layer to generate a latent message having dimensions.

Images