Data collection process and model training

Abstract

In a wireless communication system, a user equipment (UE) provider and a network entity provider may configure one or more UEs and network entities to perform data collection and training for a channel state information (CSI) feedback (CSF) model.

Description

Background Art Technical Field

[0001] The present disclosure relates generally to communication systems, and more particularly to training encoders and decoders associated with user equipment (UE) and network entities, respectively.

[0002] introduction

[0003] Wireless communication systems are widely deployed to provide a variety of 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.

[0004] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at city, country, region, and even global levels. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continuous mobile broadband evolution promulgated by the Third 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 communication (mMTC), and ultra-reliable low latency communication (URLLC). Certain aspects of 5G NR may be based on 4G Long Term Evolution (LTE) standards. It is necessary to further improve 5G NR technology. In addition, these improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0005] The following presents the summary of one or more aspects in order to provide a basic understanding of these aspects. This summary is not an extensive overview of all contemplated aspects, and is neither intended to identify the key or important elements of all aspects, nor to describe 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 presented later.

[0006] In one aspect of the present disclosure, a method, non-transitory computer-readable medium, and apparatus for a user equipment (UE) supplier are provided. The method includes: training one or more encoder-decoder pairs based on an original data set of a UE supplier; generating one or more training sets based on outputs of one or more encoders running the original data set of the UE supplier; and communicating the one or more training sets to a network entity supplier.

[0007] The present disclosure also provides a device (e.g., a UE provider / server) comprising a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device comprising a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0008] In another aspect, the present disclosure provides a method, non-transitory computer-readable medium, and apparatus for a UE supplier. The method includes: training one or more encoder-decoder pairs based on an original data set of a UE supplier; generating two training sets for each encoder-decoder pair in the one or more encoder-decoder pairs based on outputs of one or more encoders running the original data set of the UE supplier; and communicating the two training sets to a network entity supplier.

[0009] The present disclosure also provides a device (e.g., a UE provider / server) comprising a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device comprising a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0010] In another aspect, the present disclosure provides a method, non-transitory computer-readable medium, and apparatus for a network entity provider. The method includes: receiving one or more training sets from a UE provider, the one or more training sets corresponding to one or more encoder-decoder pairs; and training one or more decoders associated with the one or more training sets.

[0011] The present disclosure also provides a device (e.g., a network entity provider / server) comprising a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device comprising a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0012] In another aspect, the present disclosure provides a method, non-transitory computer-readable medium, and apparatus for a network entity provider. The method includes: receiving two training sets from a UE provider, the two training sets corresponding to one or more encoder-decoder pairs; and training one or more decoders associated with the two training sets.

[0013] The present disclosure also provides a device (e.g., a network entity provider / server) comprising a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device comprising a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0014] In another aspect, the present disclosure provides a method, a non-transitory computer-readable medium, and a device for a UE. The method includes: sending a training data request to a network entity; receiving a data collection configuration message from the network entity in response to sending the training data request; sending a data collection configuration confirmation (ACK) to the network entity in response to receiving the data collection configuration message; and performing a data collection process based on the data collection configuration message.

[0015] The present disclosure also provides a device (e.g., UE) including a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device including a component for executing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for executing the above method.

[0016] In another aspect, the present disclosure provides a method, a non-transitory computer-readable medium, and a device for a network entity. The method includes: receiving a training data request from a UE; sending a data collection configuration message to the UE in response to receiving the training data request; receiving a data collection configuration ACK from the UE in response to sending the data collection configuration message; and performing a data collection process based on the data collection configuration message.

[0017] The present disclosure also provides a device (e.g., a network entity) comprising a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device comprising a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0018] In another aspect, the present disclosure provides a method, a non-transitory computer-readable medium, and a device for a UE. The method includes: receiving a data collection configuration message from a network entity based on a training data request; sending a data collection configuration ACK to the network entity in response to receiving the data collection configuration message; performing a data collection process based on the data collection configuration message; and reporting training data between at least one of the network entity, the UE vendor, and the network entity vendor based on performing the data collection process.

[0019] The present disclosure also provides a device (e.g., UE) including a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device including a component for executing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for executing the above method.

[0020] In another aspect, the present disclosure provides a method, a non-transitory computer-readable medium, and a device for a network entity. The method includes: receiving a training data request from a network entity supplier; sending a data collection configuration message to a UE in response to receiving the training data request; receiving a data collection configuration ACK from the UE in response to sending the data collection configuration message; performing a data collection process based on the data collection configuration message; and receiving or reporting training data between the UE, the UE supplier, and the network entity supplier based on performing the data collection process.

[0021] The present disclosure also provides a device (e.g., a network entity) comprising a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device comprising a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0022] In another aspect, the present disclosure provides a method, non-transitory computer-readable medium, and apparatus for a UE vendor. The method includes: communicating a training data request to initiate model training for a UE vendor and a network entity vendor; receiving a training data report in response to communicating the training data request; performing model training for a channel state information (CSI) feedback (CSF) model; and communicating the model training report to the network entity vendor.

[0023] The present disclosure also provides a device (e.g., a UE provider, a server) including a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device including a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0024] In another aspect, the present disclosure provides a method, non-transitory computer-readable medium, and apparatus for a network entity provider. The method includes: communicating a training data request to initiate model training for a UE provider and a network entity provider; receiving a training data report in response to communicating the training data request; performing model training for a CSF model; and communicating the model training report to the UE provider.

[0025] The present disclosure also provides a device (e.g., a network entity provider / server) comprising a memory storing computer-executable instructions and at least one processor configured to execute these computer-executable instructions to perform the above method, a device comprising a component for performing the above method, and a non-transitory computer-readable medium storing computer-executable instructions for performing the above method.

[0026] To achieve the foregoing and related ends, one or more aspects include the features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail some illustrative features of one or more aspects. However, these features are merely indicative of some of the various ways in which the principles of the various aspects may be employed, and this specification is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a diagram illustrating an example of a wireless communication system including an access network in accordance with certain aspects of the present specification.

[0028] Figure 2A is a diagram illustrating an example of a first frame according to certain aspects of the present specification.

[0029] Figure 2B is a diagram illustrating an example of downlink (DL) channels within a subframe in accordance with certain aspects of the present disclosure.

[0030] Figure 2C is a diagram illustrating an example of a second frame according to certain aspects of the present specification.

[0031] Figure 2D is a diagram illustrating an example of uplink (UL) channels within a subframe in accordance with certain aspects of the present disclosure.

[0032] Figure 3 is a diagram illustrating an example of a base station and a user equipment (UE) in an access network in accordance with certain aspects of the present disclosure.

[0033] Figure 4 A diagram illustrating an example decomposed base station architecture is shown.

[0034] Figure 5 is a diagram illustrating an example of a communication system including a UE vendor and a gNB vendor.

[0035] Figure 6 is a diagram illustrating a conceptual diagram of channel state information (CSI) feedback (CSF) compression between a UE and a network entity in a wireless communication system.

[0036] Figure 7 A conceptual diagram illustrating the inner loop in UE vendor training for one encoder-decoder pair.

[0037] Figure 8 is a message diagram illustrating example messages for the data collection process for CSF compression.

[0038] Fig. 9 is a conceptual diagram illustrating an example frame structure for uploading data.

[0039] Fig.10 is a message diagram illustrating example messages for the data collection process for CSF compression.

[0040] Fig.11 is a message diagram illustrating example messages for reporting training data in steps during the data collection process for CSF compression.

[0041] Fig.12 is a message diagram illustrating example messages for the data collection process for CSF compression.

[0042] Fig.13 An example message for requesting to upload existing data to a repository is illustrated.

[0043] Fig.14 Another example message for requesting to upload existing data to a repository is illustrated.

[0044] Fig.15 Another example message for requesting to upload existing data to a repository is illustrated.

[0045] Fig.16 is a message diagram illustrating example messages for performing a data collection process and offline model training for CSF compression using area-based training at a UE.

[0046] Fig.17 is a message diagram illustrating example messages for conducting a data collection process and offline model training for CSF compression using UE-based configuration at a UE.

[0047] Fig.18 is a conceptual diagram illustrating an example frame structure for uploading data.

[0048] Fig.19 is a message diagram illustrating example messages for performing a data collection process and offline model training for CSF compression using area-based training at a UE.

[0049] Fig. 20 is a message diagram illustrating example messages for performing a data collection process and offline model training for CSF compression using UE-based training at a UE.

[0050] Fig.21 is a message diagram 2100 illustrating example messages for reporting training data in steps during the data collection process for CSF compression.

[0051] Fig. 22 is a conceptual data flow diagram illustrating the flow of data between different means / components in an example base station.

[0052] Fig.23 is a conceptual data flow diagram illustrating the data flow between different means / components in an example UE.

[0053] Fig.24 is a flow chart of an example method for a UE vendor for cross-node machine learning training.

[0054] Fig.25 is a flow chart of an example method for a UE vendor for cross-node machine learning training.

[0055] Fig.26 is a flow chart of an example method for a network entity provider for cross-node machine learning training.

[0056] Fig. 27 is a flow chart of an example method for a network entity provider for cross-node machine learning training.

[0057] Fig.28 is a flow chart of an example method for a UE to perform a CSF data collection procedure.

[0058] Fig.29 is a flow chart of an example method by which a network entity performs a CSF data collection process.

[0059] Fig.30 is a flow chart of an example method for a UE to perform a CSF data collection procedure.

[0060] Fig.31 is a flow chart of an example method by which a network entity performs a CSF data collection process.

[0061] Fig.32 is a flow chart of an example method that a UE vendor performs for data collection and offline model training for CSF compression.

[0062] Fig.33 is a flow chart of an example method that a network entity provider performs for data collection and offline model training for CSF compression.

[0063] The Appendix is ​​included herein as part of this application and provides additional details related to various aspects of the present disclosure. DETAILED DESCRIPTION

[0064] The specific embodiments described below in conjunction with the accompanying drawings are intended as descriptions of various configurations and are not intended to represent the only configurations with which the concepts described herein can be practiced. In order to provide a thorough understanding of the various concepts, the specific embodiments include specific details. However, it is obvious 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. 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.

[0065] In one aspect, the present disclosure provides techniques for training an encoder and a decoder associated with a user equipment (UE) and a network entity, respectively.

[0066] Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods will be described in the following detailed description 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 these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0067] As an example, an element, or any part of an element, or any combination of elements can be implemented as a "processing system", which includes one or more processors. The example of a processor includes a microprocessor, a microcontroller, a graphics processing unit (GPU), a central processing unit (CPU), an application processor, a digital signal processor (DSP), a reduced instruction set computing (RISC) processor, a system on a chip (SoC), a baseband processor, a field programmable gate array (FPGA), a programmable logic device (PLD), a state machine, a gate logic piece, a discrete hardware circuit 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 it is referred to as software, firmware, middleware, microcode, hardware description language or other names, software should be widely 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.

[0068] Therefore, in one or more example embodiments, the described functions can be implemented with hardware, software or any combination thereof. If implemented with 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 medium 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 device, magnetic disk storage device, other magnetic storage devices, a combination of computer-readable media of the above type, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer.

[0069] Figure 1 1 is a diagram illustrating an example of a wireless communication system and an access network 100. The wireless communication system (also referred to as a wireless wide area network (WWAN)) includes a network entity 102 (also referred to as a base station 102 and / or may include one or more decomposed base station entities), a UE 104, an evolved packet core (EPC) 160, and another core network (e.g., a 5G core (5GC) 190). 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.

[0070] One or more of the UEs 104 may include a Figure 5UE training component 140 for communicating with at least UE provider 502 of the network to perform data collection and model training. In one aspect, one or more of base stations 102 may include a UE training component 140 for communicating with at least a network entity provider (such as Figure 5 The network training component 120 communicates with the gNB provider 504 to perform data collection and model training with the UE 104. As used herein, the term "provider" includes devices, servers, repositories, and / or any other devices capable of collecting and storing data associated with training of models and transmitting / sending data associated with training of models for encoders and / or decoders.

[0071] A 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 be connected to the EPC 160 via a backhaul link 132 (e.g., an S1 interface). The backhaul link 132 can be wired or wireless. A base station 102 configured for 5G NR (collectively referred to as the Next Generation RAN (NG-RAN)) can be connected to the 5GC 190 via a backhaul link 184. The backhaul link 184 can be wired or wireless. Among other functions, the base station 102 can 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 equipment tracking, RAN information management (RIM), paging, positioning, and delivery of warning messages. The base stations 102 may communicate with each other directly or indirectly (e.g., through the EPC 160 or the 5GC 190) over a backhaul link 134 (e.g., an X2 interface). The backhaul link 134 may be wired or wireless.

[0072] Base station 102 can communicate wirelessly with UE 104. Each of base stations 102 can provide communication coverage for a corresponding geographic coverage area 110. There may be overlapping geographic coverage areas 110. For example, a small cell 102' may 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 may be referred to as a heterogeneous network. A heterogeneous network may also include a home evolved Node B (eNB) (HeNB), which may provide services to a restricted group referred to as a closed subscriber group (CSG). A communication link 112 between base station 102 and UE 104 may include an uplink (UL) (also referred to as a reverse link) transmission from UE 104 to base station 102 and / or a downlink (DL) (also referred to as a forward link) transmission from base station 102 to UE 104. The communication link 112 may use multiple input multiple output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmit diversity. The communication link may be through one or more carriers. For each carrier allocated in the carrier aggregation for a total of up to Yx MHz (x component carriers) for transmission in each direction, the base station 102 / UE 104 can use spectrum with a bandwidth of up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz, 400 MHz, etc.). 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 ​​compared to 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).

[0073] 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), a physical sidelink control channel (PSCCH), and a physical sidelink feedback channel (PSFCH). The D2D communication may be through various wireless D2D communication systems, such as FlashLinQ, WiMedia, Bluetooth, ZigBee, Wi-Fi based on IEEE 802.11 standards, LTE, or NR.

[0074] 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 the 5 GHz unlicensed spectrum. When communicating in the unlicensed spectrum, the STA 152 / AP 150 may perform a clear channel assessment (CCA) to determine whether the channel is available prior to communication.

[0075] The small cell 102' may operate in licensed and / or unlicensed spectrum. When operating in the unlicensed spectrum, the small cell 102' may employ NR and use the same 5 GHz unlicensed spectrum used by the Wi-Fi AP 150. The small cell 102' employing NR in the unlicensed spectrum may improve the coverage of the access network and / or increase the capacity of the access network.

[0076] Base station 102 (whether a small cell 102' or a large cell (e.g., a macro base station)) may include an eNB, a gNodeB (gNB), or other types of base stations. Some base stations (such as gNB 180) may operate in one or more frequency bands within the electromagnetic spectrum.

[0077] The electromagnetic spectrum is often subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410MHz–7.125GHz) and FR2 (24.25GHz–52.6GHz). Frequencies between FR1 and FR2 are often referred to as mid-band frequencies. Although a portion of FR1 is greater than 6GHz, FR1 is often (interchangeably) referred to as the “sub-6GHz” band in various documents and articles. A similar naming issue sometimes occurs with FR2, which is often (interchangeably) referred to as the “millimeter wave” band in various documents and articles, although it is different from the extremely high frequency (EHF) band (30GHz to 300GHz) identified as the “millimeter wave” (mmW) band by the International Telecommunication Union (ITU).

[0078] In view of the above aspects, unless otherwise specifically stated, it should be understood that if used in this article, the term "below 6 GHz" or the like 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 in this article, it can broadly represent frequencies that can include mid-band frequencies, can be within FR2, or can be within the EHF band. Communications using mmW radio frequency bands have extremely high path loss and short range. The mmW base station 180 can utilize beamforming 182 with the UE 104 to compensate for this path loss and short range.

[0079] Base station 180 may transmit beamformed signals in one or more transmit directions 182' to UE 104. UE 104 may receive beamformed signals from base station 180 in one or more receive directions 182". UE 104 may also transmit beamformed signals to base station 180 in one or more transmit directions. Base station 180 may receive beamformed signals from UE 104 in one or more receive directions. Base station 180 / UE 104 may perform beam training to determine the best receive direction and transmit direction for each of base stations 180 / UE 104. The transmit direction and receive direction of base station 180 may be the same or different. The transmit direction and receive direction of UE 104 may be the same or different.

[0080] 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. Typically, 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 UE IP address allocation and other functions. 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 configuration and delivery. The BM-SC 170 may serve as an entry point for content provider MBMS delivery, may be used to authorize and initiate MBMS bearer services in a public land mobile network (PLMN), and may be used to schedule MBMS delivery. 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 that broadcasts a specific service, and may be responsible for session management (start / stop) and for collecting eMBMS-related billing information.

[0081] 5GC 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. AMF 192 may communicate with unified data management (UDM) 196. AMF 192 is a control node that handles signaling between UE 104 and 5GC 190. In general, 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 is connected to IP service 197. IP service 197 may include the Internet, intranet, IP multimedia subsystem (IMS), PS streaming service and / or other IP services.

[0082] A base station may also be referred to as a gNB, a Node B, an evolved Node B (eNB), an access point, a base transceiver, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmit receive point (TRP), or some other suitable term. Base station 102 provides an access point to EPC 160 or 5GC 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, 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, 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, a toaster, a vehicle, a heart monitor, etc.). UE 104 may also be referred to as a station, a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other suitable terminology.

[0083] FIG. 2A to FIG. 2D is a resource diagram illustrating an example frame structure and channels that may be used for uplink transmissions, downlink transmissions, and sidelink transmissions to a UE 104 that includes a CB mapping component 140. Figure 2A FIG200 is a diagram illustrating an example of a first subframe within a 5G NR frame structure. Figure 2B FIG230 is a diagram illustrating an example of DL channels within a 5G NR subframe. Figure 2C 250 is a diagram illustrating an example of a second subframe within a 5G NR frame structure. Figure 2D FIG280 is a diagram illustrating an example of UL channels within a 5G NR subframe. The 5G NR frame structure may be FDD, where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to either DL or UL, or may be TDD, where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to both DL and UL. Figure 2A , Figure 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 X can be used flexibly between DL / UL, and subframe 3 is configured with slot format 34 (most of which are UL). Although subframes 3 and 4 are shown as having slot formats 34 and 28, respectively, any particular subframe may be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are both DL and both UL, respectively. Other slot formats 2-61 include a mix of DL, UL, and flexible symbols. The slot format is configured for the UE via a received slot format indicator (SFI) (dynamically configured via DL control information (DCI) or semi-statically / statically configured via radio resource control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0084] Other wireless communication technologies may have different frame structures and / or different channels. A frame (10ms) may be divided into 10 subframes of equal size (1ms). 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 symbols on the DL may be cyclic prefix (CP) OFDM (CP-OFDM) symbols. The symbols on the UL may be CP-OFDM symbols (for high throughput scenarios) or discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbols (also known as single carrier frequency division multiple access (SC-FDMA) symbols) (for power-limited scenarios; limited to single stream transmission). The number of time slots in a subframe is based on the time slot configuration and parameter set (numerology). For slot configuration 0, different parameter sets μ0 to 5 allow 1, 2, 4, 8, 16, and 32 slots per subframe, respectively. For slot configuration 1, different parameter sets 0 to 2 allow 2, 4, and 8 slots per subframe, respectively. Accordingly, for slot configuration 0 and parameter set μ, there are 14 symbols per slot and 2 per subframe. μtime slots. The subcarrier spacing and symbol length / duration are functions of the parameter set. The subcarrier spacing can be equal to 2 μ *15kHz, where μ is parameter set 0 to 5. Therefore, the subcarrier spacing for parameter set μ=0 is 15kHz, and the subcarrier spacing for parameter set μ=5 is 480kHz. The symbol length / duration is inversely related to the subcarrier spacing. FIG. 2A to FIG. 2D An example is provided for slot configuration 0 with 14 symbols per slot and parameter set μ=0 with 1 slot per subframe. The subcarrier spacing is 15 kHz and the symbol duration is approximately 66.7 μs.

[0085] A resource grid may be used to represent a frame structure. Each slot includes a resource block (RB) (also referred to as a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a plurality of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0086] like Figure 2A As illustrated, some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) (denoted as Rx for a particular configuration, where 100x is the port number, but other DM-RS configurations are also possible) and a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0087] Figure 2B Examples of various DL channels within a subframe of a frame are illustrated. The physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs), each CCE including nine RE groups (REGs), each REG including four consecutive REs in an OFDM symbol. The primary synchronization signal (PSS) may be within symbol 2 of a specific subframe of the frame. The PSS is used by UE 104 to determine the subframe / symbol timing and the physical layer identification. The secondary synchronization signal (SSS) may be within symbol 4 of a specific subframe of the frame. The SSS is used by the UE to determine the physical layer cell identification group number and the radio frame timing. Based on the physical layer identification and the physical layer cell identification group number, the UE can determine the physical cell identifier (PCI). Based on the PCI, the UE can determine the location of the aforementioned 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. The MIB provides the system frame number (SFN) and the number of RBs in the system bandwidth. The Physical Downlink Shared Channel (PDSCH) carries user data, broadcast system information such as System Information Blocks (SIBs) not sent through the PBCH, and paging messages.

[0088] like Figure 2C As illustrated, some of the REs carry DM-RS (indicated as R for a particular configuration, but other DM-RS configurations are possible) for channel estimation at the base station. 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 or first 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. Although not shown, the UE may send a sounding reference signal (SRS). The SRS may be used by the base station for channel quality estimation to enable frequency-dependent scheduling of the UL.

[0089] Figure 2D Examples of various UL channels within a subframe of a frame are illustrated. The PUCCH may be located at a position 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 HARQ 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.

[0090] Figure 3375. The UE / UE provider 350 is a block diagram of a base station / network entity provider 310 in communication with a UE / UE provider 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 handover support functions; RLC layer functions associated with delivery 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.

[0091] The transmit (Tx) processor 316 and the receive (Rx) processor 370 implement layer 1 functions associated with various signal processing functions. Layer 1 (which includes the physical (PHY) layer) may include error detection on the transmission channel, forward error correction (FEC) decoding / 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 handles 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-quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols can then be split into parallel streams. Subsequently, each stream can be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., a 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 pre-coded to produce multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine the coding and modulation schemes, as well as for spatial processing. Channel estimates may be derived from reference signals and / or channel state 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.

[0092] 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 converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). 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 channel estimates 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.

[0093] 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 between transport channels and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets from the EPC 160 or 5GC 190. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0094] Similar to the functions described in conjunction with DL transmission 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.

[0095] Channel estimates derived by the channel estimator 358 from a reference signal or feedback sent by the base station 310 may be used by the Tx processor 368 to select 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.

[0096] 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 corresponding antenna 320. Each receiver 318Rx recovers information modulated onto an RF carrier and provides the information to an Rx processor 370.

[0097] 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.

[0098] At least one of the Tx processor 368, the Rx processor 356, and the controller / processor 359 may be configured to perform Figure 1 Various aspects related to the UE training component 140.

[0099] At least one of the Tx processor 316, the Rx processor 370, and the controller / processor 375 may be configured to perform Figure 1 Various aspects related to the network training component 120.

[0100] Figure 4 A diagram illustrating an example disaggregated base station 400 architecture that may be one form of a network entity 102 or base station 102 as discussed herein is shown. The disaggregated base station 400 architecture may include one or more central units (CUs) 410 that may communicate directly with a core network 420 via a backhaul link, or indirectly with the core network 420 through one or more disaggregated base station units, such as a near real-time (near-RT) RAN intelligent controller (RIC) 425 via an E2 link, or a non-real-time (non-RT) RIC 415 associated with a service management and orchestration (SMO) framework 405, or both. The CU 410 may communicate with one or more distributed units (DUs) 430 via respective midhaul links, such as an F1 interface. The DU 430 may communicate with one or more radio units (RUs) 440 via respective fronthaul links. The RU 440 may communicate with respective UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 can be served by multiple RUs 440 simultaneously.

[0101] Each of the units (i.e., CU 410, DU 430, RU 440, and near-RT RIC 425, non-RT RIC 415, and SMO framework 405) may include or be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of these units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface configured to receive or send signals to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) configured to receive or send signals, or both, to one or more of the other units on a wireless transmission medium.

[0102] In some aspects, CU 410 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface configured to communicate signals with other control functions hosted by CU 410. CU 410 may be configured to handle user plane functions (i.e., central unit-user plane (CU-UP)), control plane functions (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, CU 410 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, CU 410 may be implemented to communicate with DU 430 for network control and signaling.

[0103] DU 430 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 440. In some aspects, DU 430 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) at least in part according to a functional split such as those defined by the 3rd Generation Partnership Project (3GPP). In some aspects, DU 430 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 430 or with control functions hosted by CU 410.

[0104] The lower layer functions may be implemented by one or more RUs 440. In some deployments, the RU 440 controlled by the DU 430 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on functional splitting (such as lower layer functional splitting). In such an architecture, the RU 440 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some specific implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 440 may be controlled by the corresponding DU 430. In some scenarios, this configuration may enable the implementation of the DU 430 and the CU 410 in a cloud-based RAN architecture (such as a vRAN architecture).

[0105] The SMO framework 405 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 405 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 405 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 490) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 410, DU 430, RU 440, and near-RT RIC 425. In some specific implementations, the SMO framework 405 may communicate with hardware aspects of the 4G RAN such as an open eNB (O-eNB) 411 via the O1 interface. Additionally, in some specific implementations, the SMO framework 405 may communicate directly with one or more RUs 440 via the O1 interface. The SMO framework 405 may also include a non-RT RIC 415 configured to support the functionality of the SMO framework 405 .

[0106] The non-RT RIC 415 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 425. The non-RT RIC 415 may be coupled to or in communication with the near-RT RIC 425 (such as via an A1 interface). The near-RT RIC 425 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 410, one or more DUs 430, or both, and the O-eNB with the near-RT RIC 425.

[0107] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 425, the non-RT RIC 415 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 425 and may be received from a non-network data source or from a network function at the SMO framework 405 or the non-RT RIC 415. In some examples, the non-RT RIC 415 or the near-RT RIC 425 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 415 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 405 (such as via reconfiguration of O1) or via creation of RAN management policies (such as A1 policies).

[0108] Figure 5 is a diagram illustrating an example of a communication system including a UE provider and a gNB provider. For example, a UE provider 502 may serve multiple UEs, such as Figure 1 UE 104, and corresponding to Figure 3 UE provider 502 may be configured to collect data from multiple UEs 104 in direct communication. Multiple UEs 104 may be linked to UE provider 502 wirelessly or via wired connections. UE provider 502 may be linked 506 directly and / or indirectly to gNB provider 504. gNB provider 504 may be linked directly and / or indirectly to multiple gNBs, such as Figure 1 The base station 102 may correspond to Figure 3 The network entity provider 310. The UE provider 502 and the gNB provider 504 can perform data collection and online / offline training for channel state information (CSI) feedback (CSF) compression for communication between the UE 104 and the gNB 102.

[0109] In one aspect, the UE vendor 502 may initiate UE-based training for multiple UEs 104 associated with it. For example, the UE vendor 502 may request the UE 104 to collect data for model training. In some cases, the request may be made via a UE application running on the UE 104. In response to receiving the request, the UE 104 may transmit the request to a gNB (such as a UE 104) via the communication link 112. Figure 1 The model manager of the gNB 102 may correspond to the gNB vendor 504.

[0110] In one aspect, the UE vendor 502 may initiate model training and coordinate with the gNB vendor 504. In another aspect, the UE vendor 502 may perform area-based training by transmitting a request to initiate model training directly to the gNB vendor 504. The gNB vendor 502 may request the gNB 102 to configure model training and select an appropriate UE 104 for training data collection based on UE type, UE capabilities, and user consent.

[0111] Figure 6 A conceptual diagram 600 illustrates CSF compression between a UE and a network entity in a wireless communication system. For example, a UE 104 may correspond to Figure 1 UE 104, and gNB 102 may correspond to Figure 1 Base station 102.

[0112] For example, in cross-node machine learning (ML), a neural network (NN) is split into two parts: an encoder 602 located on a UE (such as UE 104) and a decoder 604 located on a gNB (such as base station 102). The encoder output from UE 104 is sent to gNB 102 as input to decoder 604. In one example, encoder 602 at UE 104 outputs a compressed CSF 606, which is input to decoder 604 at gNB 102. Decoder 604 at gNB 102 outputs a reconstructed CSF 608, such as a pre-decoded vector. To train encoder 602 and decoder 604, UE vendors (such as Figure 5 UE vendor 502) can use its own dataset to train two models and share the trained decoder model with a gNB vendor (such as gNB vendor 504).

[0113] In one aspect, due to the symmetry that typically exists between encoders and decoders, the decoder shared with the underlying vendor may reveal or imply specific implementation details of the UE modem. For example, if the encoder employs convolutional layers, the decoder correspondingly employs transposed convolutional layers. To overcome this problem, the UE vendor 502 may share a training set including expected (input, output) tuples for its trained decoder with the gNB vendor 504. Then, from the perspective of the gNB vendor 504, the learning of the decoder 604 becomes supervised learning using the training set created by the UE vendor 502. Supervised learning may correspond to knowledge distillation, where the decoder model trained by the UE vendor 502 becomes the teacher and the decoder model adopted by the gNB vendor 504 becomes the student. Accordingly, the decoder model trained by the UE vendor 502 is not revealed to the gNB vendor 504. Therefore, the architecture of the decoder model adopted by the gNB vendor 504 is different from the architecture of the decoder model trained by the UE vendor 502.

[0114] In one aspect, the output of decoder 604 may correspond to a downlink channel matrix (H), a transmit covariance matrix, a downlink pre-decoder (V), an interference covariance matrix (R nn and at least one of the originally whitened downlink channels.

[0115] Figure 7 A conceptual diagram 700 illustrating an inner loop in UE vendor training for one encoder-decoder pair.

[0116] In one aspect, an access network (such as Figure 1The access network 100) may include one or more heterogeneous UEs (different baseband and RF implementations, different antennas, different OEMs) (such as UE 104) and heterogeneous channel statistics across cells. In this regard, a single encoder-decoder may not be able to achieve a performance level above a certain acceptability threshold in all scenarios. In these cases, the UE 104 participating in data collection tags the collected data with metadata describing the scenario for data collection, which is derived from both the gNB 102 and the UE 104. For example, the metadata from the gNB 102 may include gNB antenna configuration, CSI-RS beam configuration, etc. Additionally, the gNB 102 metadata may be provided to the UE 104 in the form of a "gNB meta ID" without disclosing any gNB implementation details. The metadata from the UE 104 may include UE antenna configuration, SNR, RSRP, delay spread, average delay, timestamp, etc. The UE 104 may break down the UE metadata into a "UE meta ID" that the UE vendor does not wish to disclose to the gNB vendor 504 and the remainder of the UE metadata.

[0117] In one aspect, at the UE server / UE vendor 502, N data sets are collected from multiple UEs 104 participating in data collection. For example, the UE server / UE vendor 502 may combine the N data sets into L (< N) data sets based on the associated metadata. Based on the UE type and channel statistics, the L data sets are further grouped into M (M << L) subsets. The UE vendor 502 may train M encoder-decoder pairs and obtain M training sets to be shared with the gNB vendor 504 from the M trained encoder-decoder pairs by performing an inner loop process M times, as further described herein. In some cases, each of the M trained encoder-decoders is associated with one or more metadata. The association between the M encoder-decoder pairs and the metadata enables the gNB 102 to switch between models during inference.

[0118] In one aspect, H raw represents the channel observed from the CSIRS channel; H corresponds to the processed form of H raw , such as a whitened channel. For example, H = f(H raw ,R nn ), where R nn corresponds to the observed noise covariance matrix. In this implementation, the UE 104 may wish to be hidden from the lower layer. Additionally, V may correspond to the ground truth of what the decoder aims to reconstruct, such as a pre-coded vector. q φ corresponds to the encoder, such as Figure 6 the encoder 602 of φ(H) Calculated. θ Corresponding to the decoder, such as Figure 6 The decoder 604, wherein Corresponding to the reconstruction of V by decoder 604.

[0119] In one aspect, the process for offline training of UE vendor driven cross-node ML may include the following steps. In the first step, the UE vendor 502 trains an encoder-decoder pair (q φ ,p θ ). In a second step, once the encoder-decoder pair is trained, the UE vendor 502 generates a training set {(encoder ID, z, V)} by operating the encoder 602 using the original data set of the UE vendor 502. For example, z corresponds to the encoder 602 output, such as a latent vector, and V corresponds to the desired decoder 604 output, such as a pre-decoded vector. In a third step, the UE vendor 502 provides the training set {(encoder ID, z, V)} to the gNB vendor 604.

[0120] In one aspect, another process for offline training of UE vendor driven cross-node ML may include the following steps. In a first step, on a server of UE vendor 502, UE vendor 502 trains an encoder-decoder pair (q φ ,p θ ). In the second step, after the encoder-decoder pair is trained, the UE vendor 502 generates two training sets: the first training set {(encoder ID, z, )}; and generate a second training set {(encoder ID, z+∈, p θ (z+∈))}, where z corresponds to the output of encoder 602, V corresponds to the desired output of decoder 604, and This corresponds to the reconstruction of V by the decoder 604. In the third step, the UE vendor 502 provides the two training sets to the gNB vendor 504.

[0121] In one aspect, another process for offline training of UE vendor driven cross-node ML may include the following steps. In a first step, on a server of UE vendor 502, UE vendor 502 trains an encoder-decoder pair (q φ ,p θ). In the second step, after the encoder-decoder pair is trained, the UE vendor 502 generates two training sets: the first training set {(encoder ID, z)} is generated by running the encoder 602 using the UE vendor 502 original data set; and the second training set {(encoder ID, z+∈)} is generated by perturbing the encoder 602 output z in the first training set with a small vector ∈, where z corresponds to the encoder 602 output. In the third step, the UE vendor 502 finds the decoder p that is approximately found θ An alternative decoder f is generated based on the following formula in response to the two training sets with p θ Same or similar output:

[0122] p θ (z+∈)=f(z+∈) and p θ (z) = f(z)

[0123] For example, the UE vendor 502 may determine an alternative decoder 504 for each encoder ID. In a fourth step, the UE vendor 502 provides the gNB vendor 504 with two training sets and the alternative decoder (encoder ID, f).

[0124] In one aspect, the gNB vendor 504 may train one or more decoders 604 based on the M group training set. For example, the gNB vendor 504 may perform at least one of the following training: training one decoder for all M groups, training one decoder for each group (i.e., M decoders), or training one decoder for every few groups (i.e., less than M decoders). The decoder 604 may be gNB 102 specific or shared among multiple gNBs 102. In addition, the gNB vendor 504 may determine association with a specific gNB 102 or sharing among multiple gNBs 102 based on at least one of the following: training set {(encoder ID, z, V)}; two training sets ({(encoder ID, z, V)}); )},{(encoder ID,z+∈,p θ (z+∈))}); as well as two training sets ({(encoder ID,z)}, {(encoder ID,z+∈})) and an alternative decoder {(encoder ID,f)}.

[0125] Figure 8 is a message diagram 800 illustrating example messages for a data collection process for CSF compression. For example, diagram 800 illustrates a UE vendor (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104) and gNB (such as Figure 1 Message sending and receiving between base stations 102).

[0126] In one aspect, at step 802, UE 502 may send a training data request to UE 104. In response to receiving the training data request, at step 804, UE 104 may forward the training data request to gNB 102. At step 806, in response to receiving the training data request, gNB 102 may send a data collection configuration to UE 104. For example, information about the data collection configuration message may include at least one of a reference signal (RS) for data collection such as a CSI-RS list, a region for data collection, a time period for data collection, a network side configuration, a channel type, and a process ID for data collection. In some cases, the configured RS may be dynamically activated / deactivated by gNB 102, such as via a medium access control (MAC) control element (CE) or downlink control information (DCI). In some cases, the process ID may be a model ID that has been registered with the MLF, or the process ID may be used to generate a meta ID used in data upload. In some cases, the process ID is a meta ID provided by a network entity for data collection. The meta ID may correspond to a CSI-RS beam configuration or antenna configuration including antenna layout, antenna element to TxRU mapping, digital / analog beamforming. In some cases, the signaling of the data collection configuration may correspond to reused MDT configuration signaling or as an information element (IE) in the RRCReconfiguration message.

[0127] At step 808, UE 104 may send a data collection configuration acknowledgment (ACK) to gNB 102 to indicate successful receipt of the data collection configuration. Subsequently, at step 810, UE 104 may perform data collection with gNB 102. After completing the data collection, at step 812, UE 104 may upload the collected data to UE provider 502.

[0128] Fig. 9 900 is a conceptual diagram illustrating an example frame structure for uploading data. For example, in response to performing data collection between UE 104 and gNB 102, UE 104 may send a report of the data as illustrated in multiple instances 902, 904, 906, and 908 to UE provider 502.

[0129] In one aspect, the UE report may include {H_raw, meta_id}, where H_raw is the channel estimate based on RB index, port index and Rx index; and Meta_id has the following hierarchical structure and includes: packet ID (which can be generated using data process ID), cell / carrier ID, CSI-RS resource ID (which implicitly conveys antenna mapping / layout), record list {record #1, record #2, etc.} and GNSS (if possible). For example, each record includes a timestamp, such as a CSI-RS transmission instance or timeslot index, or a measurement duration index (e.g., the record is based on a measurement of a certain duration, where the duration should be configured): gNB 102 can dynamically change the antenna mapping / layout, where the timestamp is required to mark the reported data with the correct antenna mapping / layout. Additionally, each record includes SNR, SINR or RSRP; subcarrier spacing and Doppler / delay spread measurements.

[0130] In one aspect, the format of H_raw and other additional data may include a frequency domain resolution corresponding to subcarriers, RBs, or subbands; and / or the eigendirections of H_raw are also reported as {H_raw, V_raw, meta_id}, where the V_raw frequency granularity is less than or equal to the H_raw frequency granularity.

[0131] Fig.10 is a message diagram 1000 illustrating example messages for a data collection process for CSF compression. For example, diagram 1000 illustrates a UE vendor (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 base station 102) and a data repository / collection entity (such as Figure 5 Message sending and receiving between gNB supplier 504).

[0132] In one aspect, at step 1002, the model / data repository 502 may send a training data request to the gNB 102. At step 1004, the gNB 1002 may send a data collection configuration to the UE 104. For example, information about the data collection configuration message may include at least one of a reference signal (RS) for data collection such as a CSI-RS list, a region for data collection, a time period for data collection, a network side configuration, a channel type, and a process ID for data collection. In some cases, the configured RS may be dynamically activated / deactivated by the gNB 102, such as via a medium access control (MAC) control element (CE) or downlink control information (DCI). In some cases, the process ID may be a model ID that has been registered with the MLF, or the process ID may be used to generate a meta ID used in data upload. In some cases, the signaling of the data collection configuration may correspond to reusing MDT configuration signaling or as an information element (IE) in an RRCReconfiguration message.

[0133] In response to receiving the data collection configuration, UE 104 may send a data collection configuration ACK to gNB 102 at step 1006. In some cases, UE 104 may reject the data collection request and instead transmit a model training configuration reject message to gNB 102. Subsequently, at step 1008, UE 104 may perform data collection with gNB 102. At step 1010, training data may be reported between UE vendor 502, UE 104, gNB 102, and model / data repository 504.

[0134] Fig.11 is a message diagram 1100 illustrating example messages for reporting training data in steps during a data collection process for CSF compression. For example, diagram 1100 illustrates Fig.10 During step 1010, the UE provider (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 base station 102) and a data repository / collection entity (such as Figure 5 Specific messaging occurs between the gNB supplier 504).

[0135] In one aspect, the reporting of training data may be performed based on MDT enhancements. For example, at step 1102, UE 104 may send a data report to gNB 104. At step 1104, gNB 104 may forward the data report to data repository / collection entity 504. In some cases, new IEs may be added to the MDT report signaling, which may be file-based or flow-based.

[0136] In one aspect, vendor-UE-vendor training data reporting may be performed. For example, at step 1106, UE 104 may send a data report to UE vendor 502. Additionally, at step 1108, UE 104 may send a data address report to gNB 102. At step 1110, gNB 102 may forward the data address report to data repository / collection entity 504. In some cases, UE 104 may transmit data to a UE server corresponding to UE vendor 502 due to limited memory at UE 104, and UE 104 may then provide an address for gNB vendor 504 to download the data. Alternatively, UE 104 may report the data directly to data repository / collection entity 504.

[0137] In one aspect, vendor-to-vendor training data reporting may be performed. For example, at step 1112, the UE 104 may send a data report to the UE vendor 502. At step 1114, the UE vendor 502 may upload the data received from the data report to the data repository / collection entity 504. In some cases, the UE vendor 502 may report directly to the gNB vendor 504 using a proprietary protocol.

[0138] Fig.12 is a message diagram 1200 illustrating example messages for a data collection process for CSF compression. For example, diagram 1200 illustrates a UE vendor (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 base station 102) and a data repository / collection entity (such as Figure 5 Message sending and receiving between gNB supplier 504).

[0139] In one aspect, at step 1202, the data report to the data repository / collection entity 504 may transmit a training data request to the UE provider 502. At step 1204, the UE provider 502 may forward the training data request to the UE 104. After receiving the request from the UE provider 502, the UE 104 forwards the request to the gNB 102 to request the data collection RS. At step 1206, the gNB 102 may send a data collection configuration to the UE 104. For example, the information about the data collection configuration message may include at least one of the RS for data collection such as a CSI-RS list, the area for data collection, the time period for data collection, the network side configuration, the channel type, and the process ID for data collection. In some cases, the configured RS may be dynamically activated / deactivated by the gNB 102 such as via a MAC CE or DCI. In some cases, the process ID may be a model ID that has been registered with the MLF, or the process ID may be used to generate a meta ID used in data upload. In some cases, the process ID is a meta ID to be used in data collection. The meta ID may correspond to a CSI-RS beam configuration or antenna configuration including antenna layout, antenna element to TxRU mapping, digital / analog beamforming. In some cases, the signaling of the data collection configuration may correspond to reused MDT configuration signaling or as an IE in the RRCReconfiguration message.

[0140] In response to receiving the data collection configuration, UE 104 may send a data collection configuration ACK to gNB 102 at step 1208. Subsequently, UE 104 may perform data collection with gNB 102 at step 1210. At step 1212, the data may be uploaded to UE provider 502. At step 1214, UE provider 502 may upload the data to data repository collection entity 504.

[0141] Figures 13 to 15 1300, 1400, and 1500 illustrate example messages for requesting that existing data be uploaded to a repository. Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 base station 102) and a data repository / collection entity (such as Figure 5 Message sending and receiving between gNB supplier 504).

[0142] In one aspect, the message diagram 1300 illustrates a side operation in which a repository such as the data repository / collection entity 504 may communicate directly with a UE server of the UE vendor 502 via a proprietary protocol. For example, at step 1302, the data repository / collection entity 504 may transmit a training data request to the UE vendor 502. At step 1304, in response to the training data request, the UE vendor 502 may transmit a data upload to the data repository / collection entity 504.

[0143] In one aspect, message diagram 1400 illustrates a case where there are no side operations between data repository / collection entity 504 and UE provider 502. For example, at step 1402, data repository / collection entity 504 may transmit a training data request to gNB 102. At step 1404, gNB 102 may forward training data request 1404 to UE 104. At step 1406, UE 104 may communicate a data report to data repository / collection entity 504. In some cases, UE 104 may communicate a data report to gNB 102, and gNB 102 may forward the data to data repository / collection entity 504.

[0144] In one aspect, message diagram 1500 illustrates another scenario in which there are no side operations between data repository / collection entity 504 and UE vendor 502. For example, at step 1502, data repository / collection entity 504 may transmit a training data request to gNB 102. At step 1504, gNB 102 may forward training data request 1504 to UE 104. At step 1506, UE 104 may transmit a training data query to UE vendor 502. At step 1508, UE vendor 502 may transmit data or data address to UE 104. At step 1510, UE 104 may transmit data and data address report to gNB 102. At step 1512, gNB 102 may transmit data and data address report to data repository / collection entity 504.

[0145] Fig.16 is a message diagram 1600 illustrating example messages for performing a data collection process and offline model training for CSF compression using area-based training at a UE. For example, diagram 1700 illustrates a UE vendor (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 102), model manager / OAM 1602 and model / data repository 504 (both of which are associated with Figure 5 gNB vendor 504 associated with and / or part of it).

[0146] In one aspect, at step 1604, MLF for CSF compression is defined and registered across UE vendor 502, UE 104, gNB 102, model manager / OAM 1602, and model / data repository 504. For example, UE vendor 502 registers its CSF model with a network such as gNB 102 and / or gNB vendor 504. In some cases, the registration includes: a model ID or model structure (MS) ID; a list of parameter set (PS) IDs; applicable scenarios for each PS including region, configuration, and UE type; and if multiple models are registered, applicable scenarios for each model. For example, model training is initiated by UE vendor 502. In some cases, model training is coordinated by model manager / OAM 1602, which may correspond to OAM, RIC (ORAN defined network entity, intelligent network controller), CU-XP, or gNB, such as gNB 102 depending on the deployment scenario and use case.

[0147] In the case of area-based training, the UE vendor 502 transmits a request directly to a network-side server (e.g., a model / data repository (MR) 504 corresponding to the gNB vendor 504). For example, the MR 504 requests the model manager 1602 to initiate model training. The model manager 1602 requests the gNB 102 to configure the model training. Subsequently, the gNB 102 selects a suitable UE 104 for training data collection based on UE type, UE capabilities, and user consent. For example, in step 1606, as part of the training initiation process, the UE vendor 502 may transmit a training data request to the model / data repository 504. In the model training configuration, the network such as the gNB 102 transmits metadata for model training and information about data collection. For example, the information about data collection may include: a list of RSs (e.g., CSI-RS) used for data collection, where the configured RSs may be dynamically activated / deactivated by the gNB, for example, via MAC CE or DCI; an area for data collection; and a time period for data collection. In some cases, metadata may include NM ID (associated with network side mode ID) (where data of different NM IDs may be used for model training respectively), network side configuration, and additional information such as channel type. In some cases, signaling may include reused MDT configuration signaling (where configuration information is added as IE to RRCReconfiguration message) or a new signaling process.

[0148] At step 1608, the model / data repository 504 may transmit a model training initiation message to the model manager / OAM 1602. At step 1610, the model / data repository 504 may transmit a training data request ACK to the UE vendor 502 in response to receiving the training data request at step 1606. At step 1612, the model manager / OAMA 1602 sends a model training request 1612 to the gNB 102. At step 1614, the gNB 102 may perform UE selection and transmit a model training configuration to the UE 104 at step 1616. At step 1618, the UE 104 may send a model training configuration ACK to the gNB 102. At step 1620, the gNB 102 transmits a model training response to the model manager / OAM 1602.

[0149] For example, UE 104 collects data based on the received configuration. The collected data is uploaded to the UE vendor 502 server together with additional information, including: timestamps described in absolute time, relative time, or SFN+time slot+(optionally) symbol form; location information, such as GNSS (if available) and radio fingerprints: RSRP / RSRQ measurements of serving cells and neighboring cells; and metadata, such as RS type, ID, and NM_ID. In some cases, model training may be based on previously collected data without metadata. The received configuration information may be used as metadata and reported to the UE vendor 502 server. In this case, real data collection and reporting may be skipped. In step 1622, UE 104 performs data collection. In step 1624, UE 104 reports training data to UE vendor 502 when performing data collection. In step 1626, UE vendor 502 performs model training upon receiving the training data report.

[0150] For example, the model training report may be uploaded directly to the model / data repository 504, or the data may be refined for the gNB 102 to derive the base station model. If the data is refined, the UE vendor 502 generates some refined data {Z, CSI} for the trained base station model, and the gNB vendor 504 may derive its model based on this data. Upon completion of model training, the UE vendor 502 may transmit the model training report to the model / data repository 504 at step 1628. Upon receiving the model training report, the model / data repository 504 performs a model update at step 1630.

[0151] Fig.17 is a message diagram 1700 illustrating example messages for performing a data collection process and offline model training for CSF compression using UE-based configuration at a UE. For example, diagram 1700 illustrates a UE vendor (such as Figure 5UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 102), model manager / OAM 1602 and model / data repository 504 (both of which are associated with Figure 5 gNB vendor 504 associated with and / or part of it).

[0152] In one aspect, at step 1702, MLF for CSF compression is defined and registered across UE vendor 502, UE 104, gNB 102, model manager / OAM 1602, and model / data repository 504. For example, UE vendor 502 registers its CSF model with a network such as gNB 102 and / or gNB vendor 504. In some cases, the registration includes: a model ID or model structure (MS) ID; a list of parameter set (PS) IDs; applicable scenarios for each PS including region, configuration, and UE type; and if multiple models are registered, applicable scenarios for each model. For example, model training is initiated by UE vendor 502. In some cases, model training is coordinated by model manager / OAM 1602, which may correspond to OAM, RIC (ORAN defined network entity, intelligent network controller), CU-XP, or gNB, such as gNB 102 depending on the deployment scenario and use case.

[0153] In the case of UE 104-based training, the UE provider 502 requests the UE 104 to collect data for model training, such as via a UE application. The UE 104 transmits the request to the gNB 102 and the model manager 1602 for the gNB 102 to configure the UE 104 for training data collection. For example, at step 1704, the UE provider 504 may transmit a training data request to the UE 104. At step 1706, the UE 104 may send a message to the gNB 102 that model training is required. At step 1708, the gNB 102 may forward the message that model training is required to the model manager / OAM 1602. In the model training configuration, the network, such as the gNB 102, transmits metadata for model training and information about data collection. For example, the information about data collection may include: a list of RSs (e.g., CSI-RS) for data collection, where the configured RSs may be dynamically activated / deactivated by the gNB, such as via MAC CE or DCI; an area for data collection; and a period for data collection. In some cases, metadata may include NM ID (associated with network side mode ID) (where data of different NM IDs may be used for model training respectively), network side configuration, and additional information such as channel type. In some cases, signaling may include reused MDT configuration signaling (where configuration information is added as IE to RRCReconfiguration message) or a new signaling process.

[0154] At step 1710, gNB 102 and model manager / OAM 1602 may authorize UE 104 to perform CSF model training. Upon completing the authorization, model manager / OAM 1602 may transmit a model training request to gNB 102 at step 1712. At step 1714, gNB 102 may send a model training configuration to UE 104. At step 1716, in response to receiving the model training configuration message, UE 104 may send a model training configuration ACK to gNB 102. At step 1718, gNB 102 transmits a model training response to model manager / OAM 1602.

[0155] For example, UE 104 collects data based on the received configuration. The collected data is uploaded to the UE vendor 502 server together with additional information, including: timestamps described in absolute time, relative time, or SFN+time slot+(optionally) symbol form; location information, such as GNSS (if available) and radio fingerprints: RSRP / RSRQ measurements of serving cells and neighboring cells; and metadata, such as RS type, ID, and NM_ID. In some cases, model training may be based on previously collected data without metadata. The received configuration information may be used as metadata and reported to the UE vendor 502 server. In this case, real data collection and reporting may be skipped. In step 1720, UE 104 performs data collection. In step 1722, UE 104 transmits a training data report to UE vendor 502. In step 1724, UE vendor 502 performs model training.

[0156] For example, the model training report may be uploaded directly to the model / data repository 504, or the data may be refined for the gNB 102 to derive the base station model. If the data is refined, the UE vendor 502 generates some refined data {Z, CSI} for the trained base station model, and the gNB vendor 504 may derive its model based on this data. At step 1726, the UE vendor 502 transmits the model training report to the model / data repository 504. At step 1728, the model / data repository 504 performs a model update upon receiving the model training report.

[0157] Fig.18 1800 is a conceptual diagram illustrating an example frame structure for uploading data. For example, in response to performing data collection between UE 104 and gNB 102, UE 104 may send a report of the data as illustrated in multiple instances 1802, 1804, 1806, and 1808 to UE vendor 502.

[0158] In one aspect, the UE report may include {H_raw, meta_id}, where H_raw is the channel estimate based on RB index, port index, and Rx index; and Meta_id has the following hierarchical structure and includes: Cell ID; CSI-RS resource ID (implicitly conveying antenna mapping / layout); List of records {record #1, record #2, etc.}, where each record includes a timestamp, such as a CSI-RS transmission instance or timeslot index, or a measurement duration index (for example, the record is based on a measurement of a certain duration, where the duration should be configured): gNB 102 may dynamically change the antenna mapping / layout, so a timestamp is required to mark the reported data with the correct antenna mapping / layout; SNR, SINR or RSRP; subcarrier spacing; Doppler / delay spread measurement.

[0159] In one aspect, the format of H_raw and other additional data may include a frequency domain resolution corresponding to subcarriers, RBs, or subbands; and / or the eigendirections of H_raw are also reported as {H_raw, V_raw, meta_id}, where the V_raw frequency granularity is less than or equal to the H_raw frequency granularity.

[0160] Fig.19 is a message diagram 1900 illustrating example messages for performing a data collection process and offline model training for CSF compression using area-based training at a UE. For example, diagram 1900 illustrates a UE vendor (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 102), model manager / OAM 1602 and model / data repository 504 (both of which are associated with Figure 5 gNB vendor 504 associated with and / or part of it).

[0161] In one aspect, at step 1902, MLF for CSF compression is defined and registered across UE vendor 502, UE 104, gNB 102, model manager / OAM 1602, and model / data repository 504. For example, UE vendor 502 registers its CSF model with a network such as gNB 102 and / or gNB vendor 504. In some cases, the registration includes: a model ID or model structure (MS) ID; a list of parameter set (PS) IDs; applicable scenarios for each PS including region, configuration, and UE type; and if multiple models are registered, applicable scenarios for each model. For example, model training is initiated by UE vendor 502. In some cases, model training is coordinated by model manager / OAM 1602, which may correspond to OAM, RIC (ORAN defined network entity, intelligent network controller), CU-XP, or gNB, such as gNB 102 depending on the deployment scenario and use case.

[0162] At step 1904, the model / data repository 504 may transmit a model training request to the model manager / OAM 1602. At step 1906, the model manager / OAM 1602 forwards the model training request to the gNB 102. At step 1908, the gNB 102 performs UE selection. At step 1910, the gNB 102 sends a model training configuration to the UE 104. At step 1912, the UE 104 sends a model training configuration ACK to the gNB 102. At step 1914, the gNB 102 transmits a model training response to the model manager / OAM 1602. At step 1916, a training data report is generated. At step 1918, the model / data repository 504 performs model training. At step 1920, the model / data repository 504 transmits a UE model delivery to the UE vendor 502.

[0163] Fig. 20 is a message diagram 2000 illustrating example messages for performing a data collection process and offline model training for CSF compression using UE-based training at a UE. For example, diagram 2000 illustrates a UE vendor (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 Base station 102), model manager / RIC 2002 and model / data repository 504 (both of which are Figure 5 gNB vendor 504 associated with and / or part of it).

[0164] In one aspect, at step 2004, MLF for CSF compression is defined and registered across UE vendors 502, UE 104, gNB 102, model manager / RIC 2002, and model / data repository 504. For example, UE vendor 502 registers its CSF model with a network such as gNB 102 and / or gNB vendor 504. In some cases, the registration includes: a model ID or model structure (MS) ID; a list of parameter set (PS) IDs; applicable scenarios for each PS including region, configuration, and UE type; and if multiple models are registered, applicable scenarios for each model. For example, model training is initiated by UE vendor 502. In some cases, model training is coordinated by model manager / RIC 2002, which may correspond to OAM, RIC (ORAN defined network entity, intelligent network controller), CU-XP, or gNB, such as gNB 102 depending on the deployment scenario and use case.

[0165] At step 2006, the model / data repository 504 may transmit a model training request to the model manager / RIC 2002. At step 2008, the model manager / RIC 2002 performs UE selection. At step 2010, the model manager / RIC 2002 forwards the model training request to the gNB 102. At step 2012, the gNB 102 sends a model training configuration to the UE 104. At step 2014, the UE 104 sends a model training configuration ACK to the gNB 102. At step 2016, the gNB 102 transmits a model training response to the model manager / RIC 2002. At step 2018, a training data report is generated. At step 2020, the model / data repository 504 performs model training. At step 2022, the model / data repository 504 transmits a UE model delivery to the UE vendor 502.

[0166] Fig.21 is a message diagram 2100 illustrating example messages for reporting training data in steps during a data collection process for CSF compression. For example, diagram 2100 illustrates Fig.19 Step 1916 and Fig. 20 During step 2018, the UE provider (such as Figure 5 UE provider 502), UE (such as Figure 1 UE 104), gNB (such as Figure 1 base station 102), model manager 1602 and model / data repository (such as Figure 5 The specific messaging that occurs between the gNB vendor 504 and the gNB provider 504. In one example, the data to be reported may include a channel matrix, UE model information (such as MS ID and PS ID and NM ID), and a timestamp.

[0167] In one aspect, reporting of training data may be performed based on MDT enhancements. For example, at step 2102, UE 104 may send a data report to gNB 104. At step 2104, gNB 104 may forward the data report to model manager 1602. In some cases, new IEs may be added to the MDT report signaling, which may be file-based or stream-based. At step 2106, model manager 1602 may forward the data report to model / data repository 504.

[0168] In one aspect, vendor-to-vendor training data reporting may be performed. For example, at step 2108, the UE 104 may send a data report to the UE vendor 502. At step 2110, the UE vendor 502 may upload the data received from the data report to the model / data repository 504. In some cases, the UE vendor 502 may report directly to the gNB vendor 504 using a proprietary protocol.

[0169] In one aspect, the data collected by the UE can be used to train two models on the network side. For example, data collection can be performed by the UE provider 502, similar to Fig.16 and Fig.17 UE provider 502 based on Fig.21 Steps 2108 and 2110 upload the collected data to the gNB provider 504. In addition, model training can be performed, similar to Fig.19 and Fig. 20 The gNB provider 504 transmits the UE model to the UE provider 502, similar to Fig.19 and Fig. 20 The message reception and reception described in .

[0170] Fig. 22 is a conceptual data flow diagram 2200 illustrating the flow of data between different means / components in an example base station 2202, which can be an example of a base station 102 including a network training component 120. The network training component 120 can include a data collection component 124.

[0171] Base station 2202 may also include a receiver component 2250 and a transmitter component 2252. Receiver component 2250 may include, for example, an RF receiver for receiving signals as described herein. Transmitter component 2252 may include, for example, an RF transmitter for transmitting signals as described herein. In some implementations, receiver component 2250 and transmitter component 2252 may be co-located in a transceiver (such as Figure 3 In Tx / Rx318).

[0172] Fig.23 2300 is a conceptual data flow diagram illustrating the data flow between different means / components in an example UE 2304, which may be an example of UE 104 and includes UE training component 140. Figure 1 As discussed, UE training component 140 can include data collection component 142 .

[0173] UE 104 may also include a receiver component 2370 and a transmitter component 2372. Receiver component 2370 may include, for example, an RF receiver for receiving the signals described herein. Transmitter component 2372 may include, for example, an RF transmitter for transmitting the signals described herein. In some implementations, receiver component 2370 and transmitter component 2372 may be co-located in a transceiver (such as Figure 3 in Tx / Rx 354).

[0174] Fig.2424 is a flow chart of an example method 2400 for a UE vendor for cross-node machine learning training. The method 2400 may be performed by a UE vendor (such as a UE vendor 310 / 502, which may include a memory 360 and may be the entire UE vendor 310 / 502 or a component of the UE vendor 310 / 502, such as a Tx processor 368, an Rx processor 356, and / or a controller / processor 359).

[0175] At block 2410, method 2400 trains one or more encoder-decoder pairs based on the original data set of the UE vendor. In some specific implementations, for example, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to train one or more encoder-decoder pairs based on the original data set of the UE vendor. Accordingly, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a means for training one or more encoder-decoder pairs based on the original data set of the UE vendor.

[0176] At block 2420, method 2400 includes generating one or more training sets based on outputs of one or more encoders running the UE vendor's original data set. In some specific implementations, for example, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to generate one or more training sets based on outputs of one or more encoders running the UE vendor's original data set. Accordingly, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a component for generating one or more training sets based on outputs of one or more encoders running the UE vendor's original data set.

[0177] At block 2420, method 2400 includes communicating the one or more training sets to a network entity provider. In some specific implementations, for example, the UE provider 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to communicate the one or more training sets to the network entity provider. Accordingly, the UE provider 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a component for communicating the one or more training sets to the network entity provider.

[0178] In some implementations, each of the one or more training sets includes an encoder identification (ID), an encoder output, and an expected decoder output.

[0179] In some implementations, each of the one or more training sets is associated with one or more metadata to enable switching between one or more models during inference.

[0180] In some implementations, the one or more metadata include at least one of UE antenna configuration, signal-to-noise ratio (SNR), reference signal received power (RSRP), delay rate, average delay, and timestamp.

[0181] In some implementations, the UE vendor 310 / 502 , the Rx processor 356 , or the controller / processor 359 can be configured to decompose the one or more metadata into a UE meta-ID.

[0182] In some implementations, the encoder output of the one or more encoders corresponds to a compressed channel state information (CSI) feedback (CSF) message.

[0183] In some implementations, a decoder output of one or more decoders in one or more encoder-decoder pairs includes a reconstructed CSF corresponding to one or more pre-coding vectors.

[0184] Fig.25 2 is a flow chart of an example method 2500 for a UE vendor for cross-node machine learning training. The method 2500 may be performed by a UE vendor (such as a UE vendor 310 / 502, which may include a memory 360 and may be the entire UE vendor 310 / 502 or a component of the UE vendor 310 / 502, such as a Tx processor 368, an Rx processor 356, and / or a controller / processor 359).

[0185] At block 2510, method 2500 trains one or more encoder-decoder pairs based on the original data set of the UE vendor. In some specific implementations, for example, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to train one or more encoder-decoder pairs based on the original data set of the UE vendor. Accordingly, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a means for training one or more encoder-decoder pairs based on the original data set of the UE vendor.

[0186] At block 2520, method 2500 includes generating two training sets for each encoder-decoder pair in one or more encoder-decoder pairs based on outputs of one or more encoders running the UE vendor's original data set. In some specific implementations, for example, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to generate two training sets for each encoder-decoder pair in one or more encoder-decoder pairs based on outputs of one or more encoders running the UE vendor's original data set. Accordingly, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a component for generating two training sets for each encoder-decoder pair in one or more encoder-decoder pairs based on outputs of one or more encoders running the UE vendor's original data set.

[0187] At block 2520, method 2500 includes communicating the two training sets to a network entity provider. In some specific implementations, for example, the UE provider 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to communicate the two training sets to the network entity provider. Accordingly, the UE provider 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a component for communicating the two training sets to the network entity provider.

[0188] In some implementations, generating two training sets further includes generating a first training set based on outputs of an encoder and a decoder using an original dataset of a UE vendor.

[0189] In some implementations, the first training set includes an encoder identification (ID), an encoder output, and a decoder reconstruction of an expected decoder output.

[0190] In some implementations, generating two training sets further includes generating a second training set based on perturbing encoder outputs in the first training set with the vector and calculating corresponding decoder outputs.

[0191] In some implementations, the second training set includes encoder IDs, combinations of encoder outputs and vectors, and corresponding decoder outputs.

[0192] In some implementations, the UE provider 310 / 502, Rx processor 356, or controller / processor 359 may be configured to identify a replacement decoder that approximates a found decoder within one of the one or more encoder-decoder pairs; and communicate the replacement decoder to the network entity provider.

[0193] In some implementations, the replacement decoder produces at least similar output as the found decoder in response to the first training set and the second training set.

[0194] In some implementations, identifying an alternative decoder further comprises identifying, for each encoder ID corresponding to a corresponding encoder in the one or more encoder-decoder pairs, a corresponding alternative decoder.

[0195] In some implementations, the encoder output of the one or more encoders corresponds to a compressed channel state information (CSI) feedback (CSF) message.

[0196] In some implementations, a decoder output of one or more decoders in one or more encoder-decoder pairs includes a reconstructed CSF corresponding to one or more pre-coding vectors.

[0197] Fig.26 26 is a flow chart of an example method 2600 of a network entity provider for cross-node machine learning training. The method 2600 may be performed by a network entity provider (such as a network entity / gNB provider 316 / 504, which may include a memory 376 and may be a network entity / gNB provider 316 / 504 or a component of a network entity / gNB provider 316 / 504, such as a Tx processor 316, an Rx processor 370, or a controller / processor 375).

[0198] At block 2610, method 2600 includes receiving one or more training sets from a UE vendor, the one or more training sets corresponding to one or more encoder-decoder pairs. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to receive one or more training sets from a UE vendor, the one or more training sets corresponding to one or more encoder-decoder pairs. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide a means for receiving one or more training sets from a UE vendor, the one or more training sets corresponding to one or more encoder-decoder pairs.

[0199] At block 2620, the method 2600 includes training one or more decoders associated with the one or more training sets. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to train one or more decoders associated with the one or more training sets. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide means for training one or more decoders associated with the one or more training sets.

[0200] In some implementations, each of the one or more training sets includes an encoder identification (ID), an encoder output, and an expected decoder output.

[0201] In some implementations, each of the one or more training sets is associated with one or more metadata to enable switching between one or more models during inference.

[0202] In some implementations, the one or more metadata include at least one of UE antenna configuration, signal-to-noise ratio (SNR), reference signal received power (RSRP), delay rate, average delay, and timestamp.

[0203] In some implementations, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to determine, based on the one or more training sets, whether one or more decoders are associated with a particular network entity or shared across multiple network entities.

[0204] Fig. 27 2700 is a flow chart of an example method 2700 of a network entity provider for cross-node machine learning training. The method 2700 may be performed by a network entity provider (such as a network entity / gNB provider 316 / 504, which may include a memory 376 and may be a network entity / gNB provider 316 / 504 or a component of a network entity / gNB provider 316 / 504, such as a Tx processor 316, an Rx processor 370, or a controller / processor 375).

[0205] At block 2710, method 2700 includes receiving two training sets from a UE vendor, the two training sets corresponding to one or more encoder-decoder pairs. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to receive two training sets from a UE vendor, the two training sets corresponding to one or more encoder-decoder pairs. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide a means for receiving two training sets from a UE vendor, the two training sets corresponding to one or more encoder-decoder pairs.

[0206] At block 2720, the method 2700 includes training one or more decoders associated with the two training sets. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to train one or more decoders associated with the two training sets. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide means for training one or more decoders associated with the two training sets.

[0207] In some implementations, the first training set includes an encoder identification (ID), encoder output, and reconstructions of expected decoder outputs by one or more decoders.

[0208] In some implementations, the second training set includes encoder IDs, combinations of encoder outputs and vectors, and corresponding decoder outputs.

[0209] In some implementations, the network entity / gNB provider 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to receive a replacement decoder that approximates a found decoder within one of the one or more encoder-decoder pairs.

[0210] In some implementations, the replacement decoder produces at least similar output as the found decoder in response to the first training set and the second training set.

[0211] In some implementations, each of the two training sets is associated with one or more metadata to enable switching between one or more models during inference.

[0212] In some implementations, the one or more metadata include at least one of UE antenna configuration, signal-to-noise ratio (SNR), reference signal received power (RSRP), delay rate, average delay, and timestamp.

[0213] In some implementations, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to determine whether one or more decoders are associated with a particular network entity or shared across multiple network entities based on the two training sets.

[0214] Fig.28 28 is a flow chart of an example method 2800 of a UE performing a CSF data collection process. The method 2800 may be performed by a UE, such as UE 104, which may include memory 360 and may be the entire UE 104 or a component of UE 104, such as Tx processor 368, Rx processor 356, or controller / processor 359.

[0215] At block 2810, method 2800 optionally includes receiving a training data request from a UE vendor. In some implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may be configured to receive a training data request from a UE vendor. Accordingly, UE 104, Rx processor 356, or controller / processor 359 may provide a component for receiving a training data request from a UE vendor.

[0216] At block 2820, method 2800 includes sending a training data request to a network entity. In some implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may be configured to send a training data request to a network entity. Accordingly, UE 104, Rx processor 356, or controller / processor 359 may provide a component for sending a training data request to a network entity.

[0217] At block 2830, method 2800 includes receiving a data collection configuration message from a network entity in response to sending a training data request. In some implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may be configured to receive a data collection configuration message from a network entity in response to sending a training data request. Accordingly, UE 104, Rx processor 356, or controller / processor 359 may provide a component for receiving a data collection configuration message from a network entity in response to sending a training data request.

[0218] At block 2840, method 2800 includes sending a data collection configuration confirmation (ACK) to a network entity in response to receiving the data collection configuration message. In some implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may be configured to send a data collection configuration confirmation (ACK) to a network entity in response to receiving the data collection configuration message. Accordingly, UE 104, Rx processor 356, or controller / processor 359 may provide a means for sending a data collection configuration confirmation (ACK) to a network entity in response to receiving the data collection configuration message.

[0219] At block 2850, method 2800 includes performing a data collection process based on the data collection configuration message. In some specific implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may be configured to perform a data collection process based on the data collection configuration message. Accordingly, UE 104, Rx processor 356, or controller / processor 359 may provide a component for performing a data collection process based on the data collection configuration message.

[0220] At block 2860, the method 2800 optionally includes uploading one or more data to a UE vendor based on performing the data collection process. In some specific implementations, for example, the UE 104, the Rx processor 356, or the controller / processor 359 may be configured to upload one or more data to a UE vendor based on performing the data collection process. Accordingly, the UE 104, the Rx processor 356, or the controller / processor 359 may provide a component for uploading one or more data to a UE vendor based on performing the data collection process.

[0221] In some specific implementations, the data collection configuration message includes at least one of a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and a process identifier (ID) regarding data collection.

[0222] In some implementations, the process ID corresponds to the model ID registered with the machine learning function (MLF).

[0223] In some embodiments, the process ID corresponds to a meta ID used for data collection, or a meta ID is generated based on the process ID for data upload corresponding to one or more metadata.

[0224] In some implementations, receiving the data collection configuration message further comprises receiving the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

[0225] In some implementations, the one or more data correspond to a UE report including a downlink raw channel matrix and a metadata identifier (meta ID).

[0226] In some implementations, the downlink raw channel matrix corresponds to a channel estimate based on a resource block (RB) index, a port index, and a receive antenna index.

[0227] In some implementations, the meta-ID includes at least one of a packet ID, a cell / carrier ID, a channel state information (CSI) reference signal (RS) resource ID, a list of one or more records of collected data, and a global navigation satellite system (GNSS).

[0228] In some implementations, the list of one or more records includes a timestamp, one of a signal-to-noise ratio (SNR), a signal-to-interference plus noise ratio (SINR), or a reference signal received power (RSRP), a subcarrier spacing, and at least one of a Doppler / delay spread measurement.

[0229] In some implementations, a format of a UE report including at least one of the downlink raw channel matrices corresponds to a first frequency domain resolution, and an eigendirection of the downlink raw channel matrix corresponds to a second frequency domain resolution.

[0230] In some implementations, the UE 104, Rx processor 356, or controller / processor 359 configured to perform a data collection process further includes: receiving a reference signal (RS) from a network entity in response to sending a data collection configuration ACK; and performing one or more measurements based on the RS.

[0231] Fig.29 2900 is a flow chart of an example method 2900 of a network entity performing a CSF data collection process. The method 2900 may be performed by a network entity, such as the network entity 102, which may include the memory 376 and may be the network entity 102 or a component of the network entity 102, such as the Tx processor 316, the Rx processor 370, or the controller / processor 375.

[0232] At block 2910, method 2900 includes receiving a training data request from a user equipment (UE). In some implementations, for example, the network entity 102, the Rx processor 316, or the controller / processor 375 may be configured to receive a training data request from the user equipment (UE). Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a means for receiving a training data request from the user equipment (UE).

[0233] At block 2920, method 2900 includes sending a data collection configuration message to the UE in response to receiving the training data request. In some implementations, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may be configured to send the data collection configuration message to the UE in response to receiving the training data request. Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a means for sending the data collection configuration message to the UE in response to receiving the training data request.

[0234] At block 2930, the method 2900 includes receiving a data collection configuration acknowledgment (ACK) from the UE in response to sending the data collection configuration message. In some implementations, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may be configured to receive a data collection configuration acknowledgment (ACK) from the UE in response to sending the data collection configuration message. Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a means for receiving a data collection configuration acknowledgment (ACK) from the UE in response to sending the data collection configuration message.

[0235] At block 2940, the method 2900 includes performing a data collection process based on the data collection configuration message. In some specific implementations, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may be configured to perform a data collection process based on the data collection configuration message. Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a component for performing a data collection process based on the data collection configuration message.

[0236] In some implementations, performing the data collection process also includes sending a reference signal (RS) to the UE in response to receiving a data collection configuration ACK.

[0237] In some specific implementations, the data collection configuration message includes at least one of a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and a process identifier (ID) regarding data collection.

[0238] In some implementations, the process ID corresponds to a model ID registered with the machine learning function (MLF) or to a meta ID used for data collection.

[0239] In some implementations, sending the data collection configuration message further comprises sending the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

[0240] Fig.30 3000 is a flow chart of an example method 3000 of a UE performing a CSF data collection process. The method 3000 may be performed by a UE, such as UE 104, which may include memory 360 and may be the entire UE 104 or a component of UE 104, such as Tx processor 368, Rx processor 356, or controller / processor 359.

[0241] At block 3010, method 3000 includes receiving a data collection configuration message from a network entity based on a training data request. In some implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may be configured to receive a data collection configuration message from a network entity based on a training data request. Accordingly, UE 104, Rx processor 356, or controller / processor 359 may provide a means for receiving a data collection configuration message from a network entity based on a training data request.

[0242] At block 3020, method 3000 includes sending a data collection configuration confirmation (ACK) to a network entity in response to receiving the data collection configuration message. In some implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may be configured to send a data collection configuration confirmation (ACK) to a network entity in response to receiving the data collection configuration message. Accordingly, UE 104, Rx processor 356, or controller / processor 359 may provide a means for sending a data collection configuration confirmation (ACK) to a network entity in response to receiving the data collection configuration message.

[0243] At block 3030, the method 3000 includes performing a data collection process based on the data collection configuration message. In some specific implementations, for example, the UE 104, the Rx processor 356, or the controller / processor 359 may be configured to perform the data collection process based on the data collection configuration message. Accordingly, the UE 104, the Rx processor 356, or the controller / processor 359 may provide a component for performing the data collection process based on the data collection configuration message.

[0244] At block 3040, the method 3000 includes reporting the training data between at least one of the network entity, the UE vendor, and the network entity vendor based on performing the data collection process. In some specific implementations, for example, the UE 104, the Rx processor 356, or the controller / processor 359 may be configured to report the training data between at least one of the network entity, the UE vendor, and the network entity vendor based on performing the data collection process. Accordingly, the UE 104, the Rx processor 356, or the controller / processor 359 may provide a means for reporting the training data between at least one of the network entity, the UE vendor, and the network entity vendor based on performing the data collection process.

[0245] In some implementations, reporting the training data further includes reporting the training data using at least one of minimization of drive tests (MDT) enhancement, vendor-UE-vendor, and vendor-to-vendor.

[0246] In some implementations, reporting the training data using the MDT enhancement includes sending the training data to a network entity.

[0247] In some implementations, reporting the training data using vendor-UE-vendor includes: reporting the training data to a UE vendor; and sending the data or a data address report to a network entity.

[0248] In some implementations, reporting the training data using vendor-to-vendor includes reporting the training data to a UE vendor.

[0249] In some specific implementations, the data collection configuration message includes a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and a process identification (ID) regarding data collection.

[0250] In some implementations, the process ID corresponds to a model ID registered with the machine learning function (MLF) or to a meta ID used for data collection.

[0251] In some implementations, receiving the data collection configuration message further comprises receiving the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

[0252] In some implementations, performing the data collection process further includes: receiving a reference signal (RS) from a network entity in response to sending a data collection configuration ACK; and performing one or more measurements based on the RS.

[0253] Fig.31 3100 is a flow chart of an example method 3100 of a network entity performing a CSF data collection process. The method 3100 may be performed by a network entity, such as the network entity 102, which may include the memory 376 and may be the network entity 102 or a component of the network entity 102, such as the Tx processor 316, the Rx processor 370, or the controller / processor 375.

[0254] At block 3110, the method 3100 includes receiving a training data request from a network entity provider. In some implementations, for example, the network entity 102, the Rx processor 316, or the controller / processor 375 may be configured to receive a training data request from a network entity provider. Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a component for receiving a training data request from a network entity provider.

[0255] At block 3120, the method 3100 includes sending a data collection configuration message to a user equipment (UE) in response to receiving the training data request. In some specific implementations, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may be configured to send the data collection configuration message to the user equipment (UE) in response to receiving the training data request. Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a means for sending the data collection configuration message to the user equipment (UE) in response to receiving the training data request.

[0256] At block 3130, the method 3100 includes receiving a data collection configuration acknowledgment (ACK) from the UE in response to sending the data collection configuration message. In some implementations, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may be configured to receive a data collection configuration acknowledgment (ACK) from the UE in response to sending the data collection configuration message. Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a means for receiving a data collection configuration acknowledgment (ACK) from the UE in response to sending the data collection configuration message.

[0257] At block 3140, the method 3100 includes performing a data collection process based on the data collection configuration message. In some specific implementations, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may be configured to perform a data collection process based on the data collection configuration message. Accordingly, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a component for performing a data collection process based on the data collection configuration message.

[0258] At block 3150, the method 3100 includes receiving or reporting training data between the UE, the UE vendor, and the network entity vendor based on performing a data collection procedure. In some specific implementations, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may be configured to receive or report training data between the UE, the UE vendor, and the network entity vendor based on performing a data collection procedure. Accordingly, for example, the network entity 102, the Tx processor 316, or the controller / processor 375 may provide a component for receiving or reporting training data between the UE, the UE vendor, and the network entity vendor based on performing a data collection procedure.

[0259] In some implementations, reporting the training data further includes reporting the training data using at least one of minimization of drive tests (MDT) enhancement, vendor-UE-vendor, and vendor-to-vendor.

[0260] In some implementations, using MDT enhanced reporting training data includes: receiving training data from the UE; and forwarding the training data to a network entity provider.

[0261] In some implementations, using the vendor-UE-vendor report training data includes: receiving data or a data address report from the UE; and forwarding the data or the data address report to a network entity vendor.

[0262] In some implementations, performing the data collection process also includes sending a reference signal (RS) to the UE in response to receiving a data collection configuration ACK.

[0263] Fig.32 32 is a flow chart of an example method 3200 performed by a UE vendor for data collection and offline model training for CSF compression. The method 3200 may be performed by a UE vendor (such as a UE vendor 310 / 502, which may include a memory 360 and may be the entire UE vendor 310 / 502 or a component of the UE vendor 310 / 502, such as a Tx processor 368, an Rx processor 356, and / or a controller / processor 359).

[0264] At block 3210, the method 3200 includes communicating a training data request to initiate model training for the UE vendor and the network entity vendor. In some specific implementations, for example, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to communicate a training data request to initiate model training for the UE vendor and the network entity vendor. Accordingly, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a component for communicating a training data request to initiate model training for the UE vendor and the network entity vendor.

[0265] At block 3220, the method 3200 includes receiving a training data report in response to communicating the training data request. In some implementations, for example, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to receive the training data report in response to communicating the training data request. Accordingly, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a means for receiving the training data report in response to communicating the training data request.

[0266] At block 3230, the method 3200 includes performing model training for a channel state information (CSI) feedback (CSF) model. In some specific implementations, for example, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to perform model training for a channel state information (CSI) feedback (CSF) model. Accordingly, the UE vendor 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a component for performing model training for a channel state information (CSI) feedback (CSF) model.

[0267] At block 3240, the method 3200 includes communicating the model training report to the network entity provider. In some specific implementations, for example, the UE provider 310 / 502, the Rx processor 356, or the controller / processor 359 may be configured to communicate the model training report to the network entity provider. Accordingly, the UE provider 310 / 502, the Rx processor 356, or the controller / processor 359 may provide a component for communicating the model training report to the network entity provider.

[0268] In some implementations, communicating the training data request further includes communicating the training data request to a network entity provider to initiate model training.

[0269] In some implementations, the UE provider 310 / 502, the Rx processor 356, or the controller / processor 359 can be configured to receive a training data request acknowledgment (ACK) from the network entity provider in response to communicating the training data request.

[0270] In some implementations, communicating the training data request also includes communicating the training data request to the UE to collect data for model training.

[0271] In some implementations, the UE vendor 310 / 502 , the Rx processor 356 , or the controller / processor 359 can be configured to register one or more CSF models with a network associated with the UE vendor and the network entity vendor.

[0272] In some specific implementations, registering one or more CSF models includes registering one or more model identifiers (IDs) or model structure (MS) IDs, a list of parameter sets (PS) IDs, and applicable scenarios for each PS including region, configuration, and UE type.

[0273] In some implementations, the training data report includes at least one of a timestamp, location information, and metadata.

[0274] In some implementations, the timestamp corresponds to at least one of an absolute time, a relative time, or a combination of a system frame number (SFN), a time slot, and optionally a symbol.

[0275] In some implementations, the location information includes at least one of a global navigation satellite system (GNSS) and a radio fingerprint corresponding to reference signal received power (RSRP) / reference signal received quality (RSRQ) measurements of the serving cell and neighboring cells.

[0276] In some implementations, the metadata includes at least one of a reference signal (RS) type identification (ID) and an NM ID.

[0277] In some implementations, communicating the model training also includes directly uploading the model training or refining data for the network entity to derive the model training.

[0278] In some implementations, the refined data for the network entity corresponds to a UE report including a downlink raw channel matrix and a metadata identification (meta ID).

[0279] In some implementations, the downlink raw channel matrix corresponds to a channel estimate based on a resource block (RB) index, a port index, and a receiver index.

[0280] In some implementations, the meta ID includes a cell ID, a channel state information (CSI) reference signal (RS) resource ID, and a list of one or more records.

[0281] In some implementations, the list of one or more records includes a timestamp, one of a signal-to-noise ratio (SNR), a signal-to-interference plus noise ratio (SINR), or a reference signal received power (RSRP), a subcarrier spacing, and at least one of a Doppler / delay spread measurement.

[0282] In some implementations, the format of the UE report including the downlink raw channel matrix corresponds to the frequency domain resolution and eigen-directions of the downlink raw channel matrix.

[0283] Fig.33 33 is a flow chart of an example method 3300 performed by a network entity provider for data collection and offline model training for CSF compression. The method 3300 may be performed by a network entity provider (such as a network entity / gNB provider 316 / 504, which may include a memory 376 and may be a network entity / gNB provider 316 / 504 or a component of the network entity / gNB provider 316 / 504, such as a Tx processor 316, an Rx processor 370, or a controller / processor 375).

[0284] At block 3310, the method 3300 includes communicating a training data request to initiate model training for a user equipment (UE) vendor and a network entity vendor. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to communicate a training data request to initiate model training for a user equipment (UE) vendor and a network entity vendor. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide a component for communicating a training data request to initiate model training for a user equipment (UE) vendor and a network entity vendor.

[0285] At block 3320, the method 3300 includes receiving a training data report in response to communicating the training data request. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to receive the training data report in response to communicating the training data request. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide means for receiving the training data report in response to communicating the training data request.

[0286] At block 3330, the method 3300 includes performing model training for a channel state information (CSI) feedback (CSF) model. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to perform model training for a channel state information (CSI) feedback (CSF) model. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide a component for performing model training for a channel state information (CSI) feedback (CSF) model.

[0287] At block 3340, method 3300 includes communicating the model training report to the UE vendor. In some implementations, for example, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may be configured to communicate the model training report to the UE vendor. Accordingly, the network entity / gNB vendor 316 / 504, the Tx processor 316, or the controller / processor 375 may provide a component for communicating the model training report to the UE vendor.

[0288] In some implementations, communicating the training data request also includes communicating the training data request to the model manager to forward to a network entity for performing a UE selection process.

[0289] In some implementations, communicating the training data request also includes communicating the training data request to a model manager to perform a UE selection process.

[0290] In some implementations, the network entity / gNB vendor 316 / 504, Tx processor 316, or controller / processor 375 may be configured to register one or more CSF models with a network associated with a UE vendor and a network entity vendor.

[0291] In some specific implementations, registering one or more CSF models includes registering one or more model identifiers (IDs) or model structure (MS) IDs, a list of parameter sets (PS) IDs, and applicable scenarios for each PS including region, configuration, and UE type.

[0292] In some implementations, communicating the model training also includes directly uploading the model training or refining data for the network entity to derive the model training.

[0293] In some implementations, the refined data for the network entity corresponds to a UE report including a downlink raw channel matrix and a metadata identification (meta ID).

[0294] In some implementations, the downlink raw channel matrix corresponds to a channel estimate based on a resource block (RB) index, a port index, and a receiver index.

[0295] In some implementations, the meta ID includes a cell ID, a channel state information (CSI) reference signal (RS) resource ID, and a list of one or more records.

[0296] In some implementations, receiving the training data report further includes receiving the training data report using at least one of minimization of drive tests (MDT) enhancement and vendor-to-vendor.

[0297] In some implementations, receiving the training data report using the MDT enhancement includes receiving the training data report from the model manager.

[0298] In some implementations, receiving the training data report using vendor-to-vendor includes receiving the training data report from the UE vendor using a proprietary protocol.

[0299] The Appendices are included as part of this application and provide additional details related to various aspects of the present disclosure.

[0300] The following example clauses are merely illustrative, and aspects thereof may be combined with aspects of other embodiments or teachings described herein without limitation.

[0301] 1. A method for wireless communication of a user equipment (UE), the method comprising:

[0302] Sending a training data request to a network entity;

[0303] receiving a data collection configuration message from the network entity in response to sending the training data request;

[0304] sending a data collection configuration acknowledgement (ACK) to the network entity in response to receiving the data collection configuration message;

[0305] A data collection process is performed based on the data collection configuration message.

[0306] 2. The method according to clause 1, further comprising:

[0307] receiving the training data request from a UE provider; and

[0308] One or more data are uploaded to the UE provider based on performing the data collection process.

[0309] 3. A method according to any of the preceding clauses, wherein the data collection configuration message includes a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and at least one of a process identifier (ID) regarding data collection.

[0310] 4. A method according to any preceding clause, wherein the process ID corresponds to a model ID registered with a machine learning function (MLF).

[0311] 5. A method according to any preceding clause, wherein the process ID corresponds to a meta ID for data collection, or a meta ID for data upload corresponding to one or more metadata is generated based on the process ID.

[0312] 6. The method of any preceding clause, wherein receiving the data collection configuration message further comprises receiving the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

[0313] 7. A method according to any preceding clause, wherein the one or more data corresponds to a UE report including a downlink raw channel matrix and a metadata identification (meta ID).

[0314] 8. A method according to any preceding clause, wherein the downlink raw channel matrix corresponds to a channel estimate based on a resource block (RB) index, a port index and a receive antenna index.

[0315] 9. A method according to any preceding clause, wherein the meta-ID includes a packet ID, a cell / carrier ID, a channel state information (CSI) reference signal (RS) resource ID, a list of one or more records of collected data, and at least one of a global navigation satellite system (GNSS).

[0316] 10. A method according to any preceding clause, wherein the list of one or more records includes a timestamp, one of a signal-to-noise ratio (SNR), a signal-to-interference plus noise ratio (SINR) or a reference signal received power (RSRP), a subcarrier spacing, and at least one of a Doppler / delay spread measurement.

[0317] 11. A method according to any preceding clause, wherein the format of the UE report including at least one of the downlink original channel matrices corresponds to a first frequency domain resolution, and the eigendirections of the downlink original channel matrix correspond to a second frequency domain resolution.

[0318] 12. The method according to any preceding clause, wherein performing the data collection process further comprises:

[0319] receiving a reference signal (RS) from the network entity in response to sending the data collection configuration ACK; and performing one or more measurements based on the RS.

[0320] 13. A method for wireless communication of a network entity, the method comprising:

[0321] receiving a training data request from a user equipment (UE);

[0322] sending a data collection configuration message to the UE in response to receiving the training data request;

[0323] receiving a data collection configuration acknowledgement (ACK) from the UE in response to sending the data collection configuration message; and

[0324] A data collection process is performed based on the data collection configuration message.

[0325] 14. The method of clause 13, wherein performing the data collection process further comprises sending a reference signal (RS) to the UE in response to receiving the data collection configuration ACK.

[0326] 15. A method according to clauses 13 to 14, wherein the data collection configuration message includes a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and at least one of a process identification (ID) regarding data collection.

[0327] 16. A method according to clauses 13 to 15, wherein the process ID corresponds to a model ID registered with a machine learning function (MLF) or corresponds to a meta ID used for data collection.

[0328] 17. A method as described in clauses 13 to 16, wherein sending the data collection configuration message further comprises sending the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

[0329] 18. A method for wireless communication of a user equipment (UE), the method comprising:

[0330] receiving a data collection configuration message from a network entity based on the training data request;

[0331] sending a data collection configuration acknowledgement (ACK) to the network entity in response to receiving the data collection configuration message;

[0332] executing a data collection process based on the data collection configuration message; and

[0333] Training data is reported between at least one of the network entity, a UE provider, and a network entity provider based on performing the data collection process.

[0334] 19. The method of clause 18, wherein reporting the training data further comprises reporting the training data using at least one of minimization of drive tests (MDT) enhancement, vendor-UE-vendor, and vendor-to-vendor.

[0335] 20. A method as set out in clauses 18 to 19, wherein reporting the training data using the MDT enhancement comprises sending the training data to the network entity.

[0336] 21. A method as described in clauses 18 to 20, wherein using the vendor-UE-vendor to report the training data comprises:

[0337] reporting the training data to the UE vendor; and

[0338] Data or a data address report is sent to the network entity.

[0339] 22. A method according to clauses 18 to 21, wherein the data collection configuration message includes a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and a process identification (ID) regarding data collection.

[0340] 23. A method according to clauses 18 to 22, wherein the process ID corresponds to a model ID registered with a machine learning function (MLF) or corresponds to a meta ID used for data collection.

[0341] 24. A method as described in clauses 18 to 23, wherein receiving the data collection configuration message further comprises receiving the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

[0342] 25. The method according to clauses 18 to 24, wherein performing the data collection process further comprises:

[0343] receiving a reference signal (RS) from the network entity in response to sending the data collection configuration ACK; and performing one or more measurements based on the RS.

[0344] 26. A method for wireless communication of a network entity, the method comprising:

[0345] receiving a request for training data from a network entity provider;

[0346] sending a data collection configuration message to a user equipment (UE) in response to receiving the training data request;

[0347] receiving a data collection configuration acknowledgement (ACK) from the UE in response to sending the data collection configuration message;

[0348] executing a data collection process based on the data collection configuration message; and

[0349] Training data is received or reported between the UE, UE provider, and network entity provider based on performing the data collection process.

[0350] 27. The method of clause 26, wherein reporting the training data further comprises reporting the training data using at least one of minimization of drive tests (MDT) enhancement, vendor-UE-vendor, and vendor-to-vendor.

[0351] 28. A method according to clauses 26 to 27, wherein reporting the training data using the MDT enhancement comprises:

[0352] receiving the training data from the UE; and

[0353] The training data is forwarded to the network entity provider.

[0354] 29. A method as described in clauses 26 to 28, wherein using the vendor-UE-vendor to report the training data comprises:

[0355] receiving data or a data address report from the UE; and

[0356] The data or the data address report is forwarded to the network entity provider.

[0357] 30. A method as described in clauses 26 to 29, wherein performing the data collection process further comprises sending a reference signal (RS) to the UE in response to receiving the data collection configuration ACK.

[0358] 31. An apparatus for wireless communication of a user equipment (UE), the apparatus comprising:

[0359] a memory storing computer-executable instructions; and

[0360] At least one processor coupled to the memory and configured to execute the computer-executable instructions to perform the method according to any of clauses 1 to 12.

[0361] 32. An apparatus for wireless communication of a user equipment (UE), the apparatus comprising means for performing a method according to any of clauses 1 to 12.

[0362] 33. A non-transitory computer readable medium storing computer executable code which, when executed by a processor of a user equipment (UE), causes the processor to perform the method of any of clauses 1 to 12.

[0363] 34. An apparatus for wireless communication of a network entity, the apparatus comprising:

[0364] a memory storing computer-executable instructions; and

[0365] At least one processor coupled to the memory and configured to execute the computer-executable instructions to perform the method according to any of clauses 13 to 17.

[0366] 35. An apparatus for wireless communication of a network entity, the apparatus comprising means for performing the method of any of clauses 13 to 17.

[0367] 36. A non-transitory computer readable medium storing computer executable code which, when executed by a processor of a network entity, causes the processor to perform the method of any one of clauses 13 to 17.

[0368] 37. An apparatus for wireless communication of a user equipment (UE), the apparatus comprising:

[0369] a memory storing computer-executable instructions; and

[0370] At least one processor coupled to the memory and configured to execute the computer-executable instructions to perform the method according to any of clauses 18 to 25.

[0371] 38. An apparatus for wireless communication of a user equipment (UE), the apparatus comprising means for performing a method according to any of clauses 18 to 25.

[0372] 39. A non-transitory computer-readable medium storing computer-executable code which, when executed by a processor of a user equipment (UE), causes the processor to perform the method of any of clauses 18 to 25.

[0373] 40. An apparatus for wireless communication of a network entity, the apparatus comprising:

[0374] a memory storing computer-executable instructions; and

[0375] At least one processor coupled to the memory and configured to execute the computer-executable instructions to perform the method according to any of clauses 26 to 30.

[0376] 41. An apparatus for wireless communication of a network entity, the apparatus comprising means for performing the method of any of clauses 26 to 30.

[0377] 42. A non-transitory computer readable medium storing computer executable code which, when executed by a processor of a network entity, causes the processor to perform the method of any of clauses 26 to 30.

[0378] 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 to conform to the full scope consistent with the language claims, wherein the elements mentioned in the singular are not intended to represent "one and only one", unless specifically so stated, but "one or more". 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 or having an advantage over other aspects. Unless otherwise specified, 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 multiple A, multiple B, or multiple 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 the elements of the various aspects described throughout the present disclosure that are or later will be known to one of ordinary skill in the art are expressly incorporated herein by reference and are intended to be covered by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is expressly recited in the claims. Words such as "module," "mechanism," "element," "device," etc. cannot replace the word "component." Therefore, no claim element will be understood to be a component plus function unless the element is expressly stated using the phrase "component for..."

[0379]

[0380]

[0381]

[0382]

[0383]

[0384]

[0385]

[0386]

[0387]

[0388]

[0389]

[0390]

[0391]

[0392]

[0393]

[0394]

[0395]

[0396]

[0397]

[0398]

[0399]

[0400]

[0401]

[0402]

[0403]

[0404]

[0405]

[0406]

[0407]

[0408]

[0409]

[0410]

[0411]

[0412]

[0413]

[0414]

[0415]

[0416]

[0417]

Claims

1. A method for wireless communication of a user equipment (UE), the method comprising: Sending a training data request to a network entity; receiving a data collection configuration message from the network entity in response to sending the training data request; sending a data collection configuration acknowledgement (ACK) to the network entity in response to receiving the data collection configuration message; A data collection process is performed based on the data collection configuration message.

2. The method according to claim 1, further comprising: receiving the training data request from a UE provider; as well as One or more data are uploaded to the UE provider based on performing the data collection process.

3. The method according to claim 1, wherein the data collection configuration message includes at least one of a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and a process identification (ID) regarding data collection.

4. The method of claim 3, wherein the process ID corresponds to a model ID registered with a machine learning function (MLF). 5 . The method according to claim 3 , wherein the process ID corresponds to a meta ID for data collection, or a meta ID for data upload corresponding to one or more metadata is generated based on the process ID.

6. The method of claim 1, wherein receiving the data collection configuration message further comprises receiving the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

7. The method of claim 1, wherein the one or more data corresponds to a UE report including a downlink raw channel matrix and a metadata identification (meta ID).

8. The method of claim 7, wherein the downlink original channel matrix corresponds to a channel estimate based on a resource block (RB) index, a port index, and a receive antenna index.

9. The method of claim 7, wherein the meta-ID comprises at least one of a packet ID, a cell / carrier ID, a channel state information (CSI) reference signal (RS) resource ID, a list of one or more records of collected data, and a global navigation satellite system (GNSS).

10. The method of claim 9, wherein the list of one or more records includes a timestamp, one of a signal-to-noise ratio (SNR), a signal-to-interference plus noise ratio (SINR), or a reference signal received power (RSRP), a subcarrier spacing, and at least one of a Doppler / delay spread measurement.

11. The method of claim 7, wherein the format of the UE report including at least one of the downlink original channel matrices corresponds to a first frequency domain resolution, and the eigendirections of the downlink original channel matrix correspond to a second frequency domain resolution.

12. The method of claim 1, wherein performing the data collection process further comprises: receiving a reference signal (RS) from the network entity in response to sending the data collection configuration ACK; as well as One or more measurements are performed based on the RS.

13. A method for wireless communication of a network entity, the method comprising: receiving a training data request from a user equipment (UE); sending a data collection configuration message to the UE in response to receiving the training data request; receiving a data collection configuration acknowledgement (ACK) from the UE in response to sending the data collection configuration message; as well as A data collection process is performed based on the data collection configuration message.

14. The method of claim 13, wherein performing the data collection process further comprises sending a reference signal (RS) to the UE in response to receiving the data collection configuration ACK.

15. The method of claim 13, wherein the data collection configuration message includes at least one of a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and a process identification (ID) regarding data collection.

16. The method of claim 15, wherein the process ID corresponds to a model ID registered with a machine learning function (MLF) or corresponds to a meta ID used for data collection.

17. The method of claim 13, wherein sending the data collection configuration message further comprises sending the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

18. A method for wireless communication of a user equipment (UE), the method comprising: receiving a data collection configuration message from a network entity based on the training data request; sending a data collection configuration acknowledgement (ACK) to the network entity in response to receiving the data collection configuration message; executing a data collection process based on the data collection configuration message; as well as Training data is reported between at least one of the network entity, a UE provider, and a network entity provider based on performing the data collection process.

19. The method of claim 18, wherein reporting the training data further comprises reporting the training data using at least one of minimization of drive tests (MDT) enhancement, vendor-UE-vendor, and vendor-to-vendor.

20. The method of claim 19, wherein reporting the training data using the MDT enhancement comprises sending the training data to the network entity.

21. The method of claim 19, wherein using the vendor-UE-vendor to report the training data comprises: reporting the training data to the UE vendor; as well as Data or a data address report is sent to the network entity.

22. The method of claim 18, wherein the data collection configuration message includes a reference signal (RS) list for data collection, an area for data collection, a time period for data collection, a network side configuration, a channel type, and a process identification (ID) regarding data collection.

23. The method of claim 22, wherein the process ID corresponds to a model ID registered with a machine learning function (MLF) or corresponds to a meta ID used for data collection.

24. The method of claim 18, wherein receiving the data collection configuration message further comprises receiving the data collection configuration message as at least one of a radio resource control (RRC) reconfiguration message or an information element in a new signaling procedure.

25. The method of claim 18, wherein performing the data collection process further comprises: receiving a reference signal (RS) from the network entity in response to sending the data collection configuration ACK; as well as One or more measurements are performed based on the RS.

26. A method for wireless communication of a network entity, the method comprising: receiving a request for training data from a network entity provider; sending a data collection configuration message to a user equipment (UE) in response to receiving the training data request; receiving a data collection configuration acknowledgement (ACK) from the UE in response to sending the data collection configuration message; executing a data collection process based on the data collection configuration message; as well as Training data is received or reported between the UE, UE provider, and network entity provider based on performing the data collection process.

27. The method of claim 26, wherein reporting the training data further comprises reporting the training data using at least one of minimization of drive tests (MDT) enhancement, vendor-UE-vendor, and vendor-to-vendor.

28. The method of claim 27, wherein reporting the training data using the MDT enhancement comprises: receiving the training data from the UE; as well as The training data is forwarded to the network entity provider.

29. The method of claim 27, wherein using the vendor-UE-vendor to report the training data comprises: receiving data or a data address report from the UE; as well as The data or the data address report is forwarded to the network entity provider.

30. The method of claim 26, wherein performing the data collection process further comprises sending a reference signal (RS) to the UE in response to receiving the data collection configuration ACK.

Images