UE capabilities for ai / ml

Abstract

The present disclosure provides systems, devices, apparatuses, and methods for UE capabilities for AI / ML, including computer programs encoded on storage media. A UE can receive, from a network, a request to report UE capabilities for at least one of an AI procedure or a ML procedure. The UE can transmit, to the network, an indication of one or more of: an AI capability, a ML capability, a radio capability associated with at least one of the AI procedure or the ML procedure, or a core network capability associated with at least one of the AI procedure or the ML procedure based on the request to report the UE capabilities.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit of U.S. nonprovisional patent application serial number 17 / 308,970, entitled “UE CAPABILITY FOR AI / ML”, filed May 5, 2021, the entire contents of which are expressly incorporated herein by reference. Technical Field

[0003] This disclosure generally relates to communication systems, and more specifically to user equipment (UE) capabilities for artificial intelligence (AI) and machine learning (ML). Background Technology

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies 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, Single Carrier Frequency Division Multiple Access (SC-FDMA) systems, and Time Division Synchronous Code Division Multiple Access (TD-SCDMA) systems.

[0005] These multiple access technologies have been adopted in various telecommunications standards to provide a common protocol that enables different wireless devices to communicate at the city, country, region, and even global levels. An example telecommunications standard is 5G New Radio (NR). 5G NR is part of the continuous evolution of mobile broadband released by the 3rd Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT), and other requirements). 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). Some aspects of 5G NR can be based on the 4G Long Term Evolution (LTE) standard. There is a need for further improvements to 5G NR technology. These improvements can also be applied to other multiple access technologies and telecommunications standards that adopt them. Summary of the Invention

[0006] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not a comprehensive summary of all anticipated aspects, nor is it intended to identify key or important elements of all aspects, nor to depict the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed descriptions that follow.

[0007] In one aspect of this disclosure, a method, computer-readable medium, and apparatus are provided. The apparatus can receive a request to report a user equipment (UE) capability for at least one of an artificial intelligence (AI) process or a machine learning (ML) process; and, based on the request to report the UE capability, send instructions for one or more of the following: AI capability, ML capability, radio capability associated with at least one of the AI ​​process or ML process, or core network capability associated with at least one of the AI ​​process or ML process.

[0008] In another aspect of this disclosure, a method, computer-readable medium, and apparatus are provided. The apparatus can send a request to report UE capabilities for at least one of an AI process or an ML process; and, based on the request to report UE capabilities, receive indications for one or more of the following: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​process or ML process, or core network capabilities associated with at least one of the AI ​​process or ML process.

[0009] To achieve the foregoing and related objectives, one or more aspects include the features fully described below and specifically pointed out in the claims. The following description and drawings set forth certain illustrative features of one or more aspects in detail. However, these features indicate only a few of the various ways in which the principles of each aspect can be employed, and this description is intended to include all such aspects and their equivalents. Attached Figure Description

[0010] Figure 1 This is a diagram illustrating an example of a wireless communication system and access network.

[0011] Figure 2A This is an illustration showing an example of the first frame according to various aspects of this disclosure.

[0012] Figure 2B This is a diagram illustrating an example of a downlink (DL) channel within a subframe according to various aspects of this disclosure.

[0013] Figure 2C This is an illustration of an example of a second frame according to various aspects of this disclosure.

[0014] Figure 2D This is a diagram illustrating an example of an uplink (UL) channel within a subframe according to various aspects of this disclosure.

[0015] Figure 3 This is a diagram illustrating examples of base stations and user equipment (UEs) in an access network.

[0016] Figure 4A diagram of a UE including a neural network is shown.

[0017] Figure 5 A table showing capability parameters that can be associated with UE machine learning (ML) capabilities is presented.

[0018] Figure 6 This is a flowchart illustrating the communication process between the UE and the network entity.

[0019] Figure 7 This is a flowchart of the wireless communication method at the UE.

[0020] Figure 8 This is a flowchart of the wireless communication method at the base station.

[0021] Figure 9 This is a flowchart of the wireless communication method at the base station.

[0022] Figure 10 This is a diagram illustrating an example hardware implementation for the example device.

[0023] Figure 11 This is a diagram illustrating an example hardware implementation for the example device. Detailed Implementation

[0024] The detailed description that follows, taken in conjunction with the accompanying drawings, is intended as a description of various configurations and not as representing the only configuration in which the concepts described herein can be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts.

[0025] Several aspects of a telecommunications system will now be described with reference to various apparatuses and methods. These apparatuses and methods will be described in the following detailed embodiments and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively, “elements”). These elements can be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the system as a whole.

[0026] As an example, an element, or any part of an element, or any combination of elements, may be implemented as a "processing system" including one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, system-on-a-chip (SoCs), baseband processors, field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform the various functions described throughout this disclosure. One or more processors in a processing system may execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other terms, software should be interpreted broadly as meaning instructions, instruction sets, code, code segments, program code, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc.

[0027] Accordingly, in one or more example embodiments, the described functionality can be implemented in hardware, software, or any combination thereof. If implemented in software, the functionality can be stored on or encoded as one or more instructions or code on a computer-readable medium. A computer-readable medium includes a computer storage medium. The storage medium can be any available medium accessible by a computer. By way of example, and not limitation, such a computer-readable medium can include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of types of computer-readable media, or any other medium that can be used to store computer-executable code in the form of instructions or data structures accessible by a computer.

[0028] While aspects and implementations are described herein by way of example, those skilled in the art will understand that additional implementations and use cases may arise in many different arrangements and scenarios. The innovations described herein can be implemented across many different platform types, devices, systems, shapes, sizes, and package arrangements. For example, implementations and / or uses may be via integrated chip implementations and other devices based on non-modular components (e.g., end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchasing devices, medical devices, AI-enabled devices, etc.). While some examples may or may not be specific to a particular use case or application, a wide variety of applicability to the described innovations can occur. The scope of implementations can range from chip-level or modular components to non-modular, non-chip-level implementations, and further to aggregated, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more aspects of the described innovations. In some practical settings, devices incorporating the described aspects and features may also include additional components and features for implementations and practices of the claimed and described aspects. For example, the transmission and reception of wireless signals must involve multiple components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / summers, etc.). The innovations described herein are intended to be implemented in a wide variety of devices, chip-level components, systems, distributed arrangements, end-user equipment, etc., of various sizes, shapes, and constructions.

[0029] Figure 1 This is a diagram illustrating an example of a wireless communication system and access network 100. The wireless communication system (also known as a wireless wide area network (WWAN)) includes a base station 102, a user equipment (UE) 04, an evolved packet core (EPC) 160, and another core network 190 (e.g., a 5G core (5GC)). Base station 102 may include macro cells (high-power cellular base stations) and / or small cells (low-power cellular base stations). Macro cells include base stations. Small cells include femtocells, picocells, and microcells.

[0030] Base station 102 configured for 4G LTE (collectively referred to as Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can interface with EPC 160 via a first backhaul link 132 (e.g., S1 interface). Base station 102 configured for 5G NR (collectively referred to as Next Generation RAN (NG-RAN)) can interface with core network 190 via a second backhaul link 184. Among other functions, base station 102 can also perform one or more of the following functions: transmission of 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, radio access network (RAN) sharing, multimedia broadcast multicast service (MBMS), subscriber and device tracking, RAN information management (RIM), paging, location, and warning message delivery. Base stations 102 can communicate directly or indirectly with each other on a third backhaul link 134 (e.g., an X2 interface) (e.g., via EPC 160 or core network 190). The first backhaul link 132, the second backhaul link 184, and the third backhaul link 134 can be wired or wireless.

[0031] Base station 102 can wirelessly communicate with UE 104. Each of base stations 102 can provide communication coverage for a corresponding geographic coverage area 110. Overlapping geographic coverage areas 110 may exist. For example, small cell 102' may have a coverage area 110' that overlaps with the coverage areas 110 of one or more macro base stations 102. A network that includes both small cells and macro cells can be referred to as a heterogeneous network. The heterogeneous network may also include evolved home node B (eNB) (HeNB) which can provide services to restricted groups referred to as closed subscriber groups (CSG). The communication link 120 between base station 102 and UE 104 may include uplink (UL) (also known as reverse link) transmission from UE 104 to base station 102 and / or downlink (DL) (also known as forward link) transmission from base station 102 to UE 104. The communication link 120 may use multiple-input multiple-output (MIMO) antenna technologies, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link may use one or more carriers. Base station 102 / UE 104 may use spectrum allocated per carrier up to Y MHz (e.g., 5, 10, 15, 20, 100, 400, etc.) of bandwidth in carrier aggregation for a total of up to Y x MHz (x component carriers) for transmission in each direction. Carriers may be adjacent to each other or may not be adjacent to each other. Carrier allocation may be asymmetric relative to DL and UL (e.g., more or fewer carriers may be allocated to DL compared to UL). Component carriers may include primary component carriers and one or more secondary component carriers. The primary component carrier may be referred to as the primary cell (PCell), and the secondary component carrier may be referred to as the secondary cell (SCell).

[0032] Some UEs 104 can communicate with each other using device-to-device (D2D) communication link 158. D2D communication link 158 can use DL / UL WWAN spectrum. D2D communication link 158 can use one or more sidelink channels, such as Physical Sidelink Broadcast Channel (PSBCH), Physical Sidelink Discovery Channel (PSDCH), Physical Sidelink Shared Channel (PSSCH), and Physical Sidelink Control Channel (PSCCH). D2D communication can be achieved through various wireless D2D communication systems, such as WiMedia, Bluetooth, ZigBee, Wi-Fi based on the IEEE 802.11 standard, LTE, or NR.

[0033] The wireless communication system may also include a Wi-Fi access point (AP) 150 that communicates with a Wi-Fi station (STA) 152 via a communication link 154 (e.g., in unlicensed spectrum at 5 GHz). When communicating in unlicensed spectrum, the STA 152 / AP 150 may perform a free channel assessment (CCA) before communication to determine whether the channel is available.

[0034] Small cell 102' can operate in licensed and / or unlicensed spectrum. When operating in unlicensed spectrum, small cell 102' can employ NR and use the same unlicensed spectrum (e.g., 5 GHz, etc.) as the Wi-Fi AP 150. Small cell 102' employing NR in unlicensed spectrum can improve the coverage and / or increase the capacity of the access network.

[0035] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc., based on frequency / wavelength. In 5G NR, two initial operating bands have been designated as frequency ranges FR1 (410MHz–7.125GHz) and FR2 (24.25GHz–52.6GHz). Although a portion of FR1 is greater than 6GHz, it is often (interchangeably) referred to as the “sub-6GHz” band in various documents and articles. Similar naming issues sometimes arise with FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and articles, although this differs from the Extremely High Frequency (EHF) band (30GHz–300GHz) identified as a “millimeter wave” band by the International Telecommunication Union (ITU).

[0036] The frequencies between FR1 and FR2 are generally referred to as intermediate frequency (IF) bands. Recent 5G NR studies have identified the operating bands of these IF bands as the frequency range designation FR3 (7.125GHz-24.25GHz). Bands falling within FR3 can inherit FR1 and / or FR2 characteristics, and thus can effectively extend the features of FR1 and / or FR2 to IF band frequencies. Furthermore, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6GHz. For example, three higher operating frequency bands have been identified as the frequency range names FR4a or FR4-1 (52.6GHz-71GHz), FR4 (52.6GHz-114.25GHz), and FR5 (114.25GHz-300GHz). Each of these higher frequency bands falls within the EHF band.

[0037] In light of the foregoing, unless otherwise specified, it should be understood that the terms "sub-6GHz," if used herein, can broadly refer to frequencies that are less than 6GHz, within FR1, or may include intermediate frequency bands. Furthermore, unless otherwise specified, it should be understood that the terms "millimeter wave," if used herein, can broadly refer to frequencies that may include intermediate frequency bands, within FR2, FR4, FR4-a, or FR4-1 and / or FR5, or within the EHF band.

[0038] Base station 102 (whether a small cell 102' or a large cell (e.g., a macro base station)) may include and / or be referred to as an eNB, gNodeB (gNB), or another type of base station. Some base stations (such as gNB 180) may operate in conventional sub-6 GHz spectrum, millimeter wave frequencies, and / or near-millimeter wave frequencies to communicate with UE 104. When gNB 180 operates in millimeter wave or near-millimeter wave frequencies, gNB 180 may be referred to as a millimeter wave base station. Millimeter wave base station 180 may utilize beamforming 182 with UE 104 to compensate for path loss and short range. Base station 180 and UE 104 may each include multiple antennas (such as antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming.

[0039] Base station 180 may transmit beamforming signals to UE 104 in one or more transmit directions 182'. UE 104 may receive beamforming signals from base station 180 in one or more receive directions 182'. UE 104 may also transmit beamforming signals to base station 180 in one or more transmit directions. Base station 180 may receive beamforming signals from UE 104 in one or more receive directions. Base station 180 / UE 104 may perform beam training to determine the optimal receive and transmit directions for each of base station 180 / UE 104. The transmit and receive directions of base station 180 may be the same or different. The transmit and receive directions of UE 104 may be the same or different.

[0040] EPC 160 may include Mobility Management Entity (MME) 162, other MMEs 164, Serving Gateway 166, Multimedia Broadcast Multicast Service (MBMS) Gateway 168, Broadcast Multicast Service Center (BM-SC) 170, and Packet Data Network (PDN) Gateway 172. MME 162 can communicate with Home Subscriber Server (HSS) 174. MME 162 is the control node that handles signaling between UE 104 and EPC 160. Typically, MME 162 provides bearer and connection management. All user Internet Protocol (IP) packets are transmitted through Serving Gateway 166, which is itself connected to PDN Gateway 172. PDN Gateway 172 provides UE IP address allocation and other functions. PDN Gateway 172 and BM-SC 170 are connected to IP Service 176. IP Service 176 may include the Internet, intranet, IP Multimedia Subsystem (IMS), PS streaming service, and / or other IP services. The BM-SC 170 provides functionality for MBMS user service provisioning and delivery. It can serve as an entry point for content provider MBMS transmissions, authorize and initiate MBMS bearer services within a Public Land Mobile Network (PLMN), and schedule MBMS transmissions. The MBMS gateway 168 can distribute MBMS services to base stations 102 belonging to Multicast-Broadcast Single Frequency Network (MBSFN) areas belonging to broadcast-specific services, and can be responsible for session management (start / stop) and collecting billing information related to eMBMS.

[0041] The core network 190 may include Access and Mobility Management Functions (AMF) 192, other AMFs 193, Session Management Functions (SMF) 194, and User Plane Functions (UPF) 195. AMF 192 may communicate with Unified Data Management (UDM) 196. AMF 192 is the control node that handles signaling between UE 104 and the core network 190. Typically, AMF 192 provides QoS flow and session management. All user Internet Protocol (IP) packets are transmitted through UPF 195. UPF 195 provides UE IP address allocation and other functions. UPF 195 connects to IP services 197. IP services 197 may include the Internet, intranets, IP Multimedia Subsystem (IMS), Packet Switched (PS) Streaming (PSS) services, and / or other IP services.

[0042] Base stations may include and / or be referred to as gNB, B-node, eNB, access point, base transceiver station, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), transmit / receive point (TRP), or some other suitable term. Base station 102 provides UE 104 with access to EPC 160 or core network 190. Examples of UE 104 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, GPS devices, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablet computers, smart devices, wearable devices, vehicles, electricity meters, air pumps, large or small kitchen appliances, healthcare devices, implants, sensors / actuators, displays, or any other similarly functional devices. Some UE 104 devices may be referred to as IoT devices (e.g., parking timers, air pumps, toasters, vehicles, heart monitors, etc.). UE104 may also be referred to as a station, mobile station, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handheld device, user agent, mobile client, client, or any other suitable term.

[0043] Refer again Figure 1 In some aspects, base station 180 may include UE capability requester component 199, configured to: send a request to report UE capabilities for at least one of an AI process or a machine learning (ML) process; and, based on the request to report UE capabilities, receive indications for one or more of the following: AI capability, ML capability, radio capability associated with at least one of the AI ​​process or ML process, or core network capability associated with at least one of the AI ​​process or ML process. In some aspects, UE 104 may include UE capability indicator component 198, configured to: receive a request to report UE capabilities for at least one of the AI ​​process or ML process; and, based on the request to report UE capabilities, send indications for one or more of the following: AI capability, ML capability, radio capability associated with at least one of the AI ​​process or ML process, or core network capability associated with at least one of the AI ​​process or ML process. Although the following description may focus on 5G NR, the concepts described herein are applicable to other similar fields, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies.

[0044] Figure 2A Figure 200 shows an example of the first subframe within a 5G NR frame structure. Figure 2BFigure 230 shows an example of a DL channel within a 5G NR subframe. Figure 2C Figure 250 shows an example of a second subframe within a 5G NR frame structure. Figure 2D Figure 280 illustrates an example of a UL channel within a 5G NR subframe. The 5G NR frame structure can be Frequency Division Duplex (FDD), where for a given set of subcarriers (carrier system bandwidth), subframes within that set are dedicated to either DL or UL, or it can be Time Division Duplex (TDD), where for a given set of subcarriers (carrier system bandwidth), subframes within that set are dedicated to both DL and UL. Figure 1 In the provided example. Figure 2A , Figure 2C In this example, we assume the 5G NR frame structure is TDD, where subframe 4 is configured with slot format 28 (primarily DL), where D is DL, U is UL, and F is flexibly used between DL / UL, and subframe 3 is configured with slot format 1 (all UL). Although subframes 3 and 4 are shown as having slot formats 1 and 28, respectively, any particular subframe can be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are all DL and UL, respectively. Other slot formats 2-61 include a mixture of DL, UL, and flexible symbols. The UE configures the slot format via a receive slot format indicator (SFI) (dynamically via DL control information (DCI) or semi-statically / statically via radio resource control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0045] Figure 1 Figures 2A to 2DThe frame structure is illustrated, and aspects of this disclosure are applicable to other wireless communication technologies that may have different frame structures and / or different channels. A frame (10 ms) can be divided into 10 equal-sized subframes (1 ms). Each subframe may include one or more time slots. Subframes may also include micro-time slots, which may include 7, 4, or 2 symbols. Each time slot may include 14 or 12 symbols, depending on whether the cyclic prefix (CP) is normal or extended. For normal CP, each time slot may include 14 symbols, and for extended CP, each time slot may include 12 symbols. Symbols on the DL can be CP Orthogonal Frequency Division Multiplexing (OFDM) (CP-OFDM) symbols. Symbols on the UL can be CP-OFDM symbols (for high-throughput scenarios) or Discrete Fourier Transform (DFT) Extended OFDM (DFT-s-OFDM) symbols (also known as Single Carrier Frequency Division Multiple Access (SC-FDMA) symbols) (for power-constrained scenarios, limited to single-stream transmission). The number of time slots within a subframe is based on the CP and digital scheme. The parameter set defines the subcarrier spacing (SCS) and effectively defines the symbol length / duration, which is equal to 1 / SCS.

[0046]

[0047] For a normal CP (14 symbols / slot), different parameter sets μ0 through 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For an extended CP, parameter set 2 allows 4 slots per subframe. Therefore, for a normal CP and parameter set μ, there are 14 symbols / slots and 2... μ One time slot / subframe. The subcarrier spacing can be equal to 2. μ *15kHz, where μ is the parameter set from 0 to 4. Therefore, parameter set μ = 0 has a subcarrier spacing of 15kHz, and parameter set μ = 4 has a subcarrier spacing of 240kHz. The symbol length / duration is inversely proportional to the subcarrier spacing. Figures 2A to 2D An example of normal CP is provided, with 14 symbols per slot and a parameter set μ = 2, and 4 slots per subframe. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs. Within the frame set, one or more different bandwidth portions (BWPs) of frequency division multiplexing can exist (see [link to example]). Figure 2B Each BWP can have a specific set of parameters and CP (normal or extended).

[0048] A resource grid can be used to represent the frame structure. Each time slot consists of a resource block (RB) that extends 12 consecutive subcarriers (also known as a physical RB (PRB)). The resource grid is divided into multiple resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0049] like Figure 2A As shown, some REs carry reference (pilot) signals (RS) for the UE. RSs may include demodulation RS (DM-RS) (indicated as R for a specific configuration, but other DM-RS configurations are possible) and channel state information reference signals (CSI-RS) for channel estimation at the UE. RSs may also include beam measurement RS (BRS), beam refinement RS (BRRS), and phase tracking RS (PT-RS).

[0050] Figure 2B Examples of various DL channels within a subframe of a frame are shown. The Physical Downlink Control Channel (PDCCH) carries the DCI within one or more Control Channel Elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE comprising six RE Groups (REGs), each REG comprising 12 coherent REs in the OFDM symbols of the RB. The PDCCH within a BWP may be referred to as a Control Resource Set (CORESET). The UE is configured to monitor PDCCH candidates in a PDCCH search space (e.g., a shared search space, a UE-specific search space) during PDCCH monitoring timing on the CORESET, where the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at higher and / or lower frequencies across the channel bandwidth. The Primary Synchronization Signal (PSS) may be within symbol 2 of a specific subframe of the frame. UE 104 uses the PSS to determine subframe / symbol timing and physical layer identification. The Secondary Synchronization Signal (SSS) may be within symbol 4 of a specific subframe of the frame. The UE uses the SSS to determine the Physical Layer Cell Identifier Group Number and radio frame timing. Based on the Physical Layer Identifier and the Physical Layer Cell Identifier Group Number, the UE can determine the Physical Cell Identifier (PCI). Based on the PCI, the UE can determine the location of the DM-RS. The Physical Broadcast Channel (PBCH), carrying the Master Information Block (MIB), can be logically grouped with the PSS and SSS to form a Synchronization Signal (SS) / PBCH block (also known as an SS block (SSB)). The MIB provides multiple RBs and System Frame Numbers (SFNs) in the system bandwidth. The Physical Downlink Shared Channel (PDSCH) carries user data, broadcast system information not transmitted via the PBCH (such as System Information Blocks (SIBs)), and paging messages.

[0051] like Figure 2CAs shown, some REs in the REs carry DM-RS for channel estimation at the base station (indicated as R for a specific configuration, but other DM-RS configurations are possible). The UE can transmit DM-RS for the Physical Uplink Control Channel (PUCCH) and DM-RS for the Physical Uplink Shared Channel (PUSCH). The PUSCH DM-RS can be transmitted in the first or second symbol of the PUSCH. The PUCCH DM-RS can be transmitted in different configurations depending on whether a short or long PUCCH is transmitted and on the specific PUCCH format used. The UE can transmit a Sounding Reference Signal (SRS). The SRS can be transmitted in the last symbol of a subframe. The SRS can have a comb structure, and the UE can transmit the SRS on one of the combs. The SRS can be used by the base station for channel quality estimation to implement frequency-dependent scheduling on the UL.

[0052] Figure 2D Examples of various UL channels within a subframe of a frame are shown. The PUCCH can be positioned as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), precoding matrix indicators (PMI), rank indicators (RI), and hybrid automatic repeat request (HARQ) acknowledgment (ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACKs and / or negative ACKs (NACKs)). The PUCCH carries data and can also be used to carry buffer status reports (BSR), power headroom reports (PHR), and / or UCI.

[0053] Figure 3This is a block diagram showing the communication between base station 310 and UE 350 in the access network. In the DL, IP packets from EPC 160 can be provided to controller / processor 375. Controller / processor 375 implements Layer 3 and Layer 2 functions. Layer 3 includes the Radio Resource Control (RRC) layer, and Layer 2 includes the Serving Data Adaptation Protocol (SDAP) layer, Packet Data Convergence Protocol (PDCP) layer, Radio Link Control (RLC) layer, and Media Access Control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-Radio Access Technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with upper-layer packet data unit (PDU) transmission, error correction via ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction via HARQ, priority handling, and logical channel prioritization.

[0054] Transmit (TX) processor 316 and receive (RX) processor 370 implement Layer 1 functions associated with various signal processing functions. Layer 1, including the physical (PHY) layer, may include error detection on the transport channel, forward error correction (FEC) encoding / decoding of the transport channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. TX processor 316 processes the mapping to the signal constellation diagram based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), M-order quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols can then be split into parallel streams. Each stream can then be mapped to OFDM subcarriers, multiplexed with a reference signal (e.g., a pilot) in the time and / or frequency domains, and subsequently combined using inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time-domain OFDM symbol stream. The OFDM streams are spatially precoded to produce multiple spatial streams. The channel estimate from channel estimator 374 can be used to determine the decoding and modulation scheme and for spatial processing. The channel estimate can be derived based on a reference signal transmitted by UE 350 and / or channel condition feedback. Each spatial stream can then be provided to a different antenna 320 via a separate transmitter 318TX. Each transmitter 318TX can use the corresponding spatial stream to modulate a radio frequency (RF) carrier for transmission.

[0055] At UE 350, each receiver 354RX receives signals through its corresponding antenna 352. Each receiver 354RX recovers the information modulated onto the RF carrier and provides this information to the receive (RX) processor 356. The TX processor 368 and RX processor 356 implement Layer 1 functions associated with various signal processing functions. The RX processor 356 can perform spatial processing on the information to recover any spatial streams destined for UE 350. If multiple spatial streams are destined for UE 350, the RX processor 356 can combine them into a single OFDM symbol stream. The RX processor 356 then uses a Fast Fourier Transform (FFT) to transform the OFDM symbol stream from the time domain to the frequency domain. The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols and reference signals on each subcarrier are recovered and demodulated by determining the most probable signal constellation points transmitted by base station 310. These soft decisions can be based on channel estimates calculated by channel estimator 358. The soft decision is then decoded and deinterleaved to recover the data and control signals originally transmitted by base station 310 on the physical channel. The data and control signals are then provided to controller / processor 359, which implements Layer 3 and Layer 2 functions.

[0056] The controller / processor 359 may be associated with a memory 360 that stores program code and data. The memory 360 may be referred to as a computer-readable medium. In the UL, the controller / processor 359 provides demultiplexing, packet reassembly, decryption, header decompression, and control signal processing between transport and logical channels to recover IP packets from the EPC 160. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0057] Similar to the functions described in conjunction with DL transmissions performed by base station 310, controller / processor 359 provides: RRC layer functions associated with system information (e.g., MIB, SIB) acquisition, RRC connectivity, and measurement reporting; PDCP layer functions associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functions associated with upper-layer PDU transmission, error correction via ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs to TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction via HARQ, priority handling, and logical channel prioritization.

[0058] The TX processor 368 can use the channel estimator 358 to select appropriate decoding and modulation schemes based on a reference signal transmitted by the base station 310 or a feedback-derived channel estimate, and to facilitate spatial processing. The spatial stream generated by the TX processor 368 can be provided to different antennas 352 via individual transmitters 354TX. Each transmitter 354TX can use the corresponding spatial stream to modulate an RF carrier for transmission.

[0059] UL transmissions are processed at base station 310 in a manner similar to that described in conjunction with the receiver function at UE 350. Each receiver 318RX receives signals via its corresponding antenna 320. Each receiver 318RX recovers the information modulated onto the RF carrier and provides that information to the RX processor 370.

[0060] The controller / processor 375 may be associated with a memory 376 that stores program code and data. The memory 376 may be referred to as a computer-readable medium. In the UL, the controller / processor 375 provides demultiplexing, packet reassembly, decryption, header decompression, and control signal processing between the transport and logical channels to recover IP packets from the UE 350. IP packets from the controller / processor 375 can be provided to the EPC 160. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0061] At least one of the TX processor 368, RX processor 356, and controller / processor 359 can be configured to combine Figure 1 The UE capability indicator component 198 performs various aspects.

[0062] At least one of the TX processor 316, RX processor 370, and controller / processor 375 can be configured to combine Figure 1 The UE capability requester component 199 performs various aspects.

[0063] Wireless communication systems can be configured to share available system resources and provide various telecommunications services (e.g., telephony, video, data, messaging, broadcasting, etc.) based on multiple access technologies that support communication with multiple users (such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, TD-SCDMA, etc.). In many cases, common protocols that facilitate communication with wireless devices are adopted across various telecommunications standards. For example, communication methods associated with eMBB, mMTC, and URLLC can be incorporated into the 5G NR telecommunications standard, while others can be incorporated into the 4G LTE standard. As mobile broadband technology is part of continuous evolution, further improvements to mobile broadband remain useful for the continued development of this technology.

[0064] The UE can use machine learning algorithms, deep learning algorithms, neural networks, or advanced signal processing methods for various aspects of wireless communication, such as with a base station, TRP, another UE, etc. In some aspects described herein, the coding device (e.g., the UE) can train one or more neural networks to learn the dependence of measured quality on individual parameters.

[0065] Figure 4A diagram 400 illustrates a UE 402 including a neural network 406 configured to determine communication with a second device 404. In some examples, the second device 404 may be a base station. In some examples, the second device 404 may be a TRP. In some examples, for example, if communication between the UE 402 and the second device 404 is based on a side link, the second device 404 may be another UE.

[0066] Examples of machine learning models or neural networks that may be included in UE 402 include: Artificial Neural Networks (ANNs); Decision Tree Learning; Convolutional Neural Networks (CNNs); Deep Learning Architectures in which the output of a first layer of neurons becomes the input of a second layer of neurons, etc.; Support Vector Machines (SVMs), for example, including a separating hyperplane (e.g., a decision boundary) for classifying data; Regression Analysis; Bayesian Networks; Genetic Algorithms; Deep Convolutional Networks (DCNs) configured with additional pooling and normalization layers; and Deep Belief Networks (DBNs).

[0067] Machine learning models (such as artificial neural networks (ANNs)) may comprise a set of interconnected artificial neurons (e.g., neuron models) and may be computing devices or methods that can be represented by computing devices. The connections in a neuron model can be modeled as weights. Machine learning models can provide predictive modeling, adaptive control, and other applications by being trained on a dataset. Models can adapt based on external or internal information processed by the machine learning model. Machine learning can provide nonlinear statistical data models or decision-making and can model complex relationships between input data and output information.

[0068] Machine learning models can include multiple layers and / or operations, which can be formed by cascading one or more of the referenced operations. Examples of operations that may be involved include various feature extractions of data, convolution operations, fully connected operations that can be activated or deactivated, compression, decompression, quantization, flattening, etc. As used herein, the term "layer" in a machine learning model can be used to refer to an operation on the input data. For example, convolutional layers, fully connected layers, etc., can be used to refer to the associated operations on the data input into the layer. A convolution A x B operation refers to the operation of transforming multiple input features A into multiple output features B. "Kernel size" can refer to multiple adjacent coefficients combined in a dimension. As used herein, "weight" can be used to refer to one or more coefficients used in operations in layers that combine the individual rows and / or columns of the input data. For example, a fully connected layer operation may have an output y determined at least in part based on the sum of the product of the input matrix x and the weights A (which may be matrices) and the bias B (which may be matrices). The term "weight" can be used in this document to generally refer to both weights and biases. Weights and biases are examples of parameters of a trained machine learning model. Different layers of a machine learning model can be trained independently.

[0069] Machine learning models can include various connection patterns, such as any of feedforward networks, hierarchical structures, recursive architectures, feedback connections, etc. The connections between layers of a neural network can be fully connected or locally connected. In a fully connected network, neurons in the first layer can pass their outputs to every neuron in the second layer, and every neuron in the second layer can receive inputs from every neuron in the first layer. In a locally connected network, neurons in the first layer can connect to a limited number of neurons in the second layer. In some aspects, convolutional networks can be locally connected and configured with shared connection strengths associated with the inputs of each neuron in the second layer. Locally connected layers of a network can be configured such that each neuron in a layer has the same or similar connectivity pattern but different connection strengths.

[0070] Machine learning models or neural networks can be trained. For example, a machine learning model can be trained based on supervised learning. During training, inputs can be presented to the machine learning model, which uses these inputs to compute and produce an output. The actual output can be compared to a target output, and the difference can be used to adjust the parameters of the machine learning model (such as weights and biases) to provide an output closer to the target output. Before training, the output may be incorrect or inaccurate, and the error or difference between the actual output and the target output can be calculated. The weights of the machine learning model can then be adjusted so that the output is more closely aligned with the target. To adjust the weights, the learning algorithm can compute the gradient vector of the weights. The gradient indicates the amount by which the error will increase or decrease if the weights are adjusted slightly. At the top layers, the gradient can directly correspond to the values ​​of the weights connecting the activated neurons in the penultimate layer to the neurons in the output layer. In lower layers, the gradient can depend on the values ​​of the weights and the error gradient computed in the higher layers. The weights can then be adjusted to reduce the error or move the output closer to the target. This way of adjusting the weights can be called backpropagation through the neural network. This process can continue until the achievable error rate stops decreasing or until the error rate has reached the target level.

[0071] A machine learning model can include computational complexity and the actual processor used to train the machine learning model. Figure 4 An example neural network 406 is shown, which may include a network of interconnected nodes. The output of one node is connected as input to another node. The connection between nodes may be called an edge, and weights may be applied to the connection / edge to adjust the output from one node as input to another node. A threshold may be applied to a node to determine whether or when to provide an output to a connected node. The output of each node may be computed as a nonlinear function of the sum of the node's inputs. Neural network 406 may include any number of nodes and any type of connection between nodes. Neural network 406 may include one or more hidden nodes. Nodes may be aggregated into layers, and different layers of the neural network may perform different kinds of transformations on the input. A signal may travel from an input at the first layer through multiple layers of the neural network to the output at the last layer of the neural network, and may traverse layers multiple times. As an example, the UE may input information 410 into neural network 406 and may receive output 412. The UE may report information 414 to a second device 404 based on output 412. In some aspects, the second device may send communication to the UE 402 based on information 414. In some respects, device 404 can be a base station that schedules or configures UE 402 based on information 414.

[0072] Figure 5Table 500 shows capability parameters that can be associated with UE ML capabilities. AI / ML models can be trained based on the function Y = F(X). In each respect, F, X, and Y can be based on predetermined protocols used to configure the UE in association with the AI / ML model, determined by the network. The two types of radio capabilities associated with the UE can include UE radio capabilities and UE core network capabilities. The UE's radio capabilities can be indicated by the function F, which can correspond to either a generated function / feature or a predetermined function / feature.

[0073] The network can use the UE's radio capabilities to determine whether the UE is configured for AI / ML model-based functions. Thus, the UE's radio capabilities can include bits indicating one or more supported functions F of the UE. These bits may correspond to a list of functions the UE is configured to perform. Each function can be indicated based on a single bit. Therefore, functions that can be performed based on an algorithmic process can alternatively be performed based on a neural network process. To enable the UE to indicate that it supports a specific function F, the UE may have at least one model tested against that feature. The UE can indicate that its capability bits can be used for each access layer (AS) function associated with the AI / ML model.

[0074] UE core network capabilities can correspond to two capability subtypes: Mobility Management (MM) and Session Management (SM). UE core network capabilities for MM can be determined by the AMF (e.g., AMF 192) to determine whether to use AI / ML model-based functions for the UE on MM. UE core network capabilities for SM can be determined by the SMF (e.g., SMF 194) to determine whether to use AI / ML model-based functions for the UE on SM. For each MM and / or SM function associated with an AI / ML model, UE capability bits can be indicated for the UE core network capability on MM and / or SM. Therefore, for UE core network capabilities, function F can be used for both MM and SM. For UE radio capabilities, the UE can indicate support for a list of supported functions F, where function F can be a radio-related function.

[0075] In some aspects, the UE may support a third type of radio, which may include UE AI / ML capabilities (also referred to as UE ML capabilities). UE ML capabilities can be based on the ML plane between the UE and the network. UE ML capabilities for AI / ML can be used by AI / ML entities to determine one or more AI / ML functions supported by the UE. That is, the UE's capabilities can be determined via UE ML capabilities.

[0076] UE ML capabilities can be based on one or more capability parameters, such as Figure 5Any example capability parameter indicated in Table 500. For example, the first capability parameter may correspond to processing power. Processing power may include training processing power, inference processing power, and / or total processing power. Each type of processing power can be indicated in trillions of operations per second (TOPS). For example, an AI engine may be based on 15 top operations.

[0077] The second capability parameter may correspond to memory capability. Memory capability may include the maximum model size for training and / or the maximum model size for inference. The third capability parameter may correspond to general hardware acceleration capability, which may be associated with the neural network processor. General hardware acceleration capability may include determining (e.g., yes / no) whether the AI ​​processor can be used for training. General hardware acceleration capability may also include determining (e.g., yes / no) whether the AI ​​processor can be used for inference. Hardware acceleration operations of general hardware acceleration capability may be indicated via a list of supported operations / instructions (e.g., based on two-dimensional (2D) convolution). Capability bits may indicate to the neural network processor a list of instructions for the ML procedures supported by the UE. The fourth capability parameter may correspond to the libraries supported by the UE, which may indicate the software capabilities of the UE. For example, a particular ML function may be based on a particular library.

[0078] The fifth capability parameter can correspond to the supported model formats. For example, supported model formats may include Open Neural Network Exchange (ONNX) and / or Tensor Stream (TF). Supported model formats can be indicated via a list of supported formats. ML models can also be compressed. Therefore, the capability parameter can further indicate whether model compression is included in the supported model formats (e.g., yes / no). The sixth capability parameter can correspond to the supported models (e.g., a list of models based on UE testing and caching). While an ML model can indicate a function F(X), different UEs using different models can support the same function F. Therefore, the capability parameter can indicate the ML models supported by different UEs.

[0079] The seventh capability parameter can correspond to maximum concurrency, which may include maximum model training, maximum model inference, and / or maximum training and inference. Maximum model training can be based on the maximum number of concurrent model trainings that the UE can execute simultaneously, maximum model inference can be based on the maximum number of current model inferences that the UE can execute simultaneously, and maximum training and inference can be based on the maximum total number of concurrent model training and inferences that the UE can execute simultaneously. The eighth capability parameter can correspond to model combinations, which may include one or more tested model combinations. If ML models are to be executed simultaneously, the UE can indicate the model combinations supported by the UE via a list of model combinations. The UE can support a certain number of model combinations, such as UE_model_a+Network_model_b; UE_model_1+UE_model_2+UE_model_3; etc. A tested model combination can refer to a model combination that has been confirmed for the UE, but the UE can also support other untested / unconfirmed model combinations. The ninth capability parameter can correspond to quantization. For the ML model training and inference process, the ML model can be converted into different formats to improve the execution efficiency of the ML model. The conversion of the ML model can be called quantization. Quantization can include data-free quantization and / or quantization-aware training.

[0080] Figure 6 This is a flowchart 600 illustrating communication between UE 602 and a network entity. The network entity may include a base station 604 and a core network entity of the core network 606. At 608a, UE 602 can receive a UE capability request for the AI / ML procedure from base station 604. The UE capability request may correspond to a UECapabilityEnquiry message. At 608a, the UE capability request can also be received based on an indication from the core network 606 (e.g., via base station 604). At 610a, UE 602 can send a UE capability indication to base station 604. The UE capability indication may correspond to a UECapabilityInformation message. At 610a, a UE capability request can also be sent to the core network 606 (e.g., via base station 604).

[0081] UE capability indications may be associated with UE capability list 612. UE capability list 612 may include UE radio capabilities 612(1), UE core network capabilities 612(2), and UE ML capabilities 612(3). UE radio capabilities 612(1) may be based on a single or separate AS-based indication. UE core network capabilities may be based on a single or separate MM / SM indication. UE ML capabilities 612(3) may be based on one or more capability parameters indicated in Table 500.

[0082] At 614a, UE 602 can send UE ML capabilities, included in its radio capabilities, to base station 604. At 614c, these radio capabilities can be further sent to core network 606 via base station 604. In this example, the UE radio capabilities can be indicated based on a radio capability identifier (ID). At 616a, UE 602 can send UE ML capabilities, included in its core network (CN) capabilities, to base station 604. At 616c, the core network (CN) capabilities can be further sent to core network 606 via base station 604. At 618a, UE 602 can send a separate information element (IE) for the UE ML capabilities to base station 604. At 618c, this separate information element (IE) can be further sent to core network 606 via base station 604. In this example, the UE ML capabilities can be indicated based on an AI / ML capability ID.

[0083] In a configuration where base station 604 receives UE capability information for UE 602 (which may indicate UE radio capability 612(1), UE core network capability 612(2), and / or UE ML capability 612(3)), base station 604 may report the UE capability information to core network 606 (e.g., at 614c, 616c, and / or 618c). In a configuration where core network 606 receives UE capability information for UE 602 (which may indicate UE radio capability 612(1), UE core network capability 612(2), and / or UE ML capability 612(3)), core network 606 may report the UE capability information to base station 604 serving UE 602 (e.g., at 614b, 616b, and / or 618b).

[0084] In a first aspect, the UE ML capability 612(3) can be reported at 614a via the UE radio capability 612(1). For example, the UE radio capability 612(1) may indicate a supported list of functions that can be performed in association with a neural network, wherein the UE ML capability 612(3) may correspond to a single capability. If the UE ML capability 612(3) is signaled within the UE radio capability 612(1), the delivery of the UE ML capability 612(3) may be similar to the delivery of the UE radio capability 612(1). The UE 602 may report the ML capability container to the base station 604 via RRC in association with the signaling of the UE radio capability 612(1). At 608a, the base station 604 may request the UE radio capability 612(1) from the UE 602 based on the UECapabilityEnquiry message, and at 610a, the UE 602 may report the UE radio capability 612(1) based on the UECapabilityInformation message. Filters can be applied to allow base station 604 to request UE ML capability 612(3) separately at 608a and / or to allow UE 602 to report ML UE capability 612(3) separately at 618a.

[0085] UE radio capability 612(1) can be cached at core network 606. For example, UE 602 may report UE capability information to base station 604 at 610a, and base station 604 may relay the UE capability information to core network 606 at 610b for caching the UE capability information. During RRC connection establishment, core network 606 may send UE capability information to base station 604 (e.g., at 614b, 616b, and / or 618b). If core network 606 does not have UE capability information stored in the cache, base station 604 may request UE 602 to provide the UE capability information. Base station 604 may report ML capability containers to core network 606 (e.g., AMF / SMF) for caching / storage during RRC_IDLE state.

[0086] In a second aspect, UE ML capability 612(3) can be reported at 616a via UE core network capability 612(2). If UE ML capability 612(3) is reported to UE core network capability 612(2) at 616a, the delivery of UE ML capability 612(3) can be similar to the delivery of UE core network capability 612(2). For example, UE 602 can report the ML capability container associated with UE core network capability 612(2) to AMF / SMF via NAS. UE core network capability 612(2) of MM can be reported to AMF during NAS registration. UE core network capability 612(2) for SM can be reported to SMF during PDU session management. AMF / SMF can send the ML capability container to base station 604 so that base station 604 can determine the ML capability of UE 602.

[0087] In the third aspect, the UE ML capability 612(3) can be reported as a separate capability IE at 618a. That is, the UE ML capability 612(3) is not reported together with the UE radio capability 612(1) or the UE core network capability 612(2). For example, the ML capability container can be reported to the ML-related network entity / node based on signaling performed on the ML plane. A signaling connection can be established between the UE 602 and the ML-related network entity / node to signal the UE ML capability 612(3). The signaling can be performed via RRC, NAS, U plane (e.g., Hypertext Transfer Protocol (HTTP)), etc. In the configuration, the ML plane can be a plane separate from the control plane (C plane) or the user plane (U plane).

[0088] In another example, at 618a, the ML capability container may be reported as a separate IE along with the transmission of UE radio capability 612(1) at 614a in the same signaling process as UE radio capability 612(1), but not via UE radio capability 612(3). Based on the UECapabilityEnquiry message received from base station 604 at 608a, the ML capability container may be an additional IE included in the UECapabilityInformation message sent to base station 604 at 610a. The UECapabilityEnquiry message may also be configured for base station 604 to request ML capabilities separately. At 610b, base station 604 may forward the ML capability container to 5GC (e.g., AMF / SMF) for caching / storage. In a similar example, at 618a, the ML capability container may be reported as a separate IE along with the transmission of UE core network capability 612(2) at 616a in the same signaling process as UE core network capability 612(2), but not via UE core network capability 612(2). The ML capability container may be included as an optional / separate IE in a NAS message indicating UE core network capability 612(2). The core network 606 may then forward the ML capability container (e.g., at 614b, 616b and / or 618b) to the base station 604.

[0089] In another example, an RRC procedure can be defined for UE ML capability requests and reports, where base station 604 can forward the ML capability container to 5GC. In yet another example, a NAS procedure can be defined for UE ML capability requests and reports. NAS can correspond to signaling between UE 602 and core network 606, such that the NAS procedure can be used to report UE ML capability 612(3). When core network 606 receives UE ML capability 612(3), core network 606 can forward the ML capability container (e.g., at 614b, 616b, and / or 618b) to base station 604 for use in RAN procedures.

[0090] Since the core network 606 and the RAN can configure the UE 602 independently based on the ML function, the UE ML capability 612(3) can be shared between the AS and NAS. If the UE ML capability 612(3) is reported to the base station 604, the base station 604 can forward the UE ML capability 612(3) to the core network 606 at 610b (e.g., AMF / SMF). The base station 604 can also instruct the resource allocation between the RAN and the core network 606 (e.g., based on the maximum processing capacity of the core network 606, the maximum memory of the core network 606, etc.). If the UE ML capability 612(3) is reported to the core network 606, the core network 606 can forward the UE ML capability 612(3) to the RAN (e.g., at 614b, 616b and / or 618b). The core network 606 can also instruct resource allocation (e.g., based on the maximum processing capacity of the RAN, the maximum memory of the RAN, etc.). The resource / capability allocation between the RAN and the core network 606 can be determined by the RAN.

[0091] In other cases, resource / capability allocation can be determined by UE 602. For example, UE 602 can allocate capabilities into UE AS ML capabilities and UE NAS ML capabilities, and report the capabilities to the RAN and core network 606 respectively. UE 602 can also determine the percentage of capabilities to be used for core network-related ML procedures and the percentage of capabilities to be used for RAN-related ML procedures.

[0092] The UE radio capability ID can be used to reduce the signaling load of UE capability reporting. For example, instead of reporting UE radio capability 612(1), an increased size UE radio capability report can be uniquely identified based on the UE radio capability ID. The UE radio capability ID can be communicated via a signaling procedure that avoids sending UE radio capability 612(1). When UE ML capability 612(3) is reported via UE radio capability 612(1) at 614a, the UE radio capability ID can also indicate UE ML capability 612(3). When UE ML capability is reported as a separate IE at 618a, the UE ML capability ID can be defined to indicate UE ML capability / container. UE ML capability 612(3) can be defined via the original equipment manufacturer (OEM) or mobile network operator (MNO). The UE ML capability ID can be sent based on a signaling procedure that avoids sending ML capability containers. If the wireless receiver (e.g., base station 604, 5GC, ML-related network entity / node, etc.) is not configured for the UE ML capability 612(3) associated with the UE ML capability ID, the wireless receiver may request the UE 602 to report the UE ML capability container.

[0093] In one example, UE radio capability 612(1) may include supported ML features, such as ML-based channel state information (CSI) feedback. ML-based CSI feedback may be indicated based on ml-CSIFeedback{CSI type III, maximum entropy bit, maximum bandwidth, maximum beam, ...}. Therefore, if ML features are defined, UE radio capability 612(1) may include ML features. UE ML capability 612(3) may include a list of supported models, model name / ID (e.g., ml-CSIFeedback-Model), function ID (e.g., ml-CSIFeedback), and / or other ML capability bits. These aspects may be associated with the functional division between UE radio capability 612(1) and UE ML capability 612(3).

[0094] Figure 7 This is a flowchart 700 of a wireless communication method. The method can be performed by a UE (e.g., UE 104, 402, 602; device 1002; etc.), which may include a memory 360 and may be the entire UE 104, 402, 602 or components of UE 104, 402, 602, such as a TX processor 368, an RX processor 356 and / or a controller / processor 359.

[0095] At point 702, the UE can receive requests for reporting UE capabilities related to at least one of the AI ​​or ML processes. For example, refer to... Figure 6 UE 602 can receive a UE capability request from base station 604 / core network 606 at 608a. In all respects, the UE capability request can be received by UE 602 based on the UECapabilityEnquiry message.

[0096] At point 704, the UE may send indications for one or more of the following based on a request to report UE capabilities: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​or ML processes, or core network capabilities associated with at least one of the AI ​​or ML processes. For example, refer to Figure 6 At 610a, UE 602 can send a UE capability indication to base station 604 / core network 606. In all respects, the UE capability indication can be indicated by UE 602 based on the UECapabilityInformation message.

[0097] At 610a, UE 602 may transmit at least one of AI capabilities or ML capabilities based on the capability parameters of Indication Table 500 (e.g., associated with Capability List 612). For example, UE 602 may transmit a UE ML capability at 612(3) that corresponds to at least one of processing power, memory power, hardware acceleration power, stored library, stored model format, stored model, maximum concurrency power, model combination, tested model combination, or quantization, as indicated in Table 500. At 612(1), UE 602 may also transmit radio capabilities associated with at least one of the AI ​​or ML processes for one or more AS processes. At 614a, UE 602 may transmit a separate indication for each AS function for which UE 602 supports an AI or ML process. Additionally or alternatively, at 612(2), UE 602 may transmit core network capabilities for one or more processes in the MM or SM process. At 616a, UE 602 can similarly send separate instructions for each MM function or SM function that UE 602 supports for AI or ML processes.

[0098] An indication of at least one of the AI ​​capabilities or ML capabilities transmitted at 610a may be included in the indication of the radio capabilities at 614a. In each aspect, at 614a, the indication of the radio capabilities may be based on a radio capability ID corresponding to at least one of the AI ​​capabilities or ML capabilities. An indication of at least one of the AI ​​capabilities or ML capabilities transmitted at 610a may be included in the indication of the core network capabilities at 616a. In each aspect, the indication of at least one of the AI ​​capabilities or ML capabilities transmitted at 610a may be transmitted separately at 618a from the indications of the radio capabilities at 614a and the indications of the core network capabilities at 616a. At 618a, the indication of at least one of the AI ​​capabilities or ML capabilities may be transmitted in a separate IE from the indications of the radio capabilities at 614a and the indications of the core network capabilities at 616a, wherein the separate IE may be transmitted at 618a together with or separately from at least one of the indications of the radio capabilities at 614a or the indications of the core network capabilities at 616a. The individual IE sent at 618a may include at least one of AI capability ID or ML capability ID. At least one of the requests to report UE capabilities received at 608a or the indications for one or more of AI capabilities, ML capabilities, radio capabilities, or core network capabilities sent at 610a may be included in the RRC message or NAS message.

[0099] At 610a, the transmission of the indication may include: a first portion indicating at least one of AI capabilities or ML capabilities for the AS, and a second portion indicating at least one of AI capabilities or ML capabilities for the NAS. The AI ​​capabilities or ML capabilities may correspond to processing capabilities or memory capabilities, such as those indicated in Table 500. In the example, the UE capabilities transmitted at 610a may be used for CSI feedback.

[0100] Figure 8 This is a flowchart 800 of a wireless communication method. The method can be performed by a network entity (e.g., base station 102, 404, 604, core network 606, device 1102, etc.), which may include a memory 376 and may be the entire network entity or a component of the network entity, such as a TX processor 316, an RX processor 370, and / or a controller / processor 375.

[0101] At point 802, a network entity can send a request for a report on at least one of the UE's capabilities in either the AI ​​process or the ML process. For example, refer to... Figure 6 At points 608a-b, base station 604 / core network 606 can send a UE capability request to UE 602. In all respects, the UE capability request can be sent by base station 604 / core network 606 based on a UECapabilityEnquiry message.

[0102] At point 804, a network entity may receive indications for one or more of the following based on a request for reporting UE capabilities: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​or ML processes, or core network capabilities associated with at least one of the AI ​​or ML processes. For example, refer to Figure 6 At points 610a-b, base station 604 / core network 606 can receive a UE capability indication from UE 602. In all respects, the UE capability indication can be received by base station 604 / core network 606 based on the UECapabilityInformation message.

[0103] Figure 9 This is a flowchart 900 of a wireless communication method. The method may be performed by a network entity (e.g., base station 102, 404, 604, core network 606, device 1102, etc.), which may include a memory 376 and may be the entire network entity or a component of the network entity, such as a TX processor 316, an RX processor 370, and / or a controller / processor 375.

[0104] At position 902, a network entity can send a request for a report on at least one of the UE's capabilities in either the AI ​​process or the ML process. For example, refer to... Figure 6 At points 608a-b, base station 604 / core network 606 can send a UE capability request to UE 602. In all respects, the UE capability request can be sent by base station 604 / core network 606 based on a UECapabilityEnquiry message.

[0105] At 904, a network entity may receive indications for one or more of the following based on a request for reporting UE capabilities: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​or ML processes, or core network capabilities associated with at least one of the AI ​​or ML processes. For example, refer to Figure 6 At points 610a-b, base station 604 / core network 606 can receive a UE capability indication from UE 602. In all respects, the UE capability indication can be received by base station 604 / core network 606 based on the UECapabilityInformation message.

[0106] At 610a-b, a network entity (e.g., base station 604 / core network 606) may (e.g., in association with capability list 612) receive at least one of AI capabilities or ML capabilities, which may indicate the capability parameters of table 500. For example, a network entity (e.g., base station 604 / core network 606) may receive UE ML capabilities based on 612(3), which correspond to at least one of processing power, memory power, hardware acceleration power, storage library, storage model format, storage model, maximum concurrency power, model combination, test model combination, or quantization, as indicated in table 500. A network entity (e.g., base station 604 / core network 606) may also receive radio capabilities based on 612(1) associated with at least one of the AI ​​or ML processes used for one or more AS processes. At 614a / 614c, a network entity (e.g., base station 604 / core network 606) may receive separate indications for each AS function for which UE 602 supports an AI or ML process. Alternatively or concurrently, a network entity (e.g., base station 604 / core network 606) may receive core network capabilities for one or more processes within the MM or SM process based on 612(2). At 616a / 616c, the network entity (e.g., base station 604 / core network 606) may similarly receive individual instructions for each MM or SM function that UE 602 supports within the AI ​​or ML process. In one example, the UE capabilities received at 610a-b may be used for CSI feedback.

[0107] An indication of at least one of the AI ​​capabilities or ML capabilities received at 610a-b may be included in the indication of the radio capabilities at 614a / 614c. In some aspects, at 614a / 614c, the indication of the radio capabilities may be based on a radio capability ID corresponding to at least one of the AI ​​capabilities or ML capabilities. An indication of at least one of the AI ​​capabilities or ML capabilities received at 610a-b may be included in the indication of the core network capabilities at 616a / 616c. In some aspects, the indication of at least one of the AI ​​capabilities or ML capabilities received at 610a-b may be received separately at 618a / 618c from the indication of the radio capabilities at 614a / 614c and the indication of the core network capabilities at 616a / 616c. At 618a / 618c, an indication of at least one of AI capabilities or ML capabilities may be received in a separate IE from the indication of radio capabilities at 614a / 614c and the indication of core network capabilities at 616a / 616c. At 618a / 618c, a separate IE may be received together with or separately from at least one of the indications of radio capabilities at 614a / 614c or core network capabilities at 616a / 616c. A separate IE received at 618a / 618c may include at least one of an AI capability ID or an ML capability ID. A request to report UE capabilities sent at 608a-b or at least one of the indications of one or more of AI capabilities, ML capabilities, radio capabilities, or core network capabilities received at 610a-b may be included in an RRC message or a NAS message.

[0108] At point 906, a network entity may report to a second network entity at least one of the following: instructions regarding AI capabilities, ML capabilities, radio capabilities, or core network capabilities. For example, refer to... Figure 6 The network entity can be base station 604, which can report the UE capability information received in 610a to core network 606 in 610b.

[0109] At point 908, if the first network entity is a base station, then the network entity can indicate a portion of the AI ​​or ML capabilities to the core network. For example, refer to... Figure 6 If the network entity is base station 604, then at 614c / 616c / 618c, the network entity can relay UE capability information to the core network 606.

[0110] At point 910, if the first network entity is the core network, the network entity can indicate a portion of the AI ​​or ML capabilities to the base station serving the UE. For example, refer to... Figure 6If the network entity is core network 606, then at 614b / 616b / 618b, the network entity can relay UE capability information to base station 604.

[0111] Figure 10 Figure 1000 illustrates an example of a hardware implementation for device 1002. Device 1002 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, device 1002 may include a cellular baseband processor 1004 (also referred to as a modem) coupled to a cellular RF transceiver 1022. In some aspects, device 1002 may also include one or more Subscriber Identity Module (SIM) cards 1020, an application processor 1006 coupled to a Secure Digital Card (SD) card 1008 and a screen 1010, a Bluetooth module 1012, a Wireless Local Area Network (WLAN) module 1014, a Global Positioning System (GPS) module 1016, or a power supply 1018. The cellular baseband processor 1004 communicates with the UE 104 and / or BS 102 / 180 via the cellular RF transceiver 1022. The cellular baseband processor 1004 may include computer-readable media / memory. The computer-readable media / memory may be non-transitory. Cellular baseband processor 1004 is responsible for general processing, including executing software stored on a computer-readable medium / memory. This software, when executed by cellular baseband processor 1004, causes cellular baseband processor 1004 to perform the various functions described above. The computer-readable medium / memory can also be used to store data manipulated by cellular baseband processor 1004 during software execution. Cellular baseband processor 1004 also includes a receiving component 1030, a communication manager 1032, and a transmitting component 1034. Communication manager 1032 includes one or more components shown. Components within communication manager 1032 can be stored in a computer-readable medium / memory and / or configured as hardware within cellular baseband processor 1004. Cellular baseband processor 1004 can be a component of UE 350 and can include at least one of TX processor 368, RX processor 356, and controller / processor 359 and / or memory 360. In one configuration, device 1002 can be a modem chip and only includes baseband processor 1004, while in another configuration, device 1002 can be the entire UE (e.g., see...). Figure 3 (350) and includes an additional module of device 1002.

[0112] The communications manager 1032 includes a UE capability indicator component 1040 configured (e.g., as described in conjunction with 702 and 704) to receive a request to report a UE capability for at least one of an AI process or an ML process; and to send an indication of one or more of the following based on the request to report a UE capability: an AI capability, an ML capability, a radio capability associated with at least one of an AI process or an ML process, or a core network capability associated with at least one of an AI process or an ML process.

[0113] The apparatus may include execution Figure 7 The flowchart shows the algorithm as an additional component for each box. Therefore, Figure 7 Each box in the flowchart can be executed by a component, and the apparatus can include one or more of those components. A component can be one or more hardware components specifically configured to perform the process / algorithm, implemented by a processor configured to perform the process / algorithm, stored in a computer-readable medium for processor implementation, or some combination thereof.

[0114] As shown in the figure, device 1002 may include various components configured for various functions. In one configuration, device 1002, particularly cellular baseband processor 1004, includes: components for receiving a request to report a UE capability for at least one of an AI process or an ML process; and components for transmitting an indication of one or more of the following based on the request to report the UE capability: AI capability, ML capability, radio capability associated with at least one of the AI ​​process or ML process, or core network capability associated with at least one of the AI ​​process or ML process. The components for transmitting may be configured to indicate at least one of processing capability, memory capability, hardware acceleration capability, repository, storage model format, storage model, maximum concurrency capability, model combination, test model combination, or quantization. The components for transmitting may also be configured to: a first portion indicating at least one of the AI ​​capability or ML capability for AS, and a second portion indicating at least one of the AI ​​capability or ML capability for NAS.

[0115] The component may be one or more components of the device 1002 configured to perform the functions described therein. As described above, the device 1002 may include a TX processor 368, an RX processor 356, and a controller / processor 359. Thus, in one configuration, the component may be the TX processor 368, the RX processor 356, and the controller / processor 359 configured to perform the functions described therein.

[0116] Figure 11Figure 1100 illustrates an example of a hardware implementation for device 1102. Device 1102 may be a base station, a component of a base station, or may implement base station functions. In some aspects, device 1002 may include a baseband unit 1104. Baseband unit 1104 may communicate with UE 104 via cellular RF transceiver 1122. Baseband unit 1104 may include computer-readable medium / memory. Baseband unit 1104 is responsible for general processing, including executing software stored on computer-readable medium / memory. When executed by baseband unit 1104, the software causes baseband unit 1104 to perform the various functions described above. Computer-readable medium / memory may also be used to store data manipulated by baseband unit 1104 when executing the software. Baseband unit 1104 also includes a receiving component 1130, a communication manager 1132, and a transmitting component 1134. Communication manager 1132 includes one or more of the components shown. The components within the communication manager 1132 may be stored in a computer-readable medium / memory and / or configured as hardware within the baseband unit 1104. The baseband unit 1104 may be a component of the base station 310 and may include at least one of the memory 376 and / or the TX processor 316, the RX processor 370, and the controller / processor 375.

[0117] The communication manager 1132 includes a UE capability requester component 1140 configured (e.g., as described in conjunction with 802, 804, 902, and 904) to send a request to report UE capabilities for at least one of an AI process or an ML process; and, based on the request to report UE capabilities, to receive indications for one or more of the following: AI capabilities, ML capabilities, radio capabilities associated with at least one of an AI process or an ML process, or core network capabilities associated with at least one of an AI process or an ML process. The communication manager 1132 also includes a reporter component 1142 configured (e.g., as described in conjunction with 906) to report at least one indication of an AI capability, ML capability, radio capability, or core network capability to a second network entity. The communication manager 1132 also includes an indication component 1144 configured (e.g., as described in conjunction with 908 and 910) to indicate a portion of AI capabilities or ML capabilities to the core network if the first network entity is a base station; and to indicate a portion of AI capabilities or ML capabilities to the base station serving the UE if the first network entity is the core network.

[0118] The apparatus may include execution Figures 8 to 9 The flowchart shows the algorithm as an additional component for each box. Therefore, Figures 8 to 9Each box in the flowchart can be executed by a component, and the apparatus can include one or more of those components. A component can be one or more hardware components specifically configured to perform the process / algorithm, implemented by a processor configured to perform the process / algorithm, stored in a computer-readable medium for processor implementation, or some combination thereof.

[0119] As shown in the figure, apparatus 1102 may include various components configured for various functions. In one configuration, apparatus 1102, particularly baseband unit 1104, includes: components for transmitting a request to report a UE capability for at least one of an AI process or an ML process; and components for receiving indications for one or more of the following based on the request to report UE capabilities: AI capability, ML capability, radio capability associated with at least one of the AI ​​process or ML process, or core network capability associated with at least one of the AI ​​process or ML process. Apparatus 1102 also includes: components for reporting at least one of the indications for AI capability, ML capability, radio capability, or core network capability to a second network entity. Apparatus 1102 also includes components for indicating a portion of the AI ​​capability or ML capability to the core network. Apparatus 1102 further includes components for indicating a portion of the AI ​​capability or ML capability to a base station serving the UE.

[0120] The component may be one or more components of device 1102 configured to perform the functions described therein. As described above, device 1102 may include TX processor 316, RX processor 370, and controller / processor 375. Therefore, in one configuration, the component may be TX processor 316, RX processor 370, and controller / processor 375 configured to perform the functions described therein.

[0121] It should be understood that the specific order or hierarchy of the boxes in the disclosed process / flowchart is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of the boxes in the process / flowchart can be rearranged. Furthermore, some boxes can be combined or omitted. The appended method claims present the elements of the individual boxes in a sample order and are not intended to limit one to the specific order or hierarchy presented.

[0122] The preceding description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects shown herein, but are to be consistent with the full scope of the language claims, wherein, unless specifically stated otherwise, references to singular elements are not intended to mean “one and only one,” but rather “one or more.” Terms such as “if,” “when,” and “simultaneously” should be interpreted as indicating “under this condition,” rather than implying an immediate temporal relationship or reaction. That is, these phrases (e.g., “when…”) do not imply an immediate action in response to the occurrence of an action or during the occurrence of an action, but simply imply that an action will occur if a condition is met, but without requiring a specific or immediate time constraint on the occurrence of the action. The word “exemplary” as used herein means “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects. Unless otherwise specifically stated, the term “some” means one or more. Combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, and may include multiples of A, multiples of B, or multiples of C. Specifically, combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, wherein any such combination may include one or more members of A, B, or C. All structural and functional equivalents of elements throughout the various aspects described herein that are known or will later become known to those skilled in the art are expressly incorporated herein by reference and are intended to be covered by the claims. Furthermore, nothing disclosed herein is intended to be offered to the public, whether or not such disclosure is expressly recited in the claims. The terms “module,” “mechanism,” “component,” and “device” are not necessarily substitutes for the term “part.” Therefore, no claim element should be interpreted as a component plus function unless the phrase “component for…” is used to explicitly describe the element.

[0123] The following aspects are illustrative only and may be combined with, but are not limited to, other aspects or teachings described herein.

[0124] Aspect 1 is an apparatus for wireless communication at a UE, comprising: at least one processor coupled to a memory and configured to: receive a request to report UE capabilities for at least one of an AI process or an ML process; and, based on the request to report UE capabilities, send an indication of one or more of the following: AI capability, ML capability, radio capability associated with at least one of the AI ​​process or the ML process, or core network capability associated with at least one of the AI ​​process or the ML process.

[0125] Aspect 2 may be combined with aspect 1 and includes at least one of the UE's AI transmission capability or ML capability, wherein the transmission indication processing capability, memory capability, hardware acceleration capability, storage repository, storage model format, storage model, maximum concurrency capability, model combination, test model combination, or quantization of the indication.

[0126] Aspect 3 may be combined with any of Aspects 1-2 and includes: the UE transmitting radio capabilities associated with at least one of the AI ​​or ML processes for one or more AS processes.

[0127] Aspect 4 may be combined with any of Aspects 1-3 and includes: the UE sending a separate instruction for each AS function that the UE supports for AI or ML procedures.

[0128] Aspect 5 may be combined with any of Aspects 1-4 and includes: the UE transmitting one or more core network capabilities for the MM or SM process.

[0129] Aspect 6 may be combined with any of Aspects 1-5 and includes: the UE sending a separate instruction for each MM function or SM function that the UE supports for the AI ​​process or ML process.

[0130] Aspect 7 may be combined with any of aspects 1-6 and includes: an indication of at least one of AI capabilities or ML capabilities is included in the indication of radio capabilities.

[0131] Aspect 8 may be combined with any of aspects 1-7 and includes: an indication of at least one of AI capabilities or ML capabilities included in the indication of radio capabilities, indicating a radio capability ID corresponding to at least one of AI capabilities or ML capabilities.

[0132] Aspect 9 may be combined with any of aspects 1-8, and includes: an indication of at least one of AI capabilities or ML capabilities is included in the indication of core network capabilities.

[0133] Aspect 10 may be combined with any of aspects 1-6 and includes: transmitting an indication of at least one of AI capabilities or ML capabilities separately from the indication of radio capabilities and the indication of core network capabilities.

[0134] Aspect 11 may be combined with any of aspects 1-6 or 10, and includes: transmitting an indication of at least one of AI capabilities or ML capabilities in an IE separate from the indication of radio capabilities and the indication of core network capabilities, the separate IE being transmitted together with the indication of at least one of radio capabilities or the indication of core network capabilities.

[0135] Aspect 12 may be combined with any of aspects 1-6 or 10-11, and includes: individual IEs include at least one of AI capability ID or ML capability ID.

[0136] Aspect 13 may be combined with any one of aspects 1-6 or 10-12, and includes: at least one of a request to report UE capabilities or an indication of one or more of AI capabilities, ML capabilities, radio capabilities or core network capabilities being included in an RRC message or NAS message.

[0137] Aspect 14 may be combined with any of aspects 1-13 and includes: a first part indicating the transmission of at least one of the AI ​​capabilities or ML capabilities of the AS, and a second part indicating at least one of the AI ​​capabilities or ML capabilities of the NAS.

[0138] Aspect 15 may be combined with any of aspects 1-14 and includes: AI capability or ML capability corresponding to processing capability or memory capability.

[0139] Aspect 16 can be combined with any of Aspects 1-15 and includes UE capabilities for CSI feedback.

[0140] Aspect 17 is an apparatus for wireless communication at a base station, comprising at least one processor coupled to a memory and configured to: send a request to report UE capabilities for at least one of an AI process or an ML process; and, based on the request to report UE capabilities, receive indications for one or more of the following: AI capabilities, ML capabilities, radio capabilities associated with at least one of an AI process or an ML process, or core network capabilities associated with at least one of an AI process or an ML process.

[0141] Aspect 18 may be combined with aspect 17 and includes at least one of the following AI or ML capabilities: network entity receiving instruction processing capability, memory capability, hardware acceleration capability, repository, storage model format, storage model, maximum concurrency capability, model combination, test model combination or quantization.

[0142] Aspect 19 may be combined with any of aspects 17-18 and includes: the network entity receiving radio capabilities associated with at least one of AI capabilities or ML capabilities for one or more AS processes.

[0143] Aspect 20 may be combined with any of aspects 17-19 and includes: the network entity receiving a separate instruction for each AS function that supports the AI ​​procedure or ML procedure for the UE.

[0144] Aspect 21 may be combined with any of aspects 17-20 and includes: network entities receiving one or more core network capabilities for the MM process or the SM process.

[0145] Aspect 22 may be combined with any of aspects 17-21 and includes: the network entity receiving a separate instruction for each MM function or SM function that supports the AI ​​process or ML process for the UE.

[0146] Aspect 23 may be combined with any of aspects 17-22 and includes: an indication of at least one of AI capabilities or ML capabilities is included in the indication of radio capabilities.

[0147] Aspect 24 may be combined with any of aspects 17-23 and includes: an indication of at least one of AI capabilities or ML capabilities included in the indication of radio capabilities, indicating a radio capability ID corresponding to at least one of AI capabilities or ML capabilities.

[0148] Aspect 25 may be combined with any of aspects 17-24 and includes: an indication of at least one of AI capabilities or ML capabilities is included in the indication of core network capabilities.

[0149] Aspect 26 may be combined with any of aspects 17-25 and includes: the indication is received at a base station, and further includes: at least one processor is configured to report to a second network entity at least one of the indications for AI capabilities, ML capabilities, radio capabilities, or core network capabilities.

[0150] Aspect 27 may be combined with any of aspects 17-22 or 26, and includes: receiving an indication of at least one of AI capabilities or ML capabilities separately from the indication of radio capabilities and the indication of core network capabilities.

[0151] Aspect 28 may be combined with any one of aspects 17-22 or 26-27, and includes: receiving an indication of at least one of AI capabilities or ML capabilities in an IE separate from the indication of radio capabilities and the indication of core network capabilities, the separate IE being received together with the indication of radio capabilities or the indication of core network capabilities.

[0152] Aspect 29 may be combined with any of aspects 17-22 or 26-28, and includes: individual IEs include at least one of AI capability ID or ML capability ID.

[0153] Aspect 30 may be combined with any one of aspects 17-22 or 26-29, and includes: at least one of a request to report UE capabilities or an instruction for one or more of AI capabilities, ML capabilities, radio capabilities or core network capabilities based on at least one of the RRC process or NAS process.

[0154] Aspect 31 may be combined with any of aspects 17-30 and includes: the indication of at least one of AI capabilities or ML capabilities is received at a base station, and further includes: at least one processor is configured to indicate a portion of the AI ​​capabilities or ML capabilities to the core network.

[0155] Aspect 32 may be combined with any of aspects 17-30 and includes: the indication of at least one of AI capabilities or ML capabilities is received at the core network, and further includes: at least one processor is configured to indicate a portion of the AI ​​capabilities or ML capabilities to the base station serving the UE.

[0156] Aspect 33 can be combined with any of Aspects 17-32 and includes UE capabilities for CSI feedback.

[0157] Aspect 34 is a method for implementing wireless communication in any of aspects 1-33.

[0158] Aspect 35 is a device for wireless communication, including components for implementing any one of aspects 1-33.

[0159] Aspect 36 is a computer-readable medium storing computer-executable code that, when executed by at least one processor, causes at least one processor to implement any one of aspects 1-33.

Claims

1. An apparatus for wireless communication at a user equipment (UE), comprising: A memory that stores instructions; as well as At least one processor, the at least one processor being configured to execute the instructions to cause the device to: Receive reports requesting UE capabilities for at least one of the following: artificial intelligence (AI) processes or machine learning (ML) processes; and Based on the request to report the UE capabilities, an indication is sent for one or more of the following: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​process or the ML process, or core network capabilities associated with at least one of the AI ​​process or the ML process, wherein the sending of the indication indicates a first portion of at least one of the AI ​​capabilities or the ML capabilities of the access stratum AS, and indicates a second portion of at least one of the AI ​​capabilities or the ML capabilities of the non-access stratum NAS.

2. The apparatus according to claim 1, wherein, The at least one processor is configured to execute the instructions to cause the device to send at least one of the AI ​​capabilities or the ML capabilities, and the sending instruction of the instructions includes at least one of the following: processing capability, memory capability, hardware acceleration capability, repository, storage model format, storage model, maximum concurrency capability, model combination, test model combination, or quantization.

3. The apparatus according to claim 1, wherein, The at least one processor is configured to execute the instructions to cause the device to: transmit the radio capability associated with the AI ​​process or at least one process in the ML process for one or more AS processes.

4. The apparatus according to claim 3, wherein, The at least one processor is configured to execute the instructions to cause the device to send a separate instruction for each AS function of the AI ​​process or the ML process that the UE supports.

5. The apparatus according to claim 1, wherein, The at least one processor is configured to execute the instructions to cause the device to: transmit one or more of the core network capabilities for the Mobility Management (MM) process or the Session Management (SM) process.

6. The apparatus according to claim 5, wherein, The at least one processor is configured to execute the instructions to cause the device to send a separate instruction for each MM function or SM function that supports the AI ​​process or the ML process for the UE.

7. The apparatus according to claim 1, wherein, The indication of at least one of the AI ​​capability or the ML capability is included in the indication of the radio capability.

8. The apparatus according to claim 7, wherein, The indication of the radio capability includes the indication of at least one of the AI ​​capability or the ML capability, which indicates a radio capability identifier ID corresponding to at least one of the AI ​​capability or the ML capability.

9. The apparatus according to claim 1, wherein, The indications for at least one of the AI ​​capabilities or the ML capabilities are included in the indications for the core network capabilities.

10. The apparatus according to claim 1, wherein, In order to send the indication for at least one of the AI ​​capabilities or the ML capabilities, the at least one processor is configured to execute the instructions to cause the device to send the indication for at least one of the AI ​​capabilities or the ML capabilities separately from the indication for the radio capabilities and the indication for the core network capabilities.

11. The apparatus according to claim 10, wherein, In order to send the indication for at least one of the AI ​​capabilities or the ML capabilities, the at least one processor is configured to execute the instructions to cause the device to send the indication for at least one of the AI ​​capabilities or the ML capabilities in a separate information element (IE) from the indication for the radio capabilities and the indication for the core network capabilities, and wherein, in order to send the indication for at least one of the AI ​​capabilities or the ML capabilities in the separate IE, the at least one processor is configured to execute the instructions to cause the device to send the indication for at least one of the AI ​​capabilities or the ML capabilities in the separate IE together with at least one of the indication for the radio capabilities or the indication for the core network capabilities.

12. The apparatus according to claim 10, wherein, The request for reporting the UE capabilities or the indication of one or more of the AI ​​capabilities, the ML capabilities, the radio capabilities, or the core network capabilities is included in a Radio Resource Control (RRC) message or a NAS message.

13. The apparatus according to claim 1, wherein, The UE capability is used for Channel State Information (CSI) feedback.

14. An apparatus for wireless communication in a wireless network, comprising: A memory that stores instructions; as well as At least one processor, the at least one processor being configured to execute the instructions to cause the device to: Send a request for a report on at least one of the user equipment (UE) capabilities related to artificial intelligence (AI) processes or machine learning (ML) processes; and Based on the request to report the UE capabilities, an indication is received for one or more of the following: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​process or the ML process, or core network capabilities associated with at least one of the AI ​​process or the ML process, wherein receiving the indication indicates a first portion of at least one of the AI ​​capabilities or the ML capabilities of the access stratum AS, and indicates a second portion of at least one of the AI ​​capabilities or the ML capabilities of the non-access stratum NAS.

15. The apparatus according to claim 14, wherein, The at least one processor is configured to execute the instructions to cause the device to receive at least one of the AI ​​capabilities or the ML capabilities, including at least one of the following: processing capability, memory capability, hardware acceleration capability, repository, storage model format, storage model, maximum concurrency capability, model combination, test model combination, or quantization.

16. The apparatus according to claim 14, wherein, The at least one processor is configured to execute the instructions to cause the device to: receive the radio capability associated with at least one of the AI ​​capability or the ML capability for one or more AS processes.

17. The apparatus according to claim 16, wherein, The at least one processor is configured to execute the instructions to cause the device to: receive separate instructions for each AS function of the AI ​​process or the ML process supported by the UE.

18. The apparatus according to claim 14, wherein, The at least one processor is configured to execute the instructions to cause the device to receive one or more of the core network capabilities for the Mobility Management (MM) process or the Session Management (SM) process.

19. The apparatus according to claim 18, wherein, The at least one processor is configured to execute the instructions to cause the device to: receive individual instructions for each MM function or SM function that supports the AI ​​process or the ML process for the UE.

20. The apparatus according to claim 14, wherein, The indication of at least one of the AI ​​capability or the ML capability is included in the indication of the radio capability.

21. The apparatus according to claim 20, wherein, The indication of the radio capability includes the indication of at least one of the AI ​​capability or the ML capability, which indicates a radio capability identifier ID corresponding to at least one of the AI ​​capability or the ML capability.

22. The apparatus according to claim 14, wherein, The indications for at least one of the AI ​​capabilities or the ML capabilities are included in the indications for the core network capabilities.

23. The apparatus according to claim 14, wherein, In order to receive the indication, the at least one processor is configured to execute the instructions to cause the device to receive the indication at a base station, and wherein the at least one processor is configured to execute the instructions to cause the device to: report to a network entity at least one of the indications for the AI ​​capability, the ML capability, the radio capability, or the core network capability.

24. The apparatus according to claim 14, wherein, In order to receive the indication for at least one of the AI ​​capabilities or the ML capabilities, the at least one processor is configured to execute the instructions to cause the device to receive the indication for at least one of the AI ​​capabilities or the ML capabilities separately from the indication for the radio capabilities and the indication for the core network capabilities.

25. The apparatus according to claim 24, wherein, In order to receive the indication for at least one of the AI ​​capabilities or the ML capabilities, the at least one processor is configured to execute the instructions to cause the device to receive the indication for at least one of the AI ​​capabilities or the ML capabilities in a separate information element (IE) from the indication for the radio capabilities and the indication for the core network capabilities, and wherein, in order to receive the indication for at least one of the AI ​​capabilities or the ML capabilities in the separate IE, the at least one processor is configured to execute the instructions to cause the device to receive the separate IE together with at least one of the indication for the radio capabilities or the indication for the core network capabilities.

26. The apparatus according to claim 24, wherein, The request to report the UE capabilities or the indication of one or more of the AI ​​capabilities, the ML capabilities, the radio capabilities, or the core network capabilities is based on at least one of the Radio Resource Control (RRC) or NAS procedures.

27. The apparatus according to claim 14, wherein, In order to receive the indication for at least one of the AI ​​capabilities or the ML capabilities, the at least one processor is configured to execute the instructions to cause the device to receive the indication for at least one of the AI ​​capabilities or the ML capabilities at a base station, and wherein the at least one processor is further configured to execute the instructions to cause the device to indicate a portion of the AI ​​capabilities or the ML capabilities to the core network.

28. The apparatus according to claim 14, wherein, In order to receive the indication for at least one of the AI ​​capabilities or the ML capabilities, the at least one processor is configured to execute the instructions to cause the device to receive the indication for at least one of the AI ​​capabilities or the ML capabilities at the core network, and wherein the at least one processor is further configured to execute the instructions to cause the device to indicate a portion of the AI ​​capabilities or the ML capabilities to a base station serving the UE.

29. The apparatus according to claim 14, wherein, The UE capability is based on Channel State Information (CSI) feedback.

30. A method for wireless communication at a user equipment (UE), comprising: Receive reports requesting UE capabilities for at least one of the artificial intelligence (AI) or machine learning (ML) processes; as well as Based on the request to report the UE capabilities, an indication is sent for one or more of the following: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​process or the ML process, or core network capabilities associated with at least one of the AI ​​process or the ML process, wherein the sending of the indication indicates a first portion of at least one of the AI ​​capabilities or the ML capabilities of the access stratum AS, and indicates a second portion of at least one of the AI ​​capabilities or the ML capabilities of the non-access stratum NAS.

31. The method according to claim 30, wherein, Send at least one of the AI ​​capabilities or the ML capabilities, and wherein the sending instruction of the indicated means at least one of the following: processing capability, memory capability, hardware acceleration capability, repository, storage model format, storage model, maximum concurrency capability, model combination, test model combination, or quantization.

32. The method according to claim 30, wherein, Transmit the radio capability associated with the AI ​​process or at least one process in the ML process for one or more AS processes.

33. The method according to claim 30, wherein, For each AS function that the UE supports for its AI process or ML process, send a separate instruction.

34. The method according to claim 30, wherein, Send one or more of the core network capabilities for the Mobility Management (MM) process or the Session Management (SM) process.

35. The method according to claim 34, wherein, Send a separate instruction for each MM function or SM function that the UE supports for the AI ​​process or the ML process.

36. The method according to claim 30, wherein, The indication of at least one of the AI ​​capability or the ML capability is included in the indication of the radio capability.

37. The method of claim 36, wherein, The indication of the radio capability includes the indication of at least one of the AI ​​capability or the ML capability, which indicates a radio capability identifier ID corresponding to at least one of the AI ​​capability or the ML capability.

38. The method according to claim 30, wherein, The indications for at least one of the AI ​​capabilities or the ML capabilities are included in the indications for the core network capabilities.

39. The method according to claim 30, wherein, Sending the indication for at least one of the AI ​​capabilities or the ML capabilities includes sending the indication for at least one of the AI ​​capabilities or the ML capabilities separately from the indication for the radio capabilities and the indication for the core network capabilities.

40. The method according to claim 39, wherein, Sending the indication for at least one of the AI ​​capabilities or the ML capabilities includes sending the indication for at least one of the AI ​​capabilities or the ML capabilities in a separate information element (IE) from the indication for the radio capabilities and the indication for the core network capabilities, wherein sending the indication for at least one of the AI ​​capabilities or the ML capabilities in the separate IE includes sending the indication for at least one of the AI ​​capabilities or the ML capabilities in the separate IE together with at least one of the indication for the radio capabilities or the indication for the core network capabilities.

41. The method according to claim 39, wherein, The request for reporting the UE capabilities or the indication of one or more of the AI ​​capabilities, the ML capabilities, the radio capabilities, or the core network capabilities is included in a Radio Resource Control (RRC) message or a NAS message.

42. The method according to claim 30, wherein, The UE capability is used for Channel State Information (CSI) feedback.

43. A method for wireless communication in a wireless network, comprising: Send a request for the report's coverage of at least one of the user equipment (UE) capabilities in either the artificial intelligence (AI) process or the machine learning (ML) process; as well as Based on the request to report the UE capabilities, an indication is received for one or more of the following: AI capabilities, ML capabilities, radio capabilities associated with at least one of the AI ​​process or the ML process, or core network capabilities associated with at least one of the AI ​​process or the ML process, wherein receiving the indication indicates a first portion of at least one of the AI ​​capabilities or the ML capabilities of the access stratum AS, and indicates a second portion of at least one of the AI ​​capabilities or the ML capabilities of the non-access stratum NAS.

44. The method according to claim 43, wherein, Receive at least one of the AI ​​capabilities or the ML capabilities, wherein the receiving instruction for the instruction is at least one of the following: processing capability, memory capability, hardware acceleration capability, repository, storage model format, storage model, maximum concurrency capability, model combination, test model combination, or quantization.

45. The method according to claim 43, wherein, Receive the radio capability associated with at least one of the AI ​​capability or the ML capability for one or more AS processes.

46. ​​The method according to claim 45, wherein, Receive separate instructions for each AS function that the UE supports for its AI process or ML process.

47. The method according to claim 43, wherein, Receive one or more of the core network capabilities for the Mobility Management (MM) process or the Session Management (SM) process.

48. The method according to claim 47, wherein, Receive individual instructions for each MM function or SM function that the UE supports for the AI ​​process or the ML process.

49. The method according to claim 43, wherein, The indication of at least one of the AI ​​capability or the ML capability is included in the indication of the radio capability.

50. The method according to claim 49, wherein, The indication of the radio capability includes the indication of at least one of the AI ​​capability or the ML capability, which indicates a radio capability identifier ID corresponding to at least one of the AI ​​capability or the ML capability.

51. The method according to claim 43, wherein, The indications for at least one of the AI ​​capabilities or the ML capabilities are included in the indications for the core network capabilities.

52. The method according to claim 43, wherein, Receiving the instruction includes receiving the instruction at a base station, and the method further includes: Report to the network entity at least one of the instructions regarding the AI ​​capability, the ML capability, the radio capability, or the core network capability.

53. The method according to claim 43, wherein, Receiving the indication for at least one of the AI ​​capabilities or the ML capabilities includes receiving the indication for the AI ​​capabilities or the ML capabilities separately from the indication for the radio capabilities and the indication for the core network capabilities.

54. The method according to claim 53, wherein, Receiving the indication for at least one of the AI ​​capabilities or the ML capabilities includes receiving the indication for at least one of the AI ​​capabilities or the ML capabilities in a separate information element (IE) from the indication for the radio capabilities and the indication for the core network capabilities, wherein receiving the indication for at least one of the AI ​​capabilities or the ML capabilities in the separate IE includes receiving the separate IE together with at least one of the indication for the radio capabilities or the indication for the core network capabilities.

55. The method according to claim 53, wherein, The request to report the UE capabilities or the indication of one or more of the AI ​​capabilities, the ML capabilities, the radio capabilities, or the core network capabilities is based on at least one of the Radio Resource Control (RRC) or NAS procedures.

56. The method according to claim 43, wherein, Receiving the indication for at least one of the AI ​​capabilities or the ML capabilities includes receiving the indication for at least one of the AI ​​capabilities or the ML capabilities at a base station, the method further comprising: Instruct the core network on the AI ​​capabilities or a portion of the ML capabilities.

57. The method according to claim 43, wherein, Receiving the indication for at least one of the AI ​​capabilities or the ML capabilities includes receiving the indication for at least one of the AI ​​capabilities or the ML capabilities at a core network, the method further comprising: Indicate the AI ​​capability or a portion of the ML capability to the base station serving the UE.

58. The method according to claim 43, wherein, The UE capability is based on Channel State Information (CSI) feedback.

59. An apparatus for wireless communication at a user equipment (UE), comprising components for performing the method according to any one of claims 30 to 42.

60. An apparatus for wireless communication in a wireless network, comprising components for performing the method according to any one of claims 43 to 58.

61. A computer-readable medium having program code recorded thereon, wherein the program code is executable by one or more processors of a user equipment (UE) to cause the processors to perform the method according to any one of claims 30 to 42.

62. A computer-readable medium having program code recorded thereon, wherein the program code is executable by one or more processors of a wireless network to cause the processors to perform the method according to any one of claims 43 to 58.

Images