Method and device for managing ML processing model

Abstract

The UE may indicate to the wireless network an ability to support one or more versions of the ML processing model, and a wireless network entity of the wireless network may configure the UE to apply the version of the ML processing model supported by the UE. The indication from the UE may indicate the ability to support one or more of a first version of an ML processing model that is common across multiple wireless networks and at least one alternative version of the ML processing model, such as a network-specific version. The wireless network entity may configure at least one of a network-specific algorithm structure or one or more weights of a network-specific machine learning model supported by the UE.

Description

Technical Field

[0001] The present disclosure generally relates to communication systems, and more particularly, to methods and apparatus for wireless communication between a user equipment (UE) and a base station. Background Art

[0002] Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcast. 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.

[0003] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at a city, country, region, and even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continuous mobile broadband evolution released by the Third Generation Partnership (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., together 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 may be based on the 4G Long Term Evolution (LTE) standard. There is a need for further improvements in 5G NR technology. These improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0004] A brief summary of one or more aspects is given below to provide a basic understanding of such aspects. This summary is not an extensive overview of all expected aspects, and is neither intended to identify the key or important elements of all aspects, nor to delineate 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 a more detailed description that will be given later.

[0005] In one aspect of the present disclosure, a method of wireless communication is provided. The method of wireless communication at a user equipment (UE) may include: indicating to a wireless network a capability to support one or more versions of an ML processing model; and receiving a configuration from the wireless network to apply a version of the ML processing model supported by the UE.

[0006] In another aspect of the present disclosure, a wireless communication apparatus is provided. The apparatus for wireless communication at a UE may include: a unit for indicating to a wireless network a capability of supporting one or more versions of an ML processing model; and a unit for receiving a configuration from the wireless network to apply a version of the ML processing model supported by the UE.

[0007] In another aspect of the present disclosure, a wireless communication apparatus is provided. The apparatus for wireless communication at a UE may include a memory and at least one processor, the at least one processor being coupled to the memory and configured to: indicate to a wireless network a capability of supporting one or more versions of an ML processing model; and receive a configuration from the wireless network to apply a version of the ML processing model supported by the UE.

[0008] In another aspect of the present disclosure, a computer-readable medium storing computer-executable code for wireless communication at a UE is provided. The computer-readable medium stores computer-executable code at the UE, which, when executed by a processor, may cause the processor to perform the following operations: indicating to a wireless network a capability to support one or more versions of an ML processing model; and receiving a configuration from the wireless network to apply a version of the ML processing model supported by the UE.

[0009] In one aspect of the present disclosure, a method of wireless communication is provided. The method of wireless communication at a wireless network entity may include: receiving an indication of a capability to support one or more versions of an ML processing model from a UE; and configuring the UE to apply the version of the ML processing model supported by the UE.

[0010] In another aspect of the present disclosure, an apparatus for wireless communication is provided. The apparatus for wireless communication at a wireless network entity may include: a unit for receiving an indication of a capability to support one or more versions of an ML processing model from a UE; and a unit for configuring the UE to apply a version of the ML processing model supported by the UE.

[0011] In another aspect of the present disclosure, a wireless communication apparatus is provided. The apparatus for wireless communication at a wireless network entity may include a memory and at least one processor, the at least one processor being coupled to the memory and configured to: receive an indication of a capability to support one or more versions of an ML processing model from a UE; and configure the UE to apply a version of the ML processing model supported by the UE.

[0012] In another aspect of the present disclosure, a computer-readable medium storing computer-executable code for wireless communication at a wireless network entity is provided. The computer-readable medium stores computer-executable code at the wireless network entity, which, when executed by a processor, may cause the processor to perform the following operations: receiving an indication of a capability to support one or more versions of an ML processing model from a user equipment (UE); and configuring the UE to apply a version of the ML processing model supported by the UE.

[0013] To accomplish the foregoing and related purposes, one or more aspects include features fully described below and particularly pointed out in the claims. The following description and drawings set forth in detail certain illustrative features of one or more aspects. However, these features are indicative of only some of the various ways in which the principles of the various aspects may be employed, and this description is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a diagram illustrating an example of a wireless communication system and an access network.

[0015] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0016] Figure 2B is a diagram illustrating an example of DL channels within a subframe according to various aspects of the present disclosure.

[0017] Figure 2C is a diagram illustrating an example of a second frame according to various aspects of the present disclosure.

[0018] Figure 2D is a diagram illustrating an example of UL channels within a subframe according to various aspects of the present disclosure.

[0019] Figure 3 is a diagram showing an example of a base station and a user equipment (UE) in an access network.

[0020] Figure 4A and 4B An example of wireless communication including an ML processing model is shown.

[0021] Figure 5 An example of wireless communication is shown.

[0022] Fig. 6A , 6B and 6C show examples of applications of ML processing models.

[0023] Figure 7 It is a call flow diagram for wireless communication.

[0024] Figure 8 is a flow chart of a method of wireless communication.

[0025] Fig. 9 is a diagram illustrating an example of a hardware implementation for an example apparatus.

[0026] Fig.10 is a flow chart of a method of wireless communication.

[0027] Fig.11 is a diagram illustrating an example of a hardware implementation for an example apparatus. DETAILED DESCRIPTION

[0028] The specific embodiments described below in conjunction with the accompanying drawings are intended to be descriptions of various configurations and are not intended to represent the only configurations in which the concepts described herein can be practiced. For the purpose of providing a comprehensive understanding of each concept, the specific embodiments include specific details. 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 the form of block diagrams to avoid obscuring such concepts.

[0029] Several aspects of telecommunication systems will now be presented with reference to various devices and methods. These devices and methods will be described in the detailed description below and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0030] For example, an element, or any part of an element, or any combination of elements, can 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, systems on 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 various functions described throughout the present disclosure. One or more processors in a processing system can execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other names, software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes, functions, etc.

[0031] Accordingly, in one or more examples, the described functions can be implemented in hardware, software, or any combination thereof. If implemented in software, the functions can be stored or encoded on a computer-readable medium as one or more instructions or codes. Computer-readable media include computer storage media. Storage media can be any available media that can be accessed by a computer. By way of example and not limitation, such computer-readable media 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, a combination of computer-readable media of the above types, or any other medium that can be used to store computer executable code that can be accessed by a computer in the form of instructions or data structures.

[0032] A UE in a wireless network may receive measurement information or may perform measurements. For example, a UE may receive data from one or more sensors. A UE may include a sensor and / or may receive and process data from a remote sensor. Additionally or alternatively, a UE may perform various wireless communication measurements (e.g., channel quality measurements, interference measurements, cell measurements). A UE may have the ability to process sensor data and / or measurement data based on machine learning to provide an indication or output to a wireless network. An example of a machine learning application may be used for handover measurements in a specific area or under specific conditions (e.g., on a high-speed train).

[0033] The machine learning applied by the UE may be model-based, and the model may be configured for the UE via a wireless network. The model may include an algorithm structure and / or weights configured by the network for the UE. In some examples, there may be multiple models, any of which may be configured by the network for the UE to apply. There may be a first model that is common to multiple networks, and there may be one or more alternative models. In one example, the first model may be common to multiple network operators, and the alternative model may be specific to a specific network operator. In some examples, the public model may be a more general model for a specific application, and may not be optimized for a specific network. The alternative machine processing model may include an algorithm structure and / or parameters that improve the processing for the corresponding network. For the example of a handover application of a UE on a high-speed train, a public model may provide a baseline model that can be applied to different UEs and different networks. In contrast, in one example, a network operator-specific model may include an algorithm structure and / or weights that improve the handover performance of the UE for the specific network.

[0034] As provided herein, the UE may provide capability information to the network indicating whether the UE supports a common model and / or one or alternative models. In some examples, the alternative model may be network-specific. The concepts provided herein are not limited to network-specific machine learning models or operator-specific machine learning models, and may also be applied to other scenarios of alternative models. The UE may indicate the supported models, versions of the models, and / or public land mobile network (PLMN) identifiers (IDs) to the network. The network may configure the UE to apply a machine learning model based on the UE capabilities. For example, if the UE supports a common model but does not support alternative modes, the network may configure the UE to apply a common machine learning model. If the UE supports one or more versions of a network-specific machine learning model, the network may select from the supported versions to configure the UE to apply a network-specific machine learning model. In some examples, the alternative machine learning model may be specific to a specific network operator.

[0035] Figure 1 1 is a diagram showing an example of a wireless communication system and access network 100. The wireless communication system (also referred to as a wireless wide area network (WWAN)) includes a base station 102, a UE 104, an evolved packet core (EPC) 160, and another core network 190 (e.g., a 5G core (5GC)). The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). A macro cell includes a base station. A small cell includes a femto cell, a pico cell, and a micro cell.

[0036] The base station 102 configured for 4G LTE (collectively referred to as the Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can interface with the EPC 160 via a first backhaul link 132 (e.g., an S1 interface). The base station 102 configured for 5G NR (collectively referred to as the Next Generation RAN (NG-RAN)) can interface with the core network 190 via a second backhaul link 184. Among other functions, the base station 102 can also perform one or more of the following functions: transmission of user data, wireless 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), user and device tracking, RAN information management (RIM), paging, positioning, and delivery of warning messages. Base stations 102 may communicate with each other directly or indirectly (eg, through EPC 160 or core network 190) over a third backhaul link 134 (eg, an X2 interface). First backhaul link 132, second backhaul link 184, and third backhaul link 134 may be wired or wireless.

[0037] The base station 102 can communicate wirelessly with the UE 104. Each of the base stations 102 can provide communication coverage for a corresponding geographic coverage area 110. There can be overlapping geographic coverage areas 110. For example, a small cell 102' can have a coverage area 110' that overlaps with the coverage area 110 of one or more macro base stations 102. A network including both small cells and macro cells can be referred to as a heterogeneous network. A heterogeneous network can also include a home evolved Node B (eNB) (HeNB), which can provide services to a restricted group called a closed subscriber group (CSG). The communication link 120 between the base station 102 and the UE 104 can include an uplink (UL) (also referred to as a reverse link) transmission from the UE 104 to the base station 102 and / or a downlink (DL) (also referred to as a forward link) transmission from the base station 102 to the UE 104. The communication link 120 can use multiple-input multiple-output (MIMO) antenna technology, which includes spatial multiplexing, beamforming and / or transmit diversity. The communication link may be through one or more carriers. The base station 102 / UE 104 may use a spectrum of up to Y MHz (e.g., 5, 10, 15, 20, 100, 400, etc. MHz) bandwidth per carrier allocated in a carrier aggregation of up to Yx MHz (x component carriers) for transmission in each direction. The carriers may be adjacent to each other or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​than for UL). The component carrier may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell), and the secondary component carrier may be referred to as a secondary cell (SCell).

[0038] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL WWAN spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH). The D2D communication may be through a variety of wireless D2D communication systems, such as, for example, FlashLinQ, WiMedia, Bluetooth, ZigBee, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0039] 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 in, for example, a 5 GHz unlicensed spectrum. When communicating in the unlicensed spectrum, the STA 152 / AP 150 may perform a clear channel assessment (CCA) prior to communication to determine whether the channel is available.

[0040] The small cell 102' may operate in a licensed and / or unlicensed spectrum. When operating in an unlicensed spectrum, the small cell 102' may employ NR and use the same unlicensed spectrum (e.g., 5 GHz, etc.) as used by the Wi-Fi AP 150. The small cell 102' employing NR in the unlicensed spectrum may improve coverage of the access network and / or increase capacity of the access network.

[0041] 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 identified with the frequency range names FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz. Frequencies between FR1 and FR2 are often referred to as mid-band frequencies. Although a portion of FR1 is greater than 6 GHz, FR1 is often (interchangeably) referred to as the "sub-6 GHz" band in various documents and articles. A similar naming issue sometimes arises regarding FR2, which is often (interchangeably) referred to as the "millimeter wave" band in documents and articles, although it is different from the extremely high frequency (EHF) band (30 GHz-300 GHz), which is identified as the "millimeter wave" band by the International Telecommunication Union (ITU).

[0042] In view of the above, unless otherwise specifically stated, it should be understood that if the term "sub-6 GHz" or the like is used herein, it can broadly represent frequencies that can be less than 6 GHz, can be within FR1, or can include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that if the term "millimeter wave" or the like is used herein, it can broadly represent frequencies that can include mid-band frequencies, can be within FR2, or can be within the EHF band.

[0043] The 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, a gNodeB (gNB), or another type of base station. Some base stations, such as gNB 180, may operate in traditional sub-6 GHz spectrum, in millimeter wave frequencies, and / or near millimeter wave frequencies to communicate with UE 104. When the gNB 180 operates in millimeter wave or near millimeter wave frequencies, the gNB 180 may be referred to as a millimeter wave base station. The millimeter wave base station 180 may utilize beamforming 182 with the UE 104 to compensate for the extremely high path loss and short distance. The base station 180 and the UE 104 may each include multiple antennas, such as antenna elements, antenna panels, and / or antenna arrays, to facilitate beamforming.

[0044] The base station 180 may transmit beamformed signals in one or more transmit directions 182' to the UE 104. The UE 104 may receive beamformed signals from the base station 180 in one or more receive directions 182". The UE 104 may also transmit beamformed signals to the base station 180 in one or more transmit directions. The base station 180 may receive beamformed signals from the UE 104 in one or more receive directions. The base station 180 / UE 104 may perform beam training to determine the best receive and transmit directions for each of the base station 180 / UE 104. The transmit direction and receive direction for the base station 180 may be the same or may be different. The transmit direction and receive direction for the UE 104 may be the same or may be different.

[0045] The EPC 160 may include a mobility management entity (MME) 162, other MMEs 164, a serving gateway 166, a multimedia broadcast multicast service (MBMS) gateway 168, a broadcast multicast service center (BM-SC) 170, and a packet data network (PDN) gateway 172. The MME 162 may communicate with a home subscriber server (HSS) 174. The MME 162 is a control node that handles signaling between the UE 104 and the EPC 160. Generally speaking, the MME 162 provides bearer and connection management. All user Internet Protocol (IP) packets are transmitted through the serving gateway 166, which itself is connected to the PDN gateway 172. The PDN gateway 172 provides IP address allocation and other functions to the UE. The PDN gateway 172 and the BM-SC 170 are connected to IP services 176. The IP services 176 may include the Internet, an intranet, an IP multimedia subsystem (IMS), a PS streaming service, and / or other IP services. The BM-SC 170 may provide functionality for MBMS user service setup and delivery. The BM-SC 170 may serve as an entry point for content provider MBMS transmissions, may be used to authorize and initiate MBMS bearer services within a public land mobile network (PLMN), and may be used to schedule MBMS transmissions. The MBMS gateway 168 may be used to distribute MBMS services to base stations 102 belonging to a multicast broadcast single frequency network (MBSFN) area broadcasting a particular service, and may be responsible for session management (start / stop) and for collecting eMBMS-related billing information.

[0046] The core network 190 may include an access and mobility management function (AMF) 192, other AMFs 193, a session management function (SMF) 194, and a user plane function (UPF) 195. The AMF 192 may communicate with a unified data management unit (UDM) 196. The AMF 192 is a control node that handles signaling between the UE 104 and the core network 190. Typically, the AMF 192 provides QoS flow and session management. All user Internet Protocol (IP) packets are transmitted through the UPF 195. The UPF 195 provides UE IP address allocation and other functions. The UPF 195 is connected to an IP service 197. The IP service 197 may include the Internet, an intranet, an IP multimedia subsystem (IMS), a packet switching (PS) streaming service, and / or other IP services.

[0047] A base station may include and / or be referred to as a gNB, a Node B, an eNB, an access point, a base transceiver station, a wireless base station, a wireless transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmit receive point (TRP), or some other appropriate term. Base station 102 provides an access point to EPC 160 or core network 190 for UE 104. Examples of UE 104 include a cellular phone, a smart phone, a session initiation protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio unit, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., an MP3 player), a camera, a game console, a tablet computer, a smart device, a wearable device, a vehicle, an electric meter, a gas pump, a large or small kitchen appliance, a healthcare device, an implant, a sensor / actuator, a display, or any other similarly functional device. Some of UE 104 may be referred to as IoT devices (e.g., a parking meter, a gas pump, an oven, a vehicle, a heart monitor, etc.). UE 104 may also be referred to as a station, a mobile station, a user station, a mobile unit, a user unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile user station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handheld device, a user agent, a mobile client, a client, or some other suitable terminology.

[0048] Refer again Figure 1 and 2. In certain aspects, the UE 104 may include an ML processing model management component 198 configured to: indicate to the wireless network an ability to support one or more versions of the ML processing model; and receive a configuration from the wireless network to apply a version of the ML processing model supported by the UE. In certain aspects, the base station 180 may include an ML processing model management component 199 configured to: receive an indication of an ability to support one or more versions of the ML processing model from the UE; and configure the UE to apply a version of the ML processing model supported by the UE. Although the following description may focus on 5G NR, the concepts described herein may be applicable to other similar fields, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies.

[0049] Figure 2A is a diagram 200 showing an example of a first subframe within a 5G NR frame structure. Figure 2B is a schematic diagram 230 showing an example of DL channels within a 5G NR subframe. Figure 2C is a diagram 250 showing an example of a second subframe within a 5G NR frame structure. Figure 2D280 is a diagram showing an example of UL channels within a 5G NR subframe. The 5G NR frame structure can be frequency division duplex (FDD) (wherein, for a particular set of subcarriers (carrier system bandwidth), a subframe within a subcarrier set is dedicated to either DL or UL), or can be time division duplex (TDD) (wherein, for a particular set of subcarriers (carrier system bandwidth), a subframe within a subcarrier set is dedicated to both DL and UL). Figure 2A , 2C In the example provided, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexible between DL / UL, and subframe 3 is configured with slot format 1 (all of which are 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 full DL and full UL, respectively. Other slot formats 2-61 include a mix of DL, UL and flexible symbols. The UE is configured with a slot format (dynamically configured by DL control information (DCI) or semi-statically / statically configured by radio resource control (RRC) signaling) through the received slot format indicator (SFI). It should be noted that the following description also applies to the 5G NR frame structure as TDD.

[0050] Other wireless communication technologies may have different frame structures and / or different channels. A frame (10ms) may be divided into 10 subframes (1ms) of equal size. Each subframe may include one or more time slots. A subframe may also include a microslot, which may include 7, 4 or 2 symbols. Each time slot may include 7 or 14 symbols, depending on the time slot configuration. For time slot configuration 0, each time slot may include 14 symbols, and for time slot configuration 1, each time slot may include 7 symbols. The symbol on the DL may be a cyclic prefix (CP) orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbol (also referred to as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single stream transmission). The number of time slots in a subframe may be based on the time slot configuration and numerology. For slot configuration 0, different digital schemes μ0 to 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For slot configuration 1, different digital schemes 0 to 2 allow 2, 4, and 8 slots per subframe, respectively. Accordingly, for slot configuration 0 and digital scheme μ, there are 14 symbols / slot and 2 μtime slots / subframe. The subcarrier spacing and symbol length / duration are functions of the digital scheme. The subcarrier spacing can be equal to 2 μ *15kHz, where μ is digital scheme 0 to 4. Thus, digital scheme μ=0 has a subcarrier spacing of 15kHz, and digital scheme μ=4 has a subcarrier spacing of 240kHz. The symbol length / duration is inversely related to the subcarrier spacing. Figures 2A-2D An example is provided for slot configuration 0 (with 14 symbols per slot) and digital scheme μ=2 (with 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 a frame set, there may be one or more different bandwidth parts (BWPs) that are frequency-division multiplexed (see Figure 2B ). Each BWP can have a specific numbering scheme.

[0051] The resource grid can be used to represent the frame structure. Each time slot includes a resource block (RB) (also called a physical RB (PRB)), which includes 12 consecutive subcarriers. The resource grid is divided into multiple resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0052] As in Figure 2A As shown in , some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) for channel estimation at the UE (indicated as R for a specific configuration). x , but other DM-RS configurations are possible) and a channel state information reference signal (CSI-RS). The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0053] Figure 2BExamples of various DL channels within a subframe of a frame are shown. A physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE including six RE groups (REGs), each REG including four consecutive REs in one OFDM symbol. A 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 common search space, a UE-specific search space) during a PDCCH monitoring opportunity on a CORESET, wherein the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at larger and / or lower frequencies across the channel bandwidth. A primary synchronization signal (PSS) may be within symbol 2 of a particular subframe of a frame. The PSS is used by UE 104 to determine subframe / symbol timing and physical layer identification. A secondary synchronization signal (SSS) may be within symbol 4 of a particular subframe of a frame. The SSS is used by the UE to determine the physical layer cell identification 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 above-mentioned 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 referred to as an SS block (SSB)). The MIB provides the number of RBs in the system bandwidth and the system frame number (SFN). The physical downlink shared channel (PDSCH) carries user data, broadcast system information that is not sent through the PBCH (such as a system information block (SIB)), and paging messages.

[0054] As in Figure 2C As shown in , some of 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 may send DM-RS for a physical uplink control channel (PUCCH) and DM-RS for a physical uplink shared channel (PUSCH). The PUSCH DM-RS may be sent in the first one or two symbols of the PUSCH. The PUCCH DM-RS may be sent in different configurations depending on whether a short PUCCH or a long PUCCH is sent and depending on the specific PUCCH format used. The UE may send a sounding reference signal (SRS). The SRS may be sent in the last symbol of the subframe. The SRS may have a comb structure, and the UE may send the SRS on one of the combs. The SRS may be used by the base station for channel quality estimation to enable frequency-dependent scheduling on the UL.

[0055] Figure 2D Examples of various UL channels within a subframe of a frame are shown. The PUCCH may be positioned as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicator (CQI), precoding matrix indicator (PMI), rank indicator (RI), and hybrid automatic repeat request (HARQ) acknowledgement (ACK) (HARQ-ACK) information (ACK / negative ACK (NACK)) feedback. The PUSCH carries data and may additionally be used to carry a buffer status report (BSR), a power headroom report (PHR), and / or UCI.

[0056] Figure 3 3 is a block diagram of a base station 310 communicating with a UE 350 in an access network. In the DL, IP packets from the EPC 160 may be provided to the controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functions. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides: RRC layer functions associated with: broadcasting of 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 functions associated with: header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and switching support functions; RLC layer functions associated with: transmission of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functions 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 through HARQ, priority handling, and logical channel prioritization.

[0057] The transmit (TX) processor 316 and the 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 of the transmission channel, forward error correction (FEC) encoding / decoding of the transmission channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The TX processor 316 processes the mapping to the signal constellation 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 coded and modulated symbols can then be divided into parallel streams. Each stream can then be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., pilot) in the time domain and / or frequency domain, and then combined using an inverse fast Fourier transform (IFFT) to generate a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially precoded to generate multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine coding and modulation schemes and for spatial processing. Channel estimates may be derived based on reference signals and / or channel condition feedback sent by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318TX. Each transmitter 318TX may modulate an RF carrier with a corresponding spatial stream for transmission.

[0058] At the UE 350, each receiver 354RX receives a signal through its corresponding antenna 352. Each receiver 354RX recovers the information modulated onto the RF carrier and provides the information to a receive (RX) processor 356. The TX processor 368 and the 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 stream destined for the UE 350. If multiple spatial streams are destined for the UE 350, they can be combined into a single OFDM symbol stream by the RX processor 356. The RX processor 356 then uses a fast Fourier transform (FFT) to convert 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 on each subcarrier and the reference signal are recovered and demodulated by determining the most likely signal constellation point sent by the base station 310. These soft decisions can be based on the channel estimate calculated by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by base station 310. The data and control signals are then provided to controller / processor 359, which implements layer 3 and layer 2 functions.

[0059] The controller / processor 359 may be associated with a memory 360 that stores program codes 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 channels and logical channels to recover IP packets from the EPC 160. The controller / processor 359 is also responsible for error detection using an ACK and / or NACK protocol to support HARQ operations.

[0060] Similar to the functions described in conjunction with DL transmissions performed by the base station 310, the controller / processor 359 provides: RRC layer functions associated with: system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functions associated with: header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functions associated with: transmission of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functions associated with: mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0061] Channel estimates derived by the channel estimator 358 based on a reference signal or feedback sent by the base station 310 may be used by the TX processor 368 to select the appropriate coding and modulation schemes, and to facilitate spatial processing. The spatial streams generated by the TX processor 368 may be provided to different antennas 352 via separate transmitters 354TX. Each transmitter 354TX may modulate an RF carrier with a corresponding spatial stream for transmission.

[0062] UL transmissions are processed at the base station 310 in a manner similar to that described in conjunction with the receiver functionality at the UE 350. Each receiver 318RX receives a signal through its respective antenna 320. Each receiver 318RX recovers information modulated onto an RF carrier and provides the information to a RX processor 370.

[0063] The controller / processor 375 may be associated with a memory 376 that stores program codes and data. The memory 376 may be referred to as a computer readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets from the UE 350. The IP packets from the controller / processor 375 may 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 operations.

[0064] At least one of the TX processor 368, the RX processor 356, and the controller / processor 359 may be configured to perform operations related to Figure 1 198. At least one of the TX processor 316, the RX processor 370, and the controller / processor 375 may be configured to perform operations related to Figure 1 Various aspects related to the ML processing model management component 199.

[0065] Figure 4A An example of a wireless communication and ML processing model is shown for a UE 402 and a base station 404. The UE 402 may provide device context awareness with the capability to identify different context scenarios. Figure 4A A non-limiting example is shown where base station 404 may indicate a contextual scenario, such as a machine learning application for a particular location. Other examples of machine learning based processing at the UE may include, for example, a handover application on a high-speed train. The concepts presented herein are not limited to machine learning processing for identifying contextual scenarios or for handover applications, and may be applied to other UE processing. Figure 4A , the location is shown as a commercial location, such as a mall. UE 402 can use the ML processing model to provide device context awareness. In one example, the context awareness can relate to a specific commercial location, such as a store, restaurant, or entertainment venue within a commercial location (such as a mall). Figure 4B An example of inputs and outputs of an ML processing model 406 that may be employed by the UE 402 is shown. For example, the ML processing model may be a fusion model. The ML processing model may include algorithms and parameters (e.g., weights) that build a mathematical model based on data in order to make predictions, decisions, or provide other outputs. The UE 402 may be equipped with one or more sensors, or may receive input data 408 from one or more sensors. The UE 402 may process the data and / or other wireless communication measurement data based on machine learning. The UE 402 may include a machine learning engine that may be used for a number of applications, including Figure 4A Device context awareness in .

[0066] The wireless communication device may process data / measurements based on artificial intelligence (AI) to provide an output. The device (e.g., base station 404 or UE 402) may be configured with multiple sensors and may also be configured with an AI engine (e.g., machine learning) to implement actions based on machine learning. The UE may receive input data from a sensor, such as GPS data with location information, sound data from a microphone, visual data from a camera, speed data from an accelerometer, orientation data from a gyroscope, direction data from a magnetometer, biological data from a biological sensor (such as vital sign data), etc. The device may include an ML model 406, which is configured to receive different sensor data inputs and measurement inputs. The received inputs (e.g., sensor data, measurement data, etc.) may be combined by the ML model 406 based on a machine learning scheme. For example, the UE may perform measurements such as at least one of signal strength indicator (RSSI) / reference signal received power (RSRP) / reference signal received quality (RSRQ) based on different channels, channel quality indicator (CQI) / precoding matrix indicator (PMI) / rank indicator (RI) calculations, etc. The ML model 406 may receive input data 408 and measurement inputs 410 (e.g., wireless communication measurements) from one or more sensors, and may process the input data based on a machine learning model with a configured algorithm structure and weights to generate various outputs 412. The output 412 may be a prediction, decision, or other information that the UE may use or that may be reported to the network. For example, the output generated by the ML model 406 may be a scenario indication. That is, the ML model 406 may generate an indication of the operating scenario of the UE 402.

[0067] For example, base station 404 may be located at (or near) a shopping mall and has the ability to identify the contextual scene of UE 402 attached to base station 404. Attached UE 402 may be equipped with various sensors, and UE 402 may report its location / speed / direction information to base station 404. Base station 404 may identify that UE 402 may be entering a shopping mall based on its analysis (e.g., deep learning). For example, a UE (such as a smartphone, a wearable device, etc.) may be connected to a base station, and the smartphone may be moved from outdoor to indoor (e.g., a coffee shop, a shopping mall, or other location). UE may imply a corresponding environment, and such implied information may be used for other complex applications. Base station 404 may indicate the identified contextual scene to UE 402. According to the contextual scene identified by base station 404, the shopping mall may have high congestion. Base station 404 may configure resources corresponding to the contextual scene of UE 402 in the shopping mall for UE 402. In other examples, a machine learning model may be applied to provide switching information in a specific area or under specific conditions (e.g., on a high-speed train).

[0068] Figure 5 An example of wireless communication is shown, including a UE 502 and a wireless network 504 and an ML processing model 506 at the UE 502. The intelligent wireless system can be derived from various sensor data and environmental data. First, the UE 502 can be enabled using various sensors, including a global positioning system (GPS) for location information, an accelerometer for recording speed changes, a gyroscope for learning orientation, etc. The UE 502 can be configured with a lot of environmental data based on various measurements. For example, the network-configured environment of the channel can include at least one of signal strength indicator (RSSI) / reference signal received power (RSRP) / reference signal received quality (RSRQ) based on different channels, channel quality indicator (CQI) / precoding matrix indicator (PMI) / rank indicator (RI) calculation, etc.

[0069] The ML processing model 506 may also include an AI engine for improving the application. For example, the UE 502 may include an ML processing model 506, which may include a convolutional layer that may be used to extract features of the data at 508, a sequence model that may track temporal changes and predict future actions, and / or an autoencoder structure that may be a candidate for data compression.

[0070] At 507, the network 504 may configure the model for the UE 502. At 509, the UE 502 may process various sensor data and environmental data based on the model to extract features, and the UE 502 may feed the output back to the network 504. The network 504 may define the model, and the model may generally be a machine learning-based solution. The input may be sensor data or environmental measurements, and the output may be the extracted features. The extracted features may be intermediate outputs, which may be unexplainable variables, or the extracted features may be some specific parameters, which may be interpretable.

[0071] Fig. 6A , 6B 6C show examples of applications of ML processing models. First, Fig. 6AA first application 600 of an ML processing model for intermediate extracted features (e.g., for handover prediction and / or determination) is shown, including two ML processing models. The two ML processing models may include a first model (model-1) 602 on the UE side and a second model (model-2) 604 on the network side. The output of model-1 is the extracted features used for model-2 to make a handover decision. That is, the first model 602 may receive sensor data as input and feed back extracted features based on the received sensor data to the second model 604. Based on the extracted features, the second model may determine the final determination, such as a handover decision, based on the intermediate extracted features. The first model 602 may be based on a network configuration. That is, the first model 602 may be configured by the network side.

[0072] Figure 6B A second application 610 of an ML processing model for compressing / decompressing features (e.g., for channel estimation feedback) is shown, including two ML processing models. The two ML processing models may include a first model (Model-1) 612 for compression on the UE side and a second model (Model-2) 614 for decompression on the network side. That is, the first model 612 may receive sensor data as input and feed back compressed features to the second model 614. The first model 612 may provide compressed features based on the received sensor data to the second model 614. The second model 614 may recover the sensor data from the compressed features. The output of the first model 612 may be an extracted feature (expressed feature), and the output of the second model 614 may decompress the feature.

[0073] Figure 6C A third application 620 of an ML processing model for a specified final parameter (e.g., for context-aware indication) is shown, including one ML processing model on the UE side. That is, a first model (Model-1) 622 on the UE side is configured based on a network configuration. The first model 622 may receive sensor data as input, and the output of the model may be a specified parameter for indicating the current scenario. For example, based on the model, the UE will recognize that it is in high mobility mode. The first model 622 may be configured by the network, or may be implemented based on the UE only.

[0074] In some aspects, the network can configure the ML processing model of the UE for AI applications. The relevant processes and signaling supporting the configuration may include two parts, including a process for indicating the relevant UE capabilities to the network and a process for configuring the ML processing model. In addition, operator-based models can match different scenarios. Different scenarios may include processes for switching, data compression, or specific indications from the UE side. For example, for switching applications, in a specific area, the network deployment between different operators may be different, the switching mode may be different, or UEs accessing different operators may take different switching actions in the same area. Therefore, we can configure operator-based models to support different environments.

[0075] In some aspects, multiple types of models may be provided for specific applications. The model may include an algorithm structure and corresponding weights. The model may include a standard model (e.g., a model that is common to multiple operators) and an operator-specific model (e.g., a model that is specific to a specific wireless network operator or optimized for a specific wireless network operator). The standard model may be a model referred to as a public model, and the standard model may be a default option for UEs supported by various operators that are enabled with machine learning functions. That is, the standard model may be a basic model for a scenario application without specific optimization for a specific wireless network operator.

[0076] The operator-specific model may be based on the operator configuration. The definition of the operator-specific model may be related to the operator's implementation. The UE may support the standard model and may also support the operator-specific model. The UE may support the standard model and the operator-specific model. In some examples, the UE may not support the operator-specific model.

[0077] One non-limiting example of a machine learning model is a model for switching indications in specific areas or under specific conditions (e.g., in a high-speed train).

[0078] In one or more examples, at least one standard machine learning model can be configured for UEs in scenarios supported by various networks (e.g., various network operators). That is, the standard model can provide a baseline machine learning model that can be applied by various UEs to various networks (e.g., to different network operators). The alternative model can be optimized to achieve better performance for a specific network. Therefore, at least one alternative model can be provided for a specific wireless network (e.g., a specific network operator) to provide a model optimized for a specific network. As a non-limiting example, at least one operator-specific model can be provided for operator 1 to match high-speed trains in the area, so that the UE can provide switching instructions to the network operator when traveling on the high-speed train. The network can configure the UE to apply an operator-specific model. The example of a switching application for a high-speed train is merely an example of the concept of applying a machine learning processing model for a UE. The concepts presented herein can be applied to a variety of different UE applications.

[0079] As described herein, the UE may indicate its capabilities to the network so that the network may determine whether the UE supports one or more of the machine learning models. In some examples, the UE may indicate its support for one or more machine learning models in UE capability signaling. The UE may provide capability signaling to the UE. As an example, the UE may provide capability signaling to the network in RRC signaling. In other examples, the UE may indicate the capabilities to the network in other signaling. The UE may report its capabilities to the network, and the network may configure the model for the UE. RRC signaling may include multiple information elements (IEs). The IEs may be combined in a single RRC message or provided as separate IEs. In some examples, information may be provided in a single IE, for example, the single IE combines information about support for different models.

[0080] The UE may indicate that the UE supports at least one ML processing model and may indicate which scenario is supported. For example, the IE format shown in Table 1-A may be used to indicate to the network whether the UE supports the ML processing model and which scenario the UE may support.

[0081]

[0082] Table 1-A

[0083] If the UE supports the ML processing model, the UE may indicate to the network whether the UE supports the standard model and / or different versions of the model. For example, another version may be an operator-specific model. For example, the IE format shown in Table 1-B may be used to indicate whether the UE supports the standard model and / or a model for a specific operator. For example, the UE may indicate support for the standard model without supporting other versions of the model, for example, without supporting a model for a specific operator. The UE may indicate support for the standard model and one or more operator-specific models. The UE may indicate support for an operator-specific model without supporting the standard model.

[0084]

[0085] Table 1-B

[0086] If the UE supports one or more versions of a model other than a common model, the UE may indicate the supported versions. For example, the UE may support one or more versions of an operator-specific model and may indicate the versions and the PLMNs that may be associated with the supported versions of the model. For example, the IE format shown in Table 1-C may be used to indicate the versions of the model supported by the UE and indicate the PLMNs that may be associated with the supported versions of the model.

[0087]

[0088] Table 1-C

[0089] In response to an indication from the UE, the network may configure the UE to apply one of the versions of the ML processing model supported by the UE. That is, the network may configure the ML processing model for the UE and indicate to the UE which ML processing model should be used for the application. The operator-specific dictionary may be associated with the PLMN ID.

[0090] The network may configure the UE to apply a specific version of the ML processing model. The network may configure the UE with a standard ML processing model or an operator-specific ML processing model (one or both). The network may configure the UE with a specific version of the machine learning model, for example, a specific version of the standard model or a specific version of the operator-specific ML model. The network may configure the parameters of the model. For example, the IE format shown in Table 2-A may be used to configure the UE with one of the versions of the ML processing model for the UE and the parameters of the model.

[0091]

[0092] Table 2-A

[0093] In addition, the network can configure the model content, which mainly includes two parts, including the structure and algorithm of the ML processing model and the corresponding weights of the ML processing model. For example, the IE format shown in Table 2-B can be used to configure the UE with the structure and algorithm of the ML processing model and the corresponding weights of the ML processing model.

[0094]

[0095] Table 2-B

[0096] Figure 7 7 is a call flow diagram 700 for wireless communications including a UE 702 and a base station 704. At 706, the UE 702 may indicate a capability to support one or more versions of an ML processing model to the wireless network (or base station) 704. The indication from the UE may indicate a capability to support one or more of a first version of the ML processing model that is common across wireless network operators and at least one operator-specific version of the ML processing model, a version identifier of each operator-specific machine learning model supported by the UE, and / or a PLMN ID associated with each operator-specific machine learning model supported by the UE.

[0097] At 708, a base station 704 of the wireless network may configure the UE 702 to apply a version of the ML processing model supported by the UE 702. The configuration from the wireless network may instruct the UE to use at least one of a first version of the ML processing model supported by the UE or an operator-specific version of the ML processing model, a version identifier of the ML processing model configured for the UE, a PLMN ID associated with the operator-specific machine learning model configured for the UE, and / or a network-specific algorithm structure or one or more weights of the operator-specific machine learning model supported by the UE, such as shown at 712.

[0098] Figure 8 800 is a flow chart of a method of wireless communication. The method may be performed by a UE (eg, UE 104 / 402 / 502 / 602 / 612 / 622 / 702; apparatus 802).

[0099] At 802, the UE may indicate to a wireless network (or base station) an ability to support one or more versions of an ML process model (e.g., as at 706). The indication from the UE may indicate an ability to support one or more of a first version of an ML process model that is common across multiple wireless networks (e.g., multiple network operators) and at least one alternative version of the ML process model. The alternative version of the ML process model may be a network-specific ML process model, e.g., an operator-specific ML process model. The UE may indicate a version identifier of each alternative machine learning model supported by the UE, and / or a PLMN ID associated with each alternative machine learning model supported by the UE. For example, 802 may be performed by an ML process model management component 940.

[0100] At 804, the UE may receive a configuration from the wireless network to apply a version of the ML processing model supported by the UE (e.g., as at 708). The configuration from the wireless network may instruct the UE to use at least one of a first version of the ML processing model supported by the UE or an alternative version of the ML processing model (e.g., a network-specific or operator-specific ML processing model), a version identifier of the ML processing model configured for the UE, a PLMN ID associated with the alternative machine learning model configured for the UE, and / or a network-specific algorithm structure or one or more weights of the alternative machine learning model supported by the UE. For example, 804 may be performed by the ML processing model management component 940.

[0101] Fig. 9900 is a diagram illustrating an example of a hardware implementation for an apparatus 902. In some aspects, the apparatus 902 is a UE and includes a cellular baseband processor 904 (also referred to as a modem) coupled to a cellular RF transceiver 922 and one or more subscriber identity modules (SIM) cards 920, an application processor 906 coupled to a secure digital (SD) card 908 and a screen 910, a Bluetooth module 912, a wireless local area network (WLAN) module 914, a global positioning system (GPS) module 916, and a power supply 918. The cellular baseband processor 904 communicates with the UE 104 and / or BS 102 / 180 through the cellular RF transceiver 922. The cellular baseband processor 904 may include a computer-readable medium / memory. The computer-readable medium / memory may be non-transitory. The cellular baseband processor 904 is responsible for general processing, including executing software stored on the computer-readable medium / memory. The software, when executed by the cellular baseband processor 904, causes the cellular baseband processor 904 to perform the various functions described above. The computer-readable medium / memory may also be used to store data that is manipulated by the cellular baseband processor 904 when executing software. The cellular baseband processor 904 also includes a receiving component 930, a communication manager 932, and a transmitting component 934. The communication manager 932 includes one or more of the components shown. The components within the communication manager 932 may be stored in a computer-readable medium / memory and / or configured as hardware within the cellular baseband processor 904. The cellular baseband processor 904 may be a component of the UE 350 and may include a memory 360 and / or at least one of a TX processor 368, an RX processor 356, and a controller / processor 359. In one configuration, the device 902 may be a modem chip and include only the baseband processor 904, and in another configuration, the device 902 may be the entire UE (e.g., see Figure 3 350) and includes additional modules of device 902.

[0102] The communication manager 932 includes an ML processing model management component 940, which is configured to: indicate to the wireless network (or base station) the ability to support one or more versions of the ML processing model; and receive a configuration from the wireless network to apply the version of the ML processing model supported by the UE, for example, as described in conjunction with 802 and 804.

[0103] The apparatus may include executing Figure 7 and 8 Each of the blocks in the algorithm in the above flowchart has additional components. Therefore, it can be performed by the components Figure 7 and 8Each block in the above flowchart of the present invention may include one or more of those components. The components may 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 implementation by a processor, or some combination thereof.

[0104] In one configuration, the apparatus 902 (specifically, the cellular baseband processor 904) includes: a unit for indicating to the wireless network the ability to support one or more versions of the ML processing model; and a unit for receiving a configuration from the wireless network to apply the version of the ML processing model supported by the UE (e.g., a receiving component 930, an ML processing model management component 940, and / or a sending component 934). The above-mentioned means may be one or more of the above-mentioned components of the apparatus 902 configured to perform the functions recited by the above-mentioned means. As described above, the apparatus 902 may include a TX processor 368, an RX processor 356, and a controller / processor 359. Therefore, in one configuration, the above-mentioned means may be the TX processor 368, the RX processor 356, and the controller / processor 359 configured to perform the functions recited by the above-mentioned means.

[0105] Fig.10 1000 is a flow chart of a method of wireless communication. The method may be performed by a base station (eg, base station 102 / 180 / 404 / 504 / 604 / 614 / 624 / 704; apparatus 1102).

[0106] At 1002, the base station may receive an indication of an ability to support one or more versions of a machine learning process model from a UE (e.g., as at 706). The indication from the UE may indicate an ability to support one or more of a first version of an ML process model that is common across multiple wireless networks and at least one alternative version of the ML process model (such as a network-specific ML process model or an operator-specific ML process model). The UE may indicate a version identifier of each alternative machine learning model supported by the UE, and / or a PLMN ID associated with each alternative machine learning model supported by the UE. For example, 1002 may be performed by the ML process model management component 940.

[0107] At 1004, the base station may configure the UE to apply a version of the machine learning processing model supported by the UE (e.g., as at 708). The configuration from the wireless network may instruct the UE to use at least one of a first version of the ML processing model supported by the UE or an alternative version of the ML processing model, a version identifier of the ML processing model configured for the UE, a PLMN ID associated with the alternative machine learning model configured for the UE, and / or a network-specific algorithm structure or one or more weights of the alternative machine learning model supported by the UE. For example, 1004 may be performed by the ML processing model management component 940.

[0108] Fig.11 1100 is a diagram showing an example of a hardware implementation for an apparatus 1102. The apparatus 1102 is a BS and includes a baseband unit 1104. The baseband unit 1104 can communicate with the UE 114 via a cellular RF transceiver. The baseband unit 1104 may include a computer-readable medium / memory. The baseband unit 1104 is responsible for general processing, including executing software stored on the computer-readable medium / memory. The software, when executed by the baseband unit 1104, causes the baseband unit 1104 to perform the various functions described above. The computer-readable medium / memory can also be used to store data manipulated by the baseband unit 1104 when executing the software. The baseband unit 1104 also includes a receiving component 1130, a communication manager 1132, and a sending component 1134. The communication manager 1132 includes one or more 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 BS 311 and may include a memory 376 and / or at least one of the TX processor 316 , the RX processor 370 , and the controller / processor 375 .

[0109] The communication manager 1132 includes an ML processing model management component 1140, which is configured to: receive an indication of the ability to support one or more versions of the machine learning processing model from the UE; and configure the UE to apply a version of the machine learning processing model supported by the UE, for example, as described in combination with 1002 and 1004.

[0110] The apparatus may include executing Figure 7 and 10 Each of the blocks in the algorithm in the above flowchart has additional components. Therefore, it can be performed by the components Figure 7 and 10Each block in the above flowchart of the present invention may include one or more of those components. The components may 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 implementation by a processor, or some combination thereof.

[0111] In one configuration, the apparatus 1102 (specifically, the baseband unit 1104) includes: a unit for receiving an indication of the ability to support one or more versions of a machine learning (ML) processing model from a UE; and a unit for configuring the UE to apply a version of the ML processing model supported by the UE (e.g., a receiving component 1130, an ML processing model management component 1140, and / or a sending component 1134). The above-mentioned units may be one or more of the above-mentioned components of the apparatus 1102 configured to perform the functions recited by the above-mentioned units. As described above, the apparatus 1102 may include a TX processor 316, an RX processor 370, and a controller / processor 375. Therefore, in one configuration, the above-mentioned units may be the TX processor 316, the RX processor 370, and the controller / processor 375 configured to perform the functions recited by the above-mentioned units.

[0112] The UE may indicate to the wireless network a capability to support one or more versions of the ML processing model, and a wireless network entity of the wireless network may configure the UE to apply the versions of the ML processing model supported by the UE.

[0113] The indication from the UE may indicate: an ability to support one or more of a first version of an ML processing model that is common across wireless network operators and at least one operator-specific version of the ML processing model, a version identifier of each operator-specific machine learning model supported by the UE, and / or a public land mobile network (PLMN) identifier (ID) associated with each operator-specific machine learning model supported by the UE.

[0114] The configuration from the wireless network may indicate that the UE uses a first version of an ML processing model supported by the UE or an operator-specific version of the ML processing model, a version identifier of the ML processing model configured for the UE, a public land mobile network (PLMN) identifier (ID) associated with the operator-specific machine learning model configured for the UE, and / or at least one of a network-specific algorithm structure or one or more weights of the operator-specific machine learning model supported by the UE.

[0115] The ML processing model may be used to process at least one of the sensor data or the wireless channel measurement. The UE may indicate to the wireless network the scenarios supported by the UE for at least one ML processing model.

[0116] It should be understood that the specific order or hierarchy of the blocks in the disclosed process / flowchart is an illustration of an exemplary method. It should be understood that the specific order or hierarchy of the blocks in the process / flowchart can be rearranged based on design preferences. In addition, some blocks can be merged or omitted. The attached method claims provide the elements of each block in an exemplary order and are not meant to be limited to the specific order or hierarchy provided.

[0117] The foregoing description is provided so that any person skilled in the art can implement 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 various aspects shown herein, but are given the full scope consistent with the textual claims, wherein, unless explicitly stated as such, reference to the singular element is not intended to mean "one and only one", but "one or more". Terms such as "if", "when ..." and "while ..." should be interpreted as "under the condition of ...", rather than meaning an immediate time relationship or reaction. That is, these phrases (e.g., "when ...") do not mean immediate action in response to the occurrence of an action or during the occurrence of an action, but only mean that the action will occur if the condition is met, but do not require a specific or immediate time constraint for the occurrence of the action. The word "exemplary" is used herein to mean "used as an example, instance or illustration". Any aspect described as "exemplary" herein is not necessarily interpreted as being preferred to or having advantages over other aspects. Unless otherwise expressly stated, the term "some" refers to 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 or several members of A, B, or C. All structural and functional equivalents to the elements of the various aspects described throughout the disclosure that are known or later become known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed by the claims. Furthermore, no disclosure herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly recited in the claims. The words "module," "mechanism," "element," "device," etc. may not be substitutes for the word "unit." Thus, no claim element is to be interpreted as a unit-plus-function unless the element is explicitly recited using the phrase "unit for..."

[0118] The following examples are merely illustrative and may be combined with other examples or aspects of the teachings described herein, but are not limited thereto.

[0119] Example 1 is a method of wireless communication at a UE, comprising: indicating to a wireless network an ability to support one or more versions of a machine learning processing model; and receiving a configuration from the wireless network to apply a version of the machine learning processing model supported by the UE.

[0120] Example 2 is a method according to Example 1, wherein the UE indicates the capability of supporting one or more of a first version of the machine learning processing model and at least one alternative version of the machine learning processing model that is common across multiple wireless networks.

[0121] Example 3 is a method according to any of Examples 1 or 2, wherein each alternative machine learning model includes at least one of a network-specific algorithmic structure or one or more network-specific weights.

[0122] Example 4 is a method according to any one of Examples 1 to 3, wherein the UE indicates a version identifier of each alternative machine learning model supported by the UE.

[0123] Example 5 is a method according to any one of Examples 1 to 4, wherein the UE indicates a public land mobile network (PLMN) identifier (ID) associated with each alternative machine learning model supported by the UE.

[0124] Example 6 is a method according to any one of Examples 1 to 5, wherein the configuration from the wireless network instructs the UE to use the first version of the machine learning processing model supported by the UE or an alternative version of the machine learning processing model.

[0125] Example 7 is a method according to any one of Examples 1 to 6, wherein the wireless network indicates a version identifier of the machine learning processing model configured for the UE.

[0126] Example 8 is a method according to any one of Examples 1 to 7, wherein the wireless network indicates a public land mobile network (PLMN) identifier (ID) associated with the alternative machine learning model configured for the UE.

[0127] Example 9 is a method according to any one of Examples 1 to 8, wherein the configuration received by the UE from the wireless network indicates at least one of a network-specific algorithmic structure or one or more weights of an alternative machine learning model supported by the UE.

[0128] Example 10 is a method according to any one of Examples 1 to 9, wherein the machine learning processing model is used to process at least one of sensor data or wireless channel measurements.

[0129] Example 11 is a method according to any one of Examples 1 to 10, wherein the UE indicates to the wireless network the scenarios supported by the UE for at least one machine learning processing model.

[0130] Example 12 is a device comprising: one or more processors; and one or more memories storing instructions in electronic communication with the one or more processors, wherein the instructions are executable by the one or more processors to enable the device to implement a method as in any one of Examples 1-11.

[0131] Example 13 is a system or apparatus comprising: means for indicating to a wireless network an ability to support one or more versions of an ML processing model; and means for receiving a configuration from the wireless network to apply a version of the ML processing model supported by the UE.

[0132] Example 14 is a system or apparatus according to Example 13, used to implement a method as in any one of Examples 1-11 or to implement an apparatus as in any one of Examples 1-11.

[0133] Example 15 is a non-transitory computer-readable medium storing instructions, the instructions being executable by one or more processors to cause the one or more processors to implement a method as in any one of Examples 1-11.

[0134] Example 16 is a method of wireless communication at a wireless network entity, comprising: receiving an indication of an ability to support one or more versions of a machine learning processing model from a UE; and configuring the UE to apply a version of the machine learning processing model supported by the UE.

[0135] Example 17 is a method according to Example 16, wherein the indication indicates the capability to support one or more of a first version of the machine learning processing model and at least one alternative version of the machine learning processing model that is common across multiple wireless networks.

[0136] Example 18 is a method according to any of Examples 16 or 17, wherein each alternative machine learning model includes at least one of a network-specific algorithmic structure or one or more network-specific weights.

[0137] Example 19 is a method according to any one of Examples 16 to 18, wherein the indication indicates a version identifier of each alternative machine learning model supported by the UE.

[0138] Example 20 is a method according to any one of Examples 16 to 19, wherein the indication indicates a public land mobile network (PLMN) identifier (ID) associated with each alternative machine learning model supported by the UE.

[0139] Example 21 is a method according to any one of Examples 16 to 20, wherein the wireless network entity configures the UE to use the first version of the machine learning processing model supported by the UE or an alternative version of the machine learning processing model.

[0140] Example 22 is a method according to any one of Examples 16 to 21, wherein the wireless network entity indicates a version identifier of the machine learning processing model configured for the UE.

[0141] Example 23 is a method according to any one of Examples 16 to 22, wherein the wireless network entity indicates a public land mobile network (PLMN) identifier (ID) associated with the alternative machine learning model configured for the UE.

[0142] Example 24 is a method according to any one of Examples 16 to 22, wherein the wireless network entity configures at least one of a network-specific algorithmic structure or one or more weights of an alternative machine learning model supported by the UE.

[0143] Example 25 is a method according to any one of Examples 16 to 24, wherein the machine learning processing model is used to process at least one of sensor data or wireless channel measurements.

[0144] Example 26 is a method according to any one of Examples 16 to 25, wherein the indication indicates to the wireless network the scenarios supported by the UE for at least one machine learning processing model.

[0145] Example 27 is a device comprising: one or more processors; and one or more memories storing instructions in electronic communication with the one or more processors, the instructions being executable by the one or more processors to cause the device to implement a method as in any one of Examples 16-26.

[0146] Example 28 is a system or apparatus comprising: a unit for receiving an indication of an ability to support one or more versions of a machine learning (ML) processing model from a UE; and a unit for configuring the UE to apply a version of the ML processing model supported by the UE.

[0147] Example 29 is a system or apparatus according to Example 28, used to implement a method as in any one of Examples 16-26 or to implement an apparatus as in any one of Examples 16-26.

[0148] Example 30 is a non-transitory computer-readable medium storing instructions, the instructions being executable by one or more processors to cause the one or more processors to implement the method as in any of Examples 16-26.

Claims

1. A method of wireless communication at a user equipment (UE), comprising: Indicating to a wireless network an ability to support one or more versions of a machine learning (ML) processing model; as well as A configuration is received from the wireless network to apply a version of the ML processing model supported by the UE.

2. The method according to claim 1, wherein: The UE indicates the capability to support one or more of: a first version of the ML processing model that is common across multiple wireless networks, and at least one alternate version of the ML processing model.

3. The method according to claim 2, wherein: Each alternative machine learning model includes at least one of a network-specific algorithmic structure or one or more network-specific weights.

4. An apparatus for wireless communication at a user equipment (UE), comprising: means for indicating to a wireless network an ability to support one or more versions of a machine learning (ML) processing model; as well as Means for receiving a configuration from the wireless network to apply a version of the ML processing model supported by the UE.

5. An apparatus for wireless communication at a user equipment (UE), comprising: Memory; as well as at least one processor coupled to the memory and configured to: Indicating to a wireless network an ability to support one or more versions of a machine learning (ML) processing model; as well as A configuration is received from the wireless network to apply a version of the ML processing model supported by the UE.

6. A computer readable medium storing computer executable code at a user equipment (UE), the code, when executed by a processor, causes the processor to perform the following operations: Indicating to a wireless network an ability to support one or more versions of a machine learning (ML) processing model; and A configuration is received from the wireless network to apply a version of the ML processing model supported by the UE.

7. A method of wireless communication at a wireless network entity, comprising: receiving an indication of a capability of a user equipment (UE) to support one or more versions of a machine learning (ML) processing model; as well as The UE is configured to apply a version of the ML processing model supported by the UE.

8. An apparatus for wireless communication at a wireless network entity, comprising: means for receiving an indication of a capability of a user equipment (UE) to support one or more versions of a machine learning (ML) processing model; as well as means for configuring the UE to apply a version of the ML processing model supported by the UE.

9. An apparatus for wireless communication at a wireless network entity, comprising: Memory; as well as at least one processor coupled to the memory and configured to: receiving an indication of a capability of a user equipment (UE) to support one or more versions of a machine learning (ML) processing model; and The UE is configured to apply a version of the ML processing model supported by the UE.

10. A computer readable medium storing computer executable code at a wireless network entity, the code when executed by a processor causes the processor to perform the following operations: Receiving an indication of a capability of a user equipment (UE) to support one or more versions of a machine learning (ML) processing model; and configuring the UE to apply a version of the ML processing model supported by the UE.

Images