Remote offline sequential network node encoder training

Abstract

This disclosure provides systems, methods, and devices for wireless communication that support remote offline sequential network node encoder training. In a first aspect, a method of wireless communication includes receiving training information for a first encoder of a first network node from a second network node, where the training information includes first input information for a second encoder of the second network node and output information corresponding to the first input information; and training the first encoder of the first network node using the training information. Other aspects and features are also claimed and described.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of international patent application No. PCT / CN2022 / 111368, filed on August 10, 2022, entitled “REMOTE OFFLINE SEQUENTIAL NETWORKNODE ENCODER TRAINING”, the entire text of which is expressly incorporated herein by reference. Technical Field

[0003] Aspects of the present disclosure relate generally to wireless communication systems, and more particularly to encoder training for wireless communication. Some features may enable and provide improved communications, including remote offline sequential machine learning encoder training. Background Art

[0004] Wireless communication networks are widely deployed to provide various communication services such as voice, video, packet data, messaging, broadcast, etc. These wireless networks may be multiple-access networks capable of supporting multiple users by sharing the available network resources. Such networks may be multiple-access networks capable of supporting communication for multiple users by sharing the available network resources.

[0005] A wireless communication network may include several components. These components may include wireless communication devices, such as a base station (or Node B) that may support communication of several user equipments (UEs). A UE may communicate with a base station via a downlink and an uplink. A downlink (or forward link) refers to a communication link from a base station to a UE, and an uplink (or reverse link) refers to a communication link from a UE to a base station.

[0006] The base station may send data and control information to the UE on the downlink, or receive data and control information from the UE on the uplink. On the downlink, the transmission from the base station may encounter interference caused by transmissions from neighboring base stations or other wireless radio frequency (RF) transmitters. On the uplink, the transmission from the UE may encounter interference from other UEs communicating with neighboring base stations or from uplink transmissions of other wireless RF transmitters. This interference may degrade performance on both the downlink and uplink.

[0007] As the demand for mobile broadband access continues to grow, the potential for interference and congested networks grows with more UEs accessing long-range wireless communication networks and more short-range wireless systems deployed in communities. Research and development continues to advance wireless technologies to not only meet the growing demand for mobile broadband access, but also to improve and enhance the user experience with mobile communications. Summary of the invention

[0008] The following summarizes some aspects of the present disclosure to provide a basic understanding of the technology discussed. This summary is not an exhaustive overview of all the expected features of the present disclosure, and is neither intended to identify the key or important elements of all aspects of the present disclosure, nor to delineate the scope of any or all aspects of the present disclosure. The sole purpose of this summary is to present some concepts of one or more aspects of the present disclosure in a summarized form as a prelude to more specific embodiments presented later.

[0009] In one aspect of the present disclosure, a method for wireless communication includes: receiving training information for a first encoder of a first network node from a second network node, wherein the training information includes first input information for a second encoder of the second network node and output information corresponding to the first input information, such as output information generated by the second encoder of the second network node based on the first input information; and using the training information to train the first encoder of the first network node.

[0010] In one aspect of the present disclosure, a method for wireless communication includes: generating training information, wherein the training information includes first input information for a first encoder of a first network node and output information generated by the first encoder based on the first input information; and sending the training information to a second network node for training a second encoder of the second network node.

[0011] In an additional aspect of the present disclosure, an apparatus includes at least one processor and a memory coupled to the at least one processor. The at least one processor is configured to: receive training information for a first encoder of a first network node from a second network node, wherein the training information includes first input information for a second encoder of the second network node and output information corresponding to the first input information, such as output information generated by the second encoder of the second network node based on the first input information; and use the training information to train the first encoder of the first network node.

[0012] In an additional aspect of the present disclosure, an apparatus includes at least one processor and a memory coupled to the at least one processor. The at least one processor is configured to: generate training information, wherein the training information includes first input information for a first encoder of a first network node and output information generated by the first encoder based on the first input information; and send the training information to a second network node for training a second encoder of the second network node.

[0013] In an additional aspect of the present disclosure, an apparatus includes: a component for receiving training information for a first encoder of a first network node from a second network node, wherein the training information includes first input information for a second encoder of the second network node and output information corresponding to the first input information, such as output information generated by the second encoder of the second network node based on the first input information; and a component for training the first encoder of the first network node using the training information.

[0014] In an additional aspect of the present disclosure, an apparatus includes: a component for generating training information, wherein the training information includes first input information for a first encoder of a first network node and output information generated by the first encoder based on the first input information; and a component for sending the training information to a second network node for training a second encoder of the second network node.

[0015] In additional aspects of the present disclosure, a non-transitory computer-readable medium stores instructions that, when executed by a processor, cause the processor to perform the operations described herein.

[0016] In additional aspects of the present disclosure, a computer program comprises instructions that, when executed by a processor, cause the processor to perform the operations described herein.

[0017] The features and technical advantages of examples according to the present disclosure have been outlined quite extensively above so that the following specific embodiments may be better understood. Additional features and advantages will be described below. The disclosed concepts and specific examples may be easily used as a basis for modifying or designing other structures for the same purpose of achieving the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. When considered in conjunction with the accompanying drawings, the characteristics of the concepts disclosed herein (both their organization and methods of operation) and the associated advantages will be better understood according to the following description. Each of the figures in the accompanying drawings is provided for the purpose of illustration and description, and not as a definition of limitations to the claims.

[0018] Although various aspects and specific implementations are described in this application by the illustration of some examples, it will be understood by those skilled in the art that additional specific implementations and use cases may be generated in many different arrangements and scenarios. The innovation described herein can be implemented across many different platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, aspects and / or uses can be generated via integrated chip specific implementations and other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchase equipment, medical equipment, devices that enable artificial intelligence (AI), etc.). Although some examples may or may not specifically point to use cases or applications, the applicability of a wide range of described innovations may occur. The scope of specific implementations can be in the range from chip-level or modular components to non-modular, non-chip-level specific implementations, and further to the scope of aggregated, distributed or original equipment manufacturer (OEM) devices or systems in conjunction with one or more aspects of the described innovations. In some practical environments, the equipment in conjunction with the various aspects and features described may also necessarily include additional components and features for implementing and practicing the various aspects claimed and described. For example, the transmission and reception of wireless signals necessarily include multiple components for analog and digital purposes (e.g., hardware components including antennas, radio frequency (RF) chains, power amplifiers, modulators, buffers, processors, interleavers, adders / summers, etc.). The innovations described herein are intended to be practiced in a variety of devices, chip-level components, systems, distributed arrangements, end-user devices, etc., having different sizes, shapes, and configurations. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] A further understanding of the nature and advantages of the present disclosure may be achieved by reference to the following drawings. In the drawings, similar components or features may have the same reference label. In addition, various components of the same type may be distinguished by adding a dash and a second label to distinguish between similar components after the reference label. If only the first reference label is used in the specification, the description applies to any of the similar components having the same first reference label, regardless of the second reference label.

[0020] Figure 1 is a block diagram illustrating details of an example wireless communication system in accordance with one or more aspects.

[0021] Figure 2 is a block diagram illustrating an example of a base station and a user equipment (UE) according to one or more aspects.

[0022] Figure 3 is a block diagram illustrating an example wireless communication system that supports remote offline sequential network node encoder training in accordance with one or more aspects.

[0023] Figure 4 is a timing diagram illustrating an example wireless communication system that supports remote offline sequential network node encoder training in accordance with one or more aspects.

[0024] Figure 5 is a flow chart illustrating an example process for supporting remote offline sequential network node encoder training according to one or more aspects.

[0025] Figure 6 is a flow chart illustrating an example process for supporting remote offline sequential network node encoder training according to one or more aspects.

[0026] Figure 7 is a block diagram of an example UE-side server supporting remote offline sequential network node encoder training according to one or more aspects.

[0027] Figure 8 is a block diagram of an example base station side server supporting remote offline sequential network node encoder training according to one or more aspects.

[0028] The same reference numbers and designations in different drawings indicate the same elements. DETAILED DESCRIPTION

[0029] The specific embodiments described below in conjunction with the accompanying drawings are intended as descriptions of various configurations and are not intended to limit the scope of the present disclosure. Instead, the specific embodiments include specific details for providing a thorough understanding of the subject matter of the present invention. It will be apparent to those skilled in the art that these specific details are not required in every case, and in some instances, well-known structures and components are shown in block diagram form for clarity of presentation.

[0030] The present disclosure as a whole relates to providing or participating in authorized shared access between two or more wireless devices in one or more wireless communication systems (also referred to as wireless communication networks). In various specific implementations, the various techniques and devices can be used in wireless communication networks, such as code division multiple access (CDMA) networks, time division multiple access (TDMA) networks, frequency division multiple access (FDMA) networks, orthogonal FDMA (OFDMA) networks, single carrier FDMA (SC-FDMA) networks, LTE networks, GSM networks, fifth generation (5G) or new radio (NR) networks (sometimes referred to as "5G NR" networks, systems or devices) and other communication networks. As described herein, the terms "network" and "system" can be used interchangeably.

[0031] A CDMA network may implement, for example, a radio technology such as Universal Terrestrial Radio Access (UTRA), cdma2000, etc. UTRA includes Wideband-CDMA (W-CDMA) and Low Chip Rate (LCR). CDMA2000 covers IS-2000, IS-95, and IS-856 standards.

[0032] For example, a TDMA network may implement a radio technology such as the Global System for Mobile Communications (GSM). The Third Generation Partnership Project (3GPP) defines the standard for the GSM EDGE (Enhanced Data Rate for GSM Evolution) Radio Access Network (RAN) (also known as GERAN). GERAN is the radio component of the network of GSM / EDGE together with connecting base stations (e.g., Ater and Abis interfaces) and base station controllers (A interfaces, etc.). The radio access network represents a component of the GSM network through which telephone calls and packet data are routed from the public switched telephone network (PSTN) and the Internet to subscriber phones (also known as user terminals or user equipment (UE)) and from subscriber phones to the PSTN and the Internet. The network of a mobile phone operator may include one or more GERANs, which may be coupled to the UTRAN in the case of a UMTS / GSM network. Additionally, the operator network may also include one or more LTE networks, or one or more other networks. Various network types may use different radio access technologies (RATs) and RANs.

[0033] OFDMA network can realize radio technology such as Evolved UTRA (E-UTRA), Institute of Electrical and Electronics Engineers (IEEE) 802.11, IEEE 802.16, IEEE 802.20, flash-OFDM, etc. UTRA, E-UTRA and GSM are part of Universal Mobile Telecommunication System (UMTS). Specifically, Long Term Evolution (LTE) is a UMTS version using E-UTRA. UTRA, E-UTRA, GSM, UMTS and LTE are described in documents provided by an organization named "3rd Generation Partnership Project" (3GPP), and cdma2000 is described in documents from an organization named "3rd Generation Partnership Project 2" (3GPP2). These radio technologies and standards are known or under development. For example, 3GPP is a collaboration between telecommunication association groups to define a globally applicable third generation (3G) mobile phone specification. 3GPP LTE is a 3GPP plan to improve the UMTS mobile phone standard. 3GPP can define the specifications of next generation mobile networks, mobile systems and mobile devices. The present disclosure may describe certain aspects with reference to LTE, 4G or 5G NR technology; however, the description is not intended to be limited to a particular technology or application, and one or more aspects described with reference to one technology may be understood to be applicable to another technology. Additionally, one or more aspects of the present disclosure may relate to shared access to wireless spectrum between networks using different radio access technologies or radio air interfaces.

[0034] 5G networks are expected to have diverse deployments, diverse spectrum, and diverse services and devices that can be implemented using a unified air interface based on OFDM. To achieve these goals, in addition to developing new radio technologies for 5G NR networks, further enhancements to LTE and LTE-A are also being considered. 5G NR will be able to scale to provide coverage (1) to massive Internet of Things (IoT), with ultra-high density (e.g., about 1M nodes / km 2 ), ultra-low complexity (e.g., about 10s of bits / sec), ultra-low power consumption (e.g., about 10+ years of battery life), and deep coverage with the ability to reach challenging locations; (2) including mission-critical control with strong security to protect sensitive personal, financial, or classified information, ultra-high reliability (e.g., about 99.9999% reliability), ultra-low latency (e.g., about 1 millisecond (ms)), and users with a wide range of mobility or lack of mobility; and (3) providing services with enhanced mobile broadband (including extremely high capacity (e.g., about 10Tbps / km 2 ), extremely high data rates (e.g., multi-Gbps rates, 100+Mbps user experience rates), and deep awareness coverage with advanced discovery and optimization.

[0035] Devices, networks, and systems may be configured to communicate via one or more portions of the electromagnetic spectrum. The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency ranges designated FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz). Frequencies between FR1 and FR2 are typically referred to as mid-band frequencies. Although a portion of FR1 is greater than 6 GHz, FR1 is typically (interchangeably) referred to as the "below 6 GHz" band in various documents and articles. Similar naming issues sometimes arise for FR2, which is typically (interchangeably) referred to as the "millimeter wave" (mmWave) band in documents and articles, although it is different from the extremely high frequency (EHF) band (30 GHz-300 GHz) identified as the "mmWave" band by the International Telecommunication Union (ITU).

[0036] In view of the above aspects, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" or the like is used in this document, it can broadly represent frequencies that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that if used in this document, the term "mmWave" or the like can broadly represent frequencies that may include mid-band frequencies, may be within FR2, or may be within the EHF band.

[0037] 5G NR devices, networks, and systems can be implemented using optimized OFDM-based waveform features. These features may include scalable parameter sets and transmission time intervals (TTIs); a common flexible framework that efficiently multiplexes services and features using dynamic, low-latency time division duplex (TDD) designs or frequency division duplex (FDD) designs; and advanced wireless technologies such as massive multiple-input multiple-output (MIMO), robust mmWave transmission, advanced channel decoding, and device-centric mobility. The scalability of parameter sets in 5G NR and the scaling of subcarrier spacing can efficiently address various services operating across different spectrums and different deployments. For example, in various outdoor and macro coverage deployments of less than 3GHz FDD or TDD implementations, the subcarrier spacing may appear at 15kHz, such as over bandwidths of 1MHz, 5MHz, 10MHz, 20MHz, etc. For various other outdoor and small cell coverage deployments of TDD greater than 3GHz, the subcarrier spacing may appear at 30kHz over 80MHz / 100MHz bandwidth. For various other indoor broadband implementations, using TDD on the unlicensed portion of the 5GHz band, the subcarrier spacing may occur at 60kHz over a 160MHz bandwidth. Finally, for various deployments transmitting over mmWave components at 28GHz TDD, the subcarrier spacing may occur at 120kHz over a 500MHz bandwidth.

[0038] 5G NR's scalable parameter sets facilitate scalable TTIs for diverse latency and quality of service (QoS) requirements. For example, shorter TTIs can be used for low latency and high reliability, while longer TTIs can be used for higher spectral efficiency. Efficient multiplexing of long and short TTIs allows transmission to start on symbol boundaries. 5G NR also anticipates a self-contained integrated subframe design where uplink or downlink scheduling information, data, and acknowledgments are in the same subframe. The self-contained integrated subframe supports communications in unlicensed or contention-based shared spectrum, and adaptive uplink or downlink can be flexibly configured on a per-cell basis to dynamically switch between uplink and downlink to meet current business needs.

[0039] For clarity, certain aspects of the devices and techniques may be described below with reference to example 5G NR implementations or in a 5G-centric manner, and 5G terminology may be used as illustrative examples in portions of the description below; however, the description is not intended to be limited to 5G applications.

[0040] Furthermore, it should be understood that in operation, a wireless communication network adapted according to the concepts herein can operate using any combination of licensed spectrum or unlicensed spectrum depending on load and availability. Therefore, it will be apparent to one of ordinary skill in the art that the systems, devices, and methods described herein can be applied to other communication systems and applications beyond the specific examples provided.

[0041] Although various aspects and specific implementations are described in this application by the illustration of some examples, it will be understood by those skilled in the art that additional specific implementations and use cases may be generated in many different arrangements and scenarios. The innovation described herein can be implemented across many different platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, specific implementation or use can be implemented via integrated chip specific implementation or other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail equipment or purchasing equipment, medical equipment, AI-enabled devices, etc.). Although some examples may or may not specifically point to use cases or applications, the applicability of a wide range of described innovations may occur. The scope of specific implementation can range from chip-level or modular components to non-modular, non-chip-level specific implementations, and further to aggregated, distributed, or original equipment manufacturer (OEM) devices or systems containing one or more described aspects. In some practical environments, the equipment in combination with the various aspects and features described may also necessarily include additional components and features for implementing and practicing the various aspects claimed and described. It is intended that the innovations described herein may be implemented in a wide variety of embodiments of different sizes, shapes, and configurations, including both large and small devices, chip-level components, multi-component systems (e.g., radio frequency (RF) chains, communication interfaces, processors), distributed arrangements, end-user devices, and the like.

[0042] Figure 1 1 is a block diagram illustrating details of an example wireless communication system according to one or more aspects. The wireless communication system may include a wireless network 100. The wireless network 100 may, for example, include a 5G wireless network. As will be appreciated by those skilled in the art, Figure 1 Components appearing in are likely to have related corresponding components in other network arrangements (including, for example, cellular-style network arrangements and non-cellular-style network arrangements (e.g., device-to-device or peer-to-peer or ad hoc network arrangements, etc.)).

[0043] Figure 1The illustrated wireless network 100 includes many base stations 105 and other network entities. A base station may be a station that communicates with a UE, and may also be referred to as an evolved Node B (eNB), a next generation eNB (gNB), an access point, etc. Each base station 105 may provide communication coverage for a specific geographic area. In 3GPP, the term "cell" may refer to a specific geographic coverage area of ​​a base station or a base station subsystem serving the coverage area, depending on the context in which the term is used. In the specific implementation of the wireless network 100 herein, the base station 105 may be associated with the same operator or different operators (e.g., the wireless network 100 may include multiple operator wireless networks). Additionally, in the specific implementation of the wireless network 100 herein, the base station 105 may provide wireless communication using one or more frequencies (e.g., one or more frequency bands in a licensed spectrum, an unlicensed spectrum, or a combination thereof) in the same frequency as an adjacent cell. In some examples, a separate base station 105 or UE 115 may be operated by more than one network operating entity. In other examples, each base station 105 and UE 115 may be operated by a single network operating entity.

[0044] A base station may provide communication coverage for a macro cell or a small cell (e.g., a pico cell or a femto cell), or other types of cells. A macro cell generally covers a relatively large geographic area (e.g., several kilometers in radius) and may allow unrestricted access by UEs with a service subscription with a network provider. A small cell (such as a pico cell) will generally cover a relatively small geographic area and may allow unrestricted access by UEs with a service subscription with a network provider. A small cell (such as a femto cell) will generally also cover a relatively small geographic area (e.g., a home), and in addition to unrestricted access, may also provide restricted access by UEs associated with the femto cell (e.g., UEs in a closed subscriber group (CSG), UEs of users in a home, etc.). A base station for a macro cell may be referred to as a macro base station. A base station for a small cell may be referred to as a small cell base station, a pico base station, a femto base station, or a home base station. In Figure 1 In the example shown, base stations 105d and 105e are conventional macro base stations, while base stations 105a-105c are macro base stations implemented using one of 3-dimensional (3D), full-dimensional (FD) or massive MIMO. Base stations 105a-105c use their higher-dimensional MIMO capabilities to employ 3D beamforming in elevation and azimuth beamforming to increase coverage and capacity. Base station 105f is a small cell base station, which can be a home node or a portable access point. The base station can support one or more (e.g., two, three, four, etc.) cells.

[0045] Wireless network 100 may support synchronous or asynchronous operation. For synchronous operation, base stations may have similar frame timings, and transmissions from different base stations may be approximately aligned in time. For asynchronous operation, base stations may have different frame timings, and transmissions from different base stations may not be aligned in time. In some cases, the network may be enabled or configured to handle dynamic switching between synchronous or asynchronous operation.

[0046] UE 115 is dispersed throughout the wireless network 100, and each UE may be stationary or mobile. It should be understood that, although in the standards and specifications promulgated by 3GPP, mobile devices are generally referred to as UEs, such devices may be additionally or otherwise referred to as mobile stations (MS), subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals (AT), mobile terminals, wireless terminals, remote terminals, mobile phones, terminals, user agents, mobile clients, clients, gaming devices, augmented reality devices, vehicle components, vehicle devices or vehicle modules or some other suitable terminology by those skilled in the art. In this document, a "mobile" device or UE does not necessarily have the ability to move and may be fixed. Some non-limiting examples of mobile devices (for example) may include one or more specific implementations of UE 115, including mobile phones, cellular phones, smart phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, laptop computers, personal computers (PCs), notebooks, netbooks, smart books, tablet computers, and personal digital assistants (PDAs). The mobile device may additionally be an IoT or "Internet of Everything" (IoE) device, such as a car or other transportation vehicle, a satellite radio, a global positioning system (GPS) device, a global navigation satellite system (GNSS) device, a logistics controller, a drone, a multi-rotor helicopter, a quad-rotor helicopter, a smart energy or security device, a solar panel or solar array, city lighting, tap water or other infrastructure; industrial automation and enterprise equipment; consumer and wearable devices, such as glasses, wearable cameras, smart watches, health or fitness trackers, mammal implantable devices, gesture tracking devices, medical devices, digital audio players (e.g., MP3 players), cameras, game consoles, etc.; and digital home or smart home devices, such as home audio, video and multimedia devices, appliances, sensors, vending machines, smart lighting, home security systems, smart meters, etc. In one aspect, the UE may be a device including a universal integrated circuit card (UICC). In another aspect, the UE may be a device that does not include a UICC. In some aspects, a UE that does not include a UICC may also be an IoE device. Figure 1The UEs 115a-115d of the specific implementation illustrated in the figure are examples of mobile smart phone type devices accessing the wireless network 100. The UE may also be a machine specifically configured to implement connected communications, including machine type communications (MTC), enhanced MTC (eMTC), narrowband IoT (NB-IoT), and the like. Figure 1 The illustrated UEs 115e - 115k are examples of various machines that access the wireless network 100 and are configured for communication.

[0047] A mobile device, such as UE 115, may be able to communicate with any type of base station, whether macro, pico, femto, relay, etc. Figure 1 In the present invention, the communication link (represented as a lightning beam) indicates the wireless transmission between the UE and the serving base station (which is the base station designated to serve the UE on the downlink and / or uplink) and / or the expected transmission between the base stations and / or the backhaul transmission between the base stations. The UE can operate as a base station or other network node in some scenarios. The backhaul communication between the base stations of the wireless network 100 can be performed using a wired or wireless communication link.

[0048] In operation at the wireless network 100, the base stations 105a-105c may use, among other things, 3D beamforming and collaborative spatial techniques such as coordinated multipoint (CoMP) or multi-connectivity to serve the UEs 115a and 115b. The macro base station 105d may perform backhaul communications with the base stations 105a-105c and the small cell (base station 105f). The macro base station 105d may also transmit multicast services subscribed to and received by the UEs 115c and 115d. Such multicast services may include mobile television or streaming video, or may include other services for providing community information, such as weather emergencies or alerts, such as Amber alerts or gray alerts.

[0049] The wireless network 100 of a specific implementation can support mission-critical communications with ultra-reliable and redundant links for mission-critical devices such as UE 115e as a drone. The redundant communication links with UE 115e include links from macro base stations 105d and 105e and small cell base station 105f. Other machine-type devices such as UE 115f (thermometer), UE 115g (smart meter), and UE 115h (wearable device) can communicate directly with base stations such as small cell base station 105f and macro base station 105e through the wireless network 100, or in a multi-hop configuration by communicating with another user device that relays its information to the network, such as UE 115f communicating temperature measurement information to smart meter UE 115g, which then reports it to the network through small cell base station 105f. The wireless network 100 may also provide additional network efficiency through dynamic, low-latency TDD communications or low-latency FDD communications (eg, in a vehicle-to-vehicle (V2V) mesh network between UEs 115i-115k communicating with a macro base station 105e).

[0050] The wireless network 100 may also include one or more connected servers, such as servers 120a-120c. In some embodiments, the servers 120a-120c may be connected wirelessly or otherwise, such as via a wired connection. Servers 120a and 120c may be UE-side servers and may communicate with one or more UEs, such as UEs 115c-115d. For example, server 120a may be a UE-side server associated with a first UE vendor, and may communicate with one or more UEs 115c associated with the first UE vendor. Server 120c may be a second UE-side server associated with a second UE vendor different from the first UE vendor, and may communicate with one or more UEs 115d associated with the second UE vendor. Server 120c may have similar functionality as server 120a, such as with respect to Figures 3 to 5 and Figure 7Described. Server 120b can be a base station side server and can communicate with one or more base stations (such as base station 105d). Servers 120a-120c can communicate with each other. Servers 120a-120c can communicate using various wireless or wired technologies (such as Ethernet, Wi-Fi or cellular technologies). Servers 120a and 120c can each host and train encoders for one or more UEs to use when encoding information (such as channel state feedback sensed from reference signals sent by one or more base stations). Server 120b can host and train decoders for one or more base stations to use when decoding information. It should be noted that the present disclosure is not limited to this. For example, server 120b can also host and train encoders for one or more base stations to use when encoding information, and servers 120a and 120c can also host and train decoders for one or more UEs to use when decoding information. Servers 120a-120c can use one or more machine learning (ML) algorithms to train hosted encoders and decoders.

[0051] In some embodiments, servers 120a-120b and 120b-120c can work together to train encoders for use by UEs when encoding information for sending to a base station. For example, server 120a can provide input information received by server 120a from one or more UEs to server 120b, such as sensed channel state feedback. Server 120b can use the received input information to train decoders and encoders, and can provide server 120a with training information used by server 120a when training encoders to be pushed to one or more UEs. Server 120a can use the training information to train encoders (which can include generating encoder parameters), and can send encoder parameters for trained encoders to one or more UEs (such as UE115c or 115d) for use when encoding information to be sent to a base station. In some embodiments, server 120b can also receive input information from server 120c, and can use input information from both server 120a and server 120c to train encoders. Server 120b may then generate training information using input information from both servers 120a and 120c, and may send the training information to both servers 120a and 120c. Servers 120a and 120c may then each use the received input information to train an encoder (which may include generating encoder parameters), and may send one or more encoder parameters to the connected UE. Thus, the training information generated by base station side server 120b may be generated for one or more UE side servers using input information from one or more UE side servers.

[0052] Figure 2 1 is a block diagram illustrating an example of a base station 105 and a UE 115 according to one or more aspects. The base station 105 and the UE 115 may be Figure 1 For a restricted association scenario (as described above), base station 105 may be any one of the base stations in the UE and one of the UEs. Figure 1 The small cell base station 105f in the example of FIG. 105 and the UE 115 may be a UE 115c or 115d operating in the service area of ​​the base station 105f, which will be included in the list of accessible UEs of the small cell base station 105f in order to access the small cell base station 105f. The base station 105 may also be some other type of base station. Figure 2 As shown in FIG. 1 , the base station 105 may be equipped with antennas 234a through 234t and the UE 115 may be equipped with antennas 252a through 252r for facilitating wireless communication.

[0053] At the base station 105, the transmit processor 220 may receive data from the data source 212 and control information from the controller 240 (such as a processor). The control information may be for a physical broadcast channel (PBCH), a physical control format indicator channel (PCFICH), a physical hybrid ARQ (automatic repeat request) indicator channel (PHICH), a physical downlink control channel (PDCCH), an enhanced physical downlink control channel (EPDCCH), an MTC physical downlink control channel (MPDCCH), etc. The data may be for a physical downlink shared channel (PDSCH), etc. Additionally, the transmit processor 220 may process (e.g., encode and symbol map) the data and the control information, respectively, to obtain data symbols and control symbols. The transmit processor 220 may also generate reference symbols, such as for a primary synchronization signal (PSS) and a secondary synchronization signal (SSS), and a cell-specific reference signal. The transmit (TX) MIMO processor 230 may perform spatial processing (e.g., pre-coding) on ​​data symbols, control symbols, or reference symbols, if applicable, and may provide an output symbol stream to modulators (MODs) 232a to 232t. For example, the spatial processing performed on the data symbols, control symbols, or reference symbols may include pre-coding. Each modulator 232 may process a corresponding output symbol stream (e.g., for OFDM, etc.) to obtain an output sample stream. Additionally or alternatively, each modulator 232 may process the output sample stream (e.g., analog-convert, amplify, filter, and up-convert it) to obtain a downlink signal. The downlink signals from modulators 232a to 232t may be transmitted via antennas 234a to 234t, respectively.

[0054] At the UE 115, antennas 252a to 252r may receive downlink signals from the base station 105 and may provide received signals to demodulators (DEMODs) 254a to 254r, respectively. Each demodulator 254 may condition (e.g., filter, amplify, downconvert, and digitize) a corresponding received signal to obtain input samples. Each demodulator 254 may further process the input samples (e.g., for OFDM, etc.) to obtain received symbols. The MIMO detector 256 may obtain received symbols from the demodulators 254a to 254r, perform MIMO detection on the received symbols when necessary, and provide detected symbols. The receive processor 258 may process (e.g., demodulate, deinterleave, and decode) the detected symbols, provide decoded data for the UE 115 to the data sink 260, and provide decoded control information to the controller 280 (e.g., a processor).

[0055] On the uplink, at the UE 115, the transmit processor 264 may receive and process data from a data source 262 (e.g., for a physical uplink shared channel (PUSCH)) and control information from a controller 280 (e.g., for a physical uplink control channel (PUCCH)). Additionally, the transmit processor 264 may also generate reference symbols for reference signals. The symbols from the transmit processor 264 may be pre-decoded by the TX MIMO processor 266, if necessary, further processed by the modulators 254a through 254r (e.g., for SC-FDM, etc.), and transmitted to the base station 105. At the base station 105, the uplink signal from the UE 115 may be received by the antenna 234, processed by the demodulator 232, detected by the MIMO detector 236, if necessary, and further processed by the receive processor 238 to obtain decoded data and control information transmitted by the UE 115. Receive processor 238 may provide the decoded data to a data sink 239 and the decoded control information to controller 240 .

[0056] The controllers 240 and 280 may direct the operation at the base station 105 and the UE 115, respectively. The controller 240 or other processors and modules at the base station 105 or the controller 280 or other processors and modules at the UE 115 may perform or direct the execution of various processes for the techniques described herein, such as to perform or direct the execution of various processes for the techniques described herein. Figures 4 to 6 The illustrated execution or other processes for the techniques described herein. Memories 242 and 282 may store data and program codes for base station 105 and UE 115, respectively. Scheduler 244 may schedule UEs for data transmission on the downlink or uplink.

[0057] In some cases, the UE 115 and the base station 105 may operate in a shared radio spectrum band, which may include licensed or unlicensed (e.g., contention-based) spectrum. In the unlicensed frequency portion of the shared radio spectrum band, the UE 115 or the base station 105 may traditionally perform a medium sensing procedure to compete for access to the spectrum. For example, the UE 115 or the base station 105 may perform a listen-before-talk or listen-before-send (LBT) procedure (such as a clear channel assessment (CCA)) before communicating to determine whether the shared channel is available. In some specific implementations, the CCA may include an energy detection procedure to determine whether there are any other active transmissions. For example, the device may infer that a change in the received signal strength indicator (RSSI) of the power meter indicates that the channel is occupied. Specifically, a signal power concentrated in a certain bandwidth and exceeding a predetermined noise floor may indicate another wireless transmitter. CCA may also include detection of a specific sequence indicating the use of the channel. For example, another device may send a specific preamble before sending a data sequence. In some cases, the LBT procedure may include the wireless node adjusting its own backoff window based on the amount of energy detected on the channel or acknowledgement / negative acknowledgement (ACK / NACK) feedback for its own transmitted packets (as a manifestation of a collision).

[0058] UEs and base stations designed, sold, and maintained by different vendors may implement different encoders and decoders for encoding and decoding information, such as channel state feedback information. The UE-side server may train an encoder for one or more UEs to implement offline, such as by applying one or more ML algorithms to train the encoder. The UE-side server may, for example, be operated and maintained by a specific UE vendor, and may determine encoder parameters for sending to one or more UEs associated with the specific UE vendor. In some cases, the one or more UEs whose encoders are being trained may send input information, such as channel state feedback information, to the first network node.

[0059] The UE-side server may send such input information to a base station-side server (such as a base station supplier-side server). The base station-side server may train a decoder for one or more base stations to implement offline, such as by applying one or more ML algorithms to train the decoder. The base station-side server may, for example, be operated and maintained by a specific base station supplier, and may determine decoder parameters for pushing to one or more base stations associated with the specific base station supplier. In some cases, one or more base stations whose encoders are being trained may send input information, such as channel state feedback information, to the base station-side server. The base station-side server may train a decoder for one or more base stations offline, such as by applying one or more ML algorithms to train the decoder. The base station-side server may also supervise the training of the encoder by one or more UE-side servers. For example, the base station-side server may receive input information from one or more UE-side servers or from another source, and may use the input information to train both the encoder and the decoder. For example, such training may include applying an ML algorithm to train an encoder / decoder pair to effectively encode and decode information. The base station-side server may then encode the received input information using the trained encoder to generate training information. The training information may include both the input information and the output of the encoder (such as the encoded input information). The base station side server may send training information to one or more UE side servers, and the one or more UE side servers may use the training information to perform offline training of the encoder of each corresponding UE side server. Such training may generate one or more encoder parameters for one or more UEs to use when encoding information, and these encoder parameters may be sent by one or more UE side servers to one or more UEs. It should be noted that the training information including both the input information and the output of the encoder is a specific example, and training information having other types or forms may be applied to the present disclosure.

[0060] In some embodiments, the UE-side server may train a decoder implemented by one or more UEs offline, such as by applying one or more ML algorithms to train the decoder. The UE-side server may determine decoder parameters for sending to one or more UEs. In some cases, one or more UEs whose decoders are being trained may send input information to the UE-side server. In some cases, the UE-side server may use input information received from one or more UEs to train the decoder. The UE-side server may send such input information to the base station-side server. The base station-side server may train an encoder implemented by one or more base stations offline, such as by applying one or more ML algorithms to train the encoder. The base station-side server may also supervise the training of the decoder by one or more UE-side servers. For example, the base station-side server may receive input information from one or more UE-side servers or from another source, and may use the input information to train both the encoder and the decoder. The base station-side server may send training information to one or more UE-side servers, and one or more UE-side servers may use the training information to perform offline training of the decoder of each corresponding UE-side server. This training may generate one or more decoder parameters for one or more UEs to use when decoding information, and these decoder parameters may be sent to one or more UEs by one or more UE-side servers.

[0061] Training an encoder used by one or more UEs may facilitate better interoperability between the one or more UEs and one or more base stations. For example, a UE may generate channel state feedback (CSF) information and may encode the CSF information. In some cases, such encoding may generate compressed CSF information. The compressed CSF information may be sent to one or more base stations, such as one or more gNBs. The one or more base stations may decode the received encoded CSF information to generate decoded or reconstructed CSF information, such as one or more reconstructed precoding vectors. Using one or more ML algorithms to train encoders and decoders for such encoding and decoding may enable more efficient encoding and decoding of CSF information. Such training may be performed for X-node or bilateral CSF operations, where a UE communicates encoded CSF information with a base station that decodes the encoded CSF information. Note that CSF information is a specific example of information to be encoded and / or decoded at one or more UEs and one or more base stations, and in the present disclosure, encoders and decoders may also be trained for other types of information to be encoded and / or decoded at one or more UEs and one or more base stations.

[0062] The use of a training information set from a base station side server can promote better interoperability between an encoder trained by a UE side server and a decoder trained by a base station side server. In addition, the encoder of the UE side server can be trained by using a training information set from a base station side server without sharing the architecture of a decoder or encoder used and / or trained by the base station side server. Therefore, a vendor operating a base station side server may be able to promote interoperability between a base station decoder and a UE encoder without revealing proprietary details of the trained encoder or decoder. For example, if a base station side server trains an encoder together with a decoder, and the encoder is then shared with a UE side server, then due to the symmetry between the encoder and the decoder, the UE side server may be able to reverse engineer the shared encoder to determine the architecture of the corresponding decoder, such as to determine one or more specific implementation details of the base station's modem. As a specific example, if the trained encoder employs a convolutional layer, the trained decoder may employ a transposed convolutional layer of the convolutional layer employed by the encoder, and the encoder may be used to determine the transposed convolutional layer of the decoder. Therefore, using vendor-specific base station-side and UE-side servers to share training information can allow base station and UE vendors to collaborate in training encoder / decoder pairs for UE and base station without sharing proprietary details about encoder and / or decoder architectures. The base station-side server can also be a base station vendor-specific server, and the UE-side server can be a UE vendor-specific server.

[0063] Figure 3 is a block diagram of an example wireless communication system 300 that supports remote offline sequential network node encoder training according to one or more aspects. In some examples, the wireless communication system 300 can implement aspects of the wireless network 100. The wireless communication system 300 includes a UE 115, a UE-side server 120a, and a base station-side server 120b. Although one UE 115, one UE-side server 120a, and one base station-side server 120b are shown, the wireless communication system 300 may generally include multiple UEs 115, may include more than one UE-side server 120a, may include more than one base station-side server 120b, and may include one or more base stations. In general, servers 120a-120c can each host and train a decoder for use by one or more UEs or one or more base stations when decoding information, where decoding can refer to encoding and decoding. The examples presented herein for encoding may also apply to decoding (mutatis mutandis). Similarly, the examples presented below for decoding may also apply to encoding (mutatis mutandis).

[0064] UE 115 may include various components (such as structures, hardware components) for performing one or more functions described herein. For example, these components may include one or more processors 302 (hereinafter collectively referred to as "processor 302"), one or more memory devices 304 (hereinafter collectively referred to as "memory 304"), one or more transmitters 312 (hereinafter collectively referred to as "transmitters 312"), and one or more receivers 314 (hereinafter collectively referred to as "receivers 314"). Processor 302 may be configured to execute instructions stored in memory 304 to perform the operations described herein. In some specific implementations, processor 302 includes or corresponds to one or more of receiving processor 258, transmitting processor 264, and controller 280, and memory 304 includes or corresponds to memory 282.

[0065] The memory 304 includes or is configured to store input information 306 and encoder parameter information 308. For example, the input information 306 may include CSF information. For example, the CSF information may include one or more measurements performed by the UE on one or more signals sent by a base station, such as one or more channel state information reference signals (CSI-RS) sent by the base station. In some embodiments, the CSF information may include sensed original channel information or singular vector information for one or more beamforming vectors. The input information 306 may be classified by a vendor of a base station associated with the input information or by a model of a base station associated with the input information. For example, input information 306 including sensing or measurement information of one or more signals from a base station identified with a first vendor may be classified as input information associated with a base station identified with a first vendor. The encoder parameter information 308 may include one or more encoder parameters for an encoder 316 of the UE 115. For example, such parameters 308 may be received from a UE-side server 120a. The UE 115 may use the encoder parameter information 308 to adjust the operation of the encoder 316 to encode information to be sent to the base station, such as encoding CSF information for transmission to the base station. In some embodiments, the encoder parameter information 308 may include instructions, codes, or neural network weights and biases for the encoder 316 received from the UE-side server 120a.

[0066] The transmitter 312 is configured to send reference signals, control information, and data to one or more other devices, and the receiver 314 is configured to receive reference signals, synchronization signals, control information, and data from one or more other devices. For example, the transmitter 312 can send signaling, control information, and data to the UE-side server 120a or one or more base stations, and the receiver 314 can receive signaling, control information, and data from the UE-side server or the one or more base stations. In some specific implementations, the transmitter 312 and the receiver 314 can be integrated into one or more transceivers. Additionally or alternatively, the transmitter 312 or the receiver 314 may include or correspond to a reference signal. Figure 2 One or more components of UE 115 are described.

[0067] The encoder 316 of the UE 115 may be an encoder for encoding information to be sent to one or more base stations, such as for encoding CSF information. In some embodiments, the encoder 316 may be an encoder trained offline by the UE-side server 120a and may operate according to the encoder parameter information 308. The decoder 318 may be a decoder for decoding information received by the UE 115. The UE 115 may also include an input information generation manager 320. The input information generation manager 320 may generate the input information 306, such as by sensing or measuring one or more signals from one or more base stations or processing the sensed or measured information.

[0068] The UE-side server 120a may include various components (such as structures, hardware components) for performing one or more functions described herein. For example, these components may include one or more processors 322 (hereinafter collectively referred to as "processors 322"), one or more memory devices 324 (hereinafter collectively referred to as "memory 324"), one or more transmitters 332 (hereinafter collectively referred to as "transmitters 332"), and one or more receivers 334 (hereinafter collectively referred to as "receivers 334"). The processor 322 may be configured to execute instructions stored in the memory 324 to perform the operations described herein.

[0069] The memory 354 includes or is configured to store input information 326, training information 328, and encoder parameter information 330. For example, the input information 326 may be input information received from one or more UEs (such as UE 115). The UE-side server 120a may be associated with a specific UE vendor (such as maintained or operated by a specific UE vendor) and may communicate with a UE associated with the specific UE vendor. Therefore, the input information 326 may include input information from a UE associated with a vendor associated with the UE-side server. For example, such UE may include one or more UEs using one or more encoder parameters for an encoder trained by the UE-side server 120a. In some embodiments, the input information 326 may be classified according to a vendor associated with a base station that sends a signal for generating the input information. The training information 328 may include training information received from the base station-side server 120b. For example, such training information may include input information 326 and associated output information of an encoder from the base station-side server 120b. For example, the training information 328 may include input information provided to an encoder of the base station side server 120b as input, and output information corresponding to the first input information (such as encoded input information). For example, the output information may be generated by the encoder when encoding the provided input information. For example, the input and output information of the training information 328 may be organized in input and associated output tuples. In some embodiments, the training information 328 may include training information received from multiple base station side servers associated with or operated by different vendors. The encoder parameter information 330 may include one or more parameters for an encoder 336 for sending to the UE 115 trained offline by the UE side server. For example, the encoder parameter information may include instructions or codes to be executed by the encoder 316 of the UE 115.

[0070] The transmitter 332 is configured to send reference signals, synchronization signals, control information, and data to one or more other devices, and the receiver 334 is configured to receive reference signals, control information, and data from one or more other devices. For example, the transmitter 332 can send signaling, control information, and data to the UE 115 or the base station side server 120b, and the receiver 334 can receive signaling, control information, and data from the UE or the base station side server. In some specific implementations, the transmitter 332 and the receiver 334 can be integrated in one or more transceivers.

[0071] The UE-side server 120a may include an encoder 336 for encoding information. The encoder 336 may be an encoder trained by the UE-side server 120a, and in some embodiments, the UE-side server 120a may not use the encoder to encode the information to be sent. The encoder 336 may be trained by an encoder training module 340 of the UE-side server. For example, the encoder training module 340 may use one or more ML algorithms to train the encoder 336 using the training information 328. For example, if the training information 328 includes input information and associated output information, the training module 340 may adjust the parameters of the encoder 336 so that when the input information of the training information 328 is input to the encoder 336, the encoder generates output information similar to the output information of the training information 328. For example, the decoder 338 may decode the information received by the UE-side server 120a.

[0072] The base station side server 120b may include various components (such as structures, hardware components) for performing one or more functions described herein. For example, these components may include one or more processors 342 (hereinafter collectively referred to as "processors 342"), one or more memory devices 344 (hereinafter collectively referred to as "memory 344"), one or more transmitters 350 (hereinafter collectively referred to as "transmitters 350"), and one or more receivers 352 (hereinafter collectively referred to as "receivers 352"). The processor 342 may be configured to execute instructions stored in the memory 344 to perform the operations described herein.

[0073] The memory 354 includes or is configured to store input information 346 and training information 348. As discussed above, the input information 346 may be input information received from the UE-side server 120a and used by the base station-side server 120b to train the encoder 354 or decoder 356 of the base station-side server 120b. In some embodiments, the input information 346 may be received from other sources (such as from a base station associated with the same vendor as the base station-side server 120b or a base station implementing a decoder trained by the base station-side server 120b). Such input information 346 may include measurement information received from such base stations, such as one or more measurements performed by one or more base stations on one or more sounding reference signals (SRS). In some embodiments, the input information 346 may include input information received from multiple UE-side servers (such as from multiple UE-side servers associated with different UE vendors). For example, the training information 348 may be training information generated using the encoder 354. For example, the input information 346 may be passed through the encoder 354 after it is trained to generate the training information 348. For example, the training information 348 may include the input information 346, and output information output from the encoder when the input information 346 is input. For example, the output information of the training information 348 may be the encoded input information 346.

[0074] The transmitter 350 is configured to send reference signals, synchronization signals, control information, and data to one or more other devices, and the receiver 352 is configured to receive reference signals, control information, and data from one or more other devices. For example, the transmitter 350 can send signaling, control information, and data to the UE-side server 120a or one or more base stations, and the receiver 352 can receive signaling, control information, and data from the UE-side server or the one or more base stations. In some specific implementations, the transmitter 350 and the receiver 352 can be integrated into one or more transceivers.

[0075] The base station side server 120b may include an encoder 354 for encoding information. The encoder 354 may be an encoder trained by the base station side server 120b. Similarly, the decoder 256 may be a decoder trained by the base station side server 120b, and in some embodiments, the base station side server 120b may not use the decoder 356 to decode the received information. The encoder 354 and / or the decoder 356 may be trained by a training module 358 of the base station side server 120b. For example, the training module 358 may use one or more ML algorithms to train the encoder 354 and / or the decoder 356 using the input information 346. For example, the training module 358 may adjust the parameters of the encoder 354 and / or the decoder 356 to enhance the operation of the encoder and / or the decoder when encoding and / or continuously decoding the input information. When the encoder 354 and the decoder 356 are trained, the base station side server 120 b may encode the input information 346 using the trained encoder 354 to generate training information 348 including both the input information 346 and the output of the encoder 354 .

[0076] In some implementations, the wireless communication system 300 implements a 5G NR network. For example, the wireless communication system 300 may include a plurality of 5G-capable UEs 115 and a plurality of 5G-capable base stations 105 (such as UEs and base stations configured to operate according to a 5G NR network protocol such as defined by 3GPP) and servers (such as UE-side servers 120a and base station-side servers 120b) that facilitate training of encoders and decoders of the UEs 115 or base stations 105.

[0077] During operation of the wireless communication system 300, the UE 115 may send a message 372 including input information 374 to the UE-side server 120a. For example, the input information 374 may be the input information 306. The UE-side server 120a may send a message 364 including input information 366 to the base station-side server 120b. For example, the input information 366 may be the input information 326. For example, the input information 366 may include input information collected by the UE-side server 120a from multiple UEs. In some embodiments, the base station-side server 120b may receive input information from additional UE-side servers such as Figure 1 The UE-side server 120c of the base station side receives the message with the input information. After generating the training information 348, the base station side server 120b can send a message 360 ​​including the training information 662 to the UE-side server 120a. The UE-side server can train the encoder 336 based on the received training information, and can send a message 368 including the encoder parameter information 370 to the UE 115. Thus, the base station side server 120b can control the training of the encoder for one or more UEs 115.

[0078] Figure 4 4 is a timing diagram of a system 400 that supports remote offline network node encoder training. System 400 may include UE 115, UE-side server 120a, base station-side server 120b, and base station 105. UE 115 and UE-side server 120a may be associated with the same UE vendor (such as the same manufacturer or designer). For example, UE-side server 120a may train one or more encoders implemented for UEs associated with a particular vendor, and UE-side server 120a may be operated by the same vendor. Base station-side server 120b may control the training of one or more encoders by UE-side server 120a by generating training information for use by UE-side server 120a in training one or more encoders. Such control may achieve interoperability between an encoder implemented by a UE (such as UE 115) and a decoder implemented by a base station (such as base station 105) and enhanced encoding and decoding efficiency and reliability without requiring the vendor operating base station-side server 120b to disclose details of a decoder or encoder trained by base station-side server 120b and implemented on one or more base stations, such as not disclosing decoder output information or encoder parameters. In some embodiments, the system 400 may include multiple UE-side servers associated with multiple corresponding UE vendors or multiple base station-side servers associated with multiple base station-side servers. For example, a single base station-side server 120b in a single training session may train an encoder using input information received from multiple UE-side servers associated with different corresponding UE vendors, and may generate and send the same set of training information to multiple UE-side servers associated with different corresponding UE vendors.

[0079] At 402, the UE 115 may generate input information. For example, the input information may include CSF information. Generating the input information at 402 may include performing one or more measurements of one or more signals (such as CSI-RS) transmitted by one or more base stations (such as the base station 105). For example, the base station that transmits the signal for the UE 115 to measure when generating the CSF information may include a base station associated with the same vendor as the base station-side server 120b. In some embodiments, the UE 115 may generate the input information using signals received from multiple base stations associated with multiple vendors.

[0080] At 404, UE 115 may send input information to UE-side server 120a. For example, UE-side server 120a may be a UE-side server operated by the same vendor as the vendor associated with UE 115 or associated with the vendor. For example, the input information sent may include input information generated based on signals from multiple base stations associated with multiple different corresponding vendors, multiple base stations associated with a single vendor, or a single base station associated with a single vendor. In some embodiments, input information generated based on signals received from base stations associated with different vendors may be identified for separate processing by UE-side server 120a. UE-side server 120a may receive input information from multiple UEs associated with the same vendor as UE-side server 120a. Therefore, in some embodiments, UE-side server 120a may store multiple sets of input information associated with multiple corresponding base station vendors.

[0081] At 406, the UE-side server 120a may send input information to the base station-side server 120b. The input information sent at 406 may be input information received by the UE-side server 120a from one or more UEs (such as UE 115). In some embodiments, the input information sent at 406 may be input information generated by one or more UEs based on signals received from one or more base stations associated with the same vendor as the base station server 120b. In some embodiments, the base station-side server 120b may receive input information from multiple UE-side servers, such as receiving input information from multiple UE-side servers associated with different corresponding vendors. The input information received by the base station-side server 120b may be input information generated based on signals sent by base stations associated with the same vendor as the base station-side server 120b. Therefore, in some embodiments, the input information received by the base station-side server 120b may be associated with the same vendor as the base station-side server 120b, but may be associated with multiple corresponding UE vendors, and the base station-side server 120b may maintain multiple sets of input information received from multiple UE-side servers associated with different corresponding UE vendors.

[0082] At 408, the base station 105 may generate input information. For example, the base station 105 may be a base station associated with the same vendor as the base station side server 120b. For example, the base station 105 may decode the information received from the UE using a decoder trained by the base station side server 120b. The base station 105 may generate the input information by sensing or performing one or more measurements of one or more sounding reference signals. At 410, the base station 105 may send the generated input information to the base station side server 120b. Thus, the base station side server 120b may receive input information from one or more UE side servers or from one or more base stations.

[0083] At 412, the base station side server 120b can train the encoder and decoder. For example, the base station side server 120b can train the decoder to determine one or more decoder parameters for sending to one or more base stations. The base station side server 120b can train the corresponding encoder to generate training information. The base station side server can use the input information received at 406 or 410 to train the encoder and decoder. In some embodiments, the base station side server 120b can use one or more ML algorithms to train the encoder and decoder. In some embodiments, the base station side server 120b can use both the input information received from the base station 105 and the input information received from the UE side server 120a or other input information to train the encoder and decoder.

[0084] At 414, the base station side server 120b may generate training information. For example, when training an encoder, the base station side server may provide input information to the encoder, such as the input information received at 406 or the input information received at 410. The trained encoder may encode the input information and output the encoded input information. The combined input information and output information (such as the encoded input information) may be training information.

[0085] In some embodiments, the base station side server 120b may train an encoder at 412 and generate training information for each of a plurality of UE side servers associated with different UE vendors at 414. For example, the base station side server 120b may train an encoder specific to a particular UE vendor. In some embodiments, the base station side server 120b may train a single encoder and generate single training information for multiple UE vendors using input information from multiple UE vendors in a single training session. In some embodiments, the base station side server 120b may train multiple encoders. The base station side server 120b may generate multiple sets of training information, such as multiple sets of training information for multiple UE side servers. For example, a set of training information for a specific UE side server may be generated by passing the input information received from each respective UE side server through an encoder trained with the input information from each respective UE side server, or passing the set of input information received from each respective UE side server through a single encoder to generate a set of training information.

[0086] At 416, the base station side server 120b may send training information to the UE side server 120a. At 418, the UE side server 120a may use the training information to train the encoder. In some embodiments, the UE side server 120a may use multiple sets of training information received from multiple corresponding base station side servers associated with different vendors to train multiple encoders. Training the encoder may include applying one or more ML algorithms to generate encoder parameters. For example, the encoder parameters may include computer code, instructions, neural network weights and biases or other encoder parameters for use by UE 115. In some embodiments, in order to train the encoder, the UE side server 120a may pass the input information of the input-output tuple of the training information through the encoder, and may adjust the parameters of the encoder until the output of the encoder approaches or matches the output of the corresponding tuple. When training the encoder, the UE side server 120a may send the encoder parameters to the UE 115 at 420. At 422, the UE 115 may encode the information using the received encoder parameters. Therefore, the base station side server 120b may provide training information for training the encoder to be used by one or more UEs. This training can be remote, in that the remote UE-side server and the remote base station-side server can collaborate to train the encoder for use by one or more UEs, the training can be offline, in that the UE-side server and the base station-side server can train the encoder when the encoder is not being used to encode information for transmission, and the training can be sequential, in that the base station-side server can train the encoder to generate training information for use by the UE-side server when training the encoder.

[0087] Figure 5 5 is a flow chart illustrating an example process 500 for supporting remote offline sequential network node training. The operations of process 500 may be performed by a UE-side server (such as the one described above with reference to Figure 1 , Figure 3 and Figure 4 The UE-side server 120a described or reference Figure 7 For example, the operations (also referred to as "boxes") of process 500 may enable the UE-side server 120a to support remote offline sequential network node training.

[0088] At box 502, the UE-side server may receive input information. For example, the UE-side server may receive CSF information from one or more UEs. The CSF information may include one or more measurements of one or more CSI-RS measured or sensed by one or more UEs from one or more base stations associated with one or more vendors. For example, the input information may include original channel information or singular vector information. The UE from which the input information is received may be a UE associated with the same vendor as the UE-side server. The received input information may be classified according to the base station that sends the signal, and the input information is generated by the corresponding UE based on these signals. For example, the received input information may be classified according to the vendor associated with the base station that sends the signal, and the input information is generated based on these signals. Therefore, the UE-side server may maintain multiple sets of input information associated with multiple corresponding base station vendors.

[0089] At box 504, the UE-side server may send input information to the base station side server. For example, the base station side server may be a base station side server associated with a particular vendor, such as a base station side server that trains a decoder for a base station associated with the particular vendor. For example, the input information sent may be input information generated by the UE based on a signal sent by a base station associated with the particular vendor. Alternatively or additionally, the input information may be input information generated by the UE based on signals sent by base stations associated with various respective vendors. In some embodiments, the UE-side server may not send input information to the base station side server, and the base station side server may receive input information from other sources, such as other UE-side servers or base stations.

[0090] At box 506, the UE side server may receive training information from the base station side server. For example, the training information may include input information of a trained encoder passed through the base station side server and output information corresponding to the first input information, such as output information generated by an encoder of the base station side server based on the input information. The input information included in the training information may include input information sent by the UE side server at box 504. The input information included in the training information may also include other input information not sent by the UE side server, such as input information received by the base station side server from one or more other UE side servers. For example, the input information and output information of the training information may be included in one or more input-output tuples to indicate the input information and the associated output information. For example, the output information of the training information may be the encoded input information generated by the encoder trained using the input information. For example, the input information may include CSF information, such as original channel information or singular vector information, and the output information may include encoded CSF information, such as encoded original channel information or encoded singular vector information. In some embodiments, the input information of the training information may include input information from a source other than the UE side server (such as other UE side servers or base stations). For example, the input information may include measurement information from one or more base stations generated based on one or more measurements performed by the one or more base stations on one or more sounding reference signals.

[0091] At box 508, the UE side server may use the received training information to train the encoder. For example, the UE side server may apply one or more ML algorithms to train the encoder using the received training information, adjusting one or more parameters of the encoder to generate output information that matches the output information of the training information according to the input information of the training information. In some embodiments, the UE may train multiple encoders using multiple corresponding sets of training information from multiple corresponding base station side servers. For example, the UE side server may train an encoder for each base station supplier in multiple base station suppliers, and the base station side server from which the training information is received is associated with the multiple base station suppliers. In some embodiments, the UE may train a single encoder using multiple sets of training information from multiple base station side servers associated with different corresponding suppliers. When training the encoder, the UE side server may generate one or more encoder parameters. The encoder parameters may include, for example, instructions for operating the encoder, computer code for operating the encoder, neural network weights and biases for the encoder, or other encoder parameters.

[0092] At block 510, the UE-side server may send one or more encoder parameters. For example, the UE-side server may send instructions or computer code for operating a trained encoder, or neural network weights and biases for a trained encoder, to one or more UEs connected to the UE-side server. The UE may then use the encoder parameters for the trained encoder to encode information (such as channel state feedback information) for transmission to a base station. For example, the UE may adjust one or more parameters of an encoder operated by the UE based on the received encoder parameters.

[0093] Figure 6 600 is a flow chart illustrating an example process 600 for supporting remote offline sequential network node training. The operations of process 600 may be performed by a base station side server (such as the one described above with reference to Figure 1 , Figure 3 and Figure 4 The base station side server 120b described or reference Figure 8 For example, the operations (also referred to as "boxes") of process 600 may enable the base station side server 120b to support remote offline sequential network node training.

[0094] At box 602, the base station side server may receive input information. As discussed herein, such input information may be received from one or more UE side servers, one or more base stations, or one or more other sources. For example, the base station side server may receive input information from one or more base stations associated with the same supplier as the base station server. For example, the input information may include channel state feedback information, or measurement information generated based on one or more measurements of signals (such as one or more SRS) sent by one or more base stations. For example, the input information received from one or more base stations may be a public information set and may not correspond to a UE or UE side server of a specific UE supplier. In some embodiments, the input information received by the base station side server may be input information associated with the supplier of the base station side server, such as input information generated based on a signal sent by a base station associated with the supplier of the base station side server. In some embodiments, the input information may be input information associated with multiple base station suppliers. In some embodiments, the input information may be input information generated by a UE associated with a specific UE supplier and aggregated by a UE side server associated with the same UE supplier. In some embodiments, the input information received by the base station side server may be input information generated by a UE associated with multiple UE suppliers and aggregated by multiple UE side servers associated with multiple corresponding suppliers. Thus, input information may be received from a variety of sources as described herein.

[0095] At box 604, the base station side server may train the encoder. At box 606, the base station side server may train the decoder. In some embodiments, the base station side server may employ one or more ML algorithms to train the encoder and decoder separately or together. The base station side server may train the encoder to generate training information for sending to one or more UE side servers. The base station side server may train the decoder to generate one or more decoder parameters for sending to one or more base stations. The encoder and decoder may be trained together to facilitate more efficient interoperability of the UE (encoder managed using one or more encoder parameters generated by the UE side server using the training information of the encoder from the base station side server) and the base station (decoder managed using one or more decoder parameters generated by the base station side server). The encoder and decoder may be trained using any combination of input information received by the base station side server. In some embodiments, the base station side server may train more than one encoder and more than one decoder, such as training multiple encoders using corresponding input information associated with corresponding UE vendors. In some embodiments, the base station side server may train the encoder using input information generated by UEs associated with multiple different vendors and aggregated by and received from multiple corresponding UE side servers associated with each of the corresponding different vendors. Thus, in some embodiments, a single encoder may be trained using information associated with multiple different UE vendors in a single training session.

[0096] At box 608, the base station side server may generate training information. For example, when training the encoder, the base station side server may provide input information to the encoder, and the encoder may use the provided input information to generate output information. For example, the output information may be the input information of the encoding. The training information may include both the provided input information and the generated output information. For example, the training information may include one or more input-output tuples, which include input information and output information generated based on the input information. As a specific example, the base station side server may provide the encoder with original channel information or singular vector information, and the encoder may output the encoded original channel information or the encoded singular vector information. Therefore, the training information may include the original channel information or singular vector information and the encoded original channel information or singular vector information. The base station side server may generate a set of training information for sending to multiple UE side servers, or may generate multiple sets of training information for sending to multiple corresponding UE side servers. For example, an encoder trained with input information from a specific UE side server may be used to generate training information for the specific UE side server based on the input information from the specific UE side server. As another example, an encoder trained using input information from multiple UE-side servers associated with multiple different corresponding UE vendors can be used to generate training information based on input information from multiple UE-side servers associated with multiple UE vendors.

[0097] At 610, the base station side server may send training information. For example, the base station side server may send training information to the UE side server for use by the UE side server in training an encoder, which is used by one or more UEs when encoding information for sending to one or more base stations. In some embodiments, the base station side server may send a single set of training information to multiple UE side servers associated with multiple corresponding UE vendors, while in other embodiments, the base station side server may send different sets of training information to different UE side servers, such as sets of training information generated for specific corresponding UE side servers. For example, multiple UE side servers associated with different vendors may participate in the same training session with a single base station side server. The base station side server may use input information from multiple UE side servers to train a single encoder, and may generate a single set of training information for sending to multiple UE side servers. Therefore, the base station side server may act as a teacher when training one or more student UE side server encoders in the knowledge distillation process. The training performed by the UE side server of the encoder may become supervised learning using training information from the base station side server. Because the base station side server shares training information with the UE side server, the UE side server may not be aware of the encoder trained by the base station side server. Therefore, the encoder trained by the UE-side server may adopt an architecture different from the architecture adopted by the encoder trained by the base station-side server.

[0098] Figure 7 is a block diagram of an example UE-side server 700 that supports remote offline sequential network node training in one or more aspects. The UE-side server 700 may be configured to perform operations, including reference Figures 4 to 5 In some specific implementations, the UE-side server 700 includes a reference Figure 3 The structure, hardware, and components shown and described in the UE-side server 120a of the present invention. For example, the UE-side server 700 includes a controller 702 that operates to execute logic or computer instructions stored in a memory 706, and controls components of the UE-side server 700 that provide features and functionality of the UE-side server 700. Under the control of the controller 702, the UE-side server 700 sends and receives signals via a communication module 704. For example, the communication module 704 may include various components and hardware, such as an Ethernet module, a Bluetooth module, a Wi-Fi module, or other communication modules.

[0099] As shown, the memory 706 may include input information 708, training information 710, encoder parameter information 712, encoding logic 714, and training logic 716. For example, as discussed herein, the input information 708 may include channel state feedback information or other input information. As discussed herein, the training information 710 may include training information received from one or more base station side servers. As discussed herein, the encoder parameter information 712 may include one or more encoder parameters for one or more encoders trained by the UE side server. As discussed herein, the encoding logic 714 may include logic for one or more encoders trained by the UE side server 700, and may be configured to encode information. As discussed herein, the training logic 716 may include logic for training an encoder (such as an encoder of the encoding logic 714) using the training information 710, and may train the encoder to generate one or more elements of the encoder parameter information 712. The UE side server 700 may receive information from one or more network entities (such as Figure 1 and Figure 3 to Figure 4 UE 115 or base station side server 120b or as Figure 8 The base station side server 800 shown receives a signal or sends a signal to the one or more network entities.

[0100] Figure 8 800 is a block diagram of an example base station side server 800 supporting remote offline sequential network node encoder training according to one or more aspects. The base station side server 800 can be configured to perform operations, including reference Figure 6 In some implementations, the base station side server 800 includes a reference Figure 1 , Figure 3 to Figure 4 The structure, hardware, and components shown and described in the base station side server 120b of the present invention. For example, the base station side server 800 may include a controller 802 that operates to execute logic or computer instructions stored in a memory 806, and controls components of the base station side server 800 that provide features and functionality of the base station side server 800. Under the control of the controller 802, the base station side server 800 sends and receives signals via a communication module 804. For example, the communication module 804 may include various components and hardware, such as an Ethernet module, a Bluetooth module, a Wi-Fi module, or other communication modules.

[0101] As shown, the memory 806 may include input information 810, training information 812, decoding logic 816, encoding logic 818, training logic 820, and training information generation logic 822. For example, as discussed herein, the input information 810 may include input information received from one or more UE-side servers or from one or more base stations. For example, as discussed herein, the training information 812 may include input information and corresponding output information for an encoder trained by the base station side server 800. The decoding logic 816 may be configured to decode the information, such as according to one or more decoding parameters. For example, the decoding logic 816 may include one or more associated parameters for sending to one or more base stations for decoding the information. The encoding logic 818 may be configured to encode the information, such as according to one or more encoding parameters. The training logic 820 may be configured to use the input information 810 to train the encoder and decoder of the base station side server 800, such as by adjusting one or more parameters of the encoding logic 818 and the decoding logic 816. The training information generation logic 822 may be configured to generate training information using a trained encoder of a base station side server, such as by providing input information 810 to the trained encoding logic 818 to encode the input information and pairing the encoded information in one or more tuples with the input information from which the encoded information was generated. The base station 800 may receive training information from one or more UE side servers such as Figure 1 , Figure 3 to Figure 4 UE-side server 120a or Figure 7 UE-side server 700) receives signals or sends signals to one or more UE-side servers.

[0102] Please note that reference Figures 4 to 6 One or more blocks (or operations) described may be combined with one or more blocks (or operations) described with reference to another figure. Figure 4 One or more boxes (or operations) of Figure 5 One or more boxes (or operations) of . Figure 5 One or more boxes associated with Figure 6 One or more frame combinations. Figure 4 One or more boxes associated with Figure 6 Additionally or alternatively, the above reference Figures 1 to 3 One or more of the operations described may be combined with Figure 7 or Figure 8 A combination of one or more of the operations described.

[0103] Although the above reference Figures 3 to 8The description describes that the UE-side server can receive training information from the base station side server and use the received training information to train the encoder, but the present disclosure is not limited to this. For example, similar to the UE-side server, the UE can be configured to receive training information from the base station side server and use the received training information to train the encoder. In another example, the base station can be configured to generate training information (as described with respect to the base station side server) and send the training information to other systems, devices, or nodes. That is, the above operations or steps performed by the UE-side server and the base station side server can be performed by other systems, devices, or nodes, which does not fall outside the scope of the present disclosure.

[0104] In one or more aspects, the technology for supporting remote offline sequential network node training may include additional aspects, such as any single aspect or any combination of aspects described below or in combination with one or more other processes or devices described elsewhere herein. In a first aspect, supporting remote offline sequential network node training may include a device configured to: receive training information for a first encoder of a first network node from a second network node, wherein the training information includes first input information for a second encoder of the second network node and output information corresponding to the first input information; and use the training information to train the first encoder of the first network node. Additionally, the device may be performed or operated according to one or more aspects as described below. In some specific implementations, the device includes a network node, such as a UE-side server. In some specific implementations, the device may include at least one processor, and a memory coupled to the processor. The processor may be configured to perform the operations described herein with respect to the device. In some other specific implementations, the device may include a non-transitory computer-readable medium having a program code recorded thereon, and the program code may be executable by a computer to cause the computer to perform the operations described herein with reference to the device. In some implementations, the apparatus may include one or more components configured to perform the operations described herein. In some implementations, a method of wireless communication may include one or more operations described herein with reference to the apparatus.

[0105] In a second aspect, alone or in combination with one or more of the above aspects, the first input information and the output information are included in one or more input-output tuples of the training information.

[0106] In a third aspect, alone or in combination with one or more of the above aspects, the first network node comprises a user equipment (UE) vendor specific server and the second network node comprises a base station vendor specific server.

[0107] In a fourth aspect, alone or in combination with one or more of the above aspects, the apparatus may be configured to send encoder parameters generated during training of the first encoder to a third network node, wherein the third network node comprises a user equipment (UE).

[0108] In a fifth aspect, alone or in combination with one or more of the above aspects, the first input information includes original channel information or singular vector information, and the output information includes encoded original channel information or encoded singular vector information.

[0109] In a sixth aspect, alone or in combination with one or more of the above aspects, the apparatus may be further configured to send second input information to a second network node, wherein the first input information includes the second input information.

[0110] In a seventh aspect, either alone or in combination with one or more of the above aspects, the apparatus may be further configured to receive second input information from one or more user equipments (UEs), wherein the second input information comprises one or more measurements of one or more signals sent by a base station.

[0111] In an eighth aspect, either alone or in combination with one or more of the above aspects, the first input information further comprises third input information received by the second network node from a third network node, wherein the first network node comprises a first user equipment (UE) vendor specific server, and wherein the third network node comprises a second user equipment (UE) vendor specific server different from the first UE vendor specific server.

[0112] In a ninth aspect, alone or in combination with one or more of the above aspects, the first input information comprises second input information received by the second network node from a third network node, wherein the third network node comprises a base station.

[0113] In a tenth aspect, alone or in combination with one or more of the above aspects, the second input information comprises measurement information generated by a third network node.

[0114] In an eleventh aspect, alone or in combination with one or more of the above aspects, the second encoder is trained using the first input information before generating the output information.

[0115] In one or more aspects, the technology for supporting remote offline sequential network node training may include additional aspects, such as any single aspect or any combination of aspects described below or in combination with one or more other processes or devices described elsewhere herein. In a twelfth aspect, supporting remote offline sequential network node training may include a device configured to: remote offline sequential network node training; and send training information to a second network node for training a second encoder of the second network node. Additionally, the device may be performed or operated according to one or more aspects as described below. In some specific implementations, the device includes a network node, such as a base station side server. In some specific implementations, the device may include at least one processor, and a memory coupled to the processor. The processor may be configured to perform the operations described herein with respect to the device. In some other specific implementations, the device may include a non-transitory computer-readable medium having a program code recorded thereon, and the program code may be executable by a computer for causing the computer to perform the operations described herein with reference to the device. In some specific implementations, the device may include one or more components configured to perform the operations described herein. In some specific implementations, the method of wireless communication may include one or more operations described herein with reference to the device.

[0116] In a thirteenth aspect, alone or in combination with one or more of the above aspects, the first input information and the output information are included in one or more input-output tuples of the training information.

[0117] In a fourteenth aspect, alone or in combination with one or more of the above aspects, the first network node comprises a base station vendor specific server and the second network node comprises a user equipment (UE) vendor specific server.

[0118] In a fifteenth aspect, either alone or in combination with one or more of the above aspects, the first input information comprises original channel information or singular vector information, and the output information comprises encoded original channel information or encoded singular vector information.

[0119] In a sixteenth aspect, alone or in combination with one or more of the above aspects, the apparatus may be configured to receive second input information from a second network node, wherein the first input information includes the second input information.

[0120] In a seventeenth aspect, either alone or in combination with one or more of the above aspects, a second network node receives second input information from one or more user equipments (UEs), and wherein the second input information comprises one or more measurements of one or more signals sent by a base station.

[0121] In an eighteenth aspect, alone or in combination with one or more of the above aspects, the apparatus may be configured to receive third input information from a third network node, wherein the second network node includes a first user equipment (UE) vendor specific server, and wherein the third network node includes a second user equipment (UE) vendor specific server different from the first UE vendor specific server.

[0122] In a nineteenth aspect, alone or in combination with one or more of the above aspects, the apparatus may be configured to receive second input information from a third network node, wherein the first input information includes the second input information, and wherein the third network node includes a base station.

[0123] In a twentieth aspect, alone or in combination with one or more of the above aspects, the second input information comprises measurement information from one or more measurements generated by a third network node.

[0124] In a twenty-first aspect, alone or in combination with one or more of the above aspects, the apparatus may be configured to train a first encoder using the first input information, wherein generating the training information is performed after training the first encoder.

[0125] In a twenty-second aspect, alone or in combination with one or more of the above aspects, the apparatus may be configured to train a first decoder of a first network node using the first input information.

[0126] In a twenty-third aspect, a method of wireless communication performed by a system including a first network node and a second network node may include: generating output information by a second decoder of the second network node based on first input information; transmitting, by the second network node, training information for the first decoder of the first network node to the first network node, wherein the training information includes the output information of the second decoder of the second network node and the corresponding first input information of the second decoder of the second network node; and using the training information to train the first decoder of the first network node.

[0127] In a twenty-fourth aspect, a system may include a first network node and a second network node, the first network node and the second network node including means for performing the method according to the twenty-third aspect.

[0128] As described herein, a node (which may be referred to as a node, a network node, a network entity, or a wireless node) may include, may be, or may be included in (e.g., as a component of) a base station (e.g., any base station described herein), a UE (e.g., any UE described herein), a network controller, an apparatus, a device, a computing system, an integrated access and backhaul (IAB) node, a distributed unit (DU), a central unit (CU), a remote / radio unit (RU) (which may also be referred to as a remote radio unit (RRU)), and / or another processing entity configured to perform any of the techniques described herein. For example, the network node may be a UE. For another example, the network node may be a base station or a network entity. For another example, the network node may be a server, such as a UE-side server or a base station-side server. For another example, the first network node may be configured to communicate with a second network node or a third network node. In one aspect of this example, the first network node may be a UE, the second network node may be a base station, and the third network node may be a UE. In another aspect of this example, the first network node may be a UE, the second network node may be a base station, and the third network node may be a base station. In another aspect of this example, the first network node may be a UE-side server, the second network node may be a base station-side server, and the third network node may be a UE or a base station. In yet other aspects of this example, the first network node, the second network node, and the third network node may be different relative to these examples. Similarly, references to UE, base station, device, equipment, computing system, etc. may include disclosure of UE, base station, device, equipment, computing system, etc. as network nodes. For example, the disclosure that the UE is configured to receive information from the base station also discloses that the first network node is configured to receive information from the second network node. Consistent with the present disclosure, once a specific example is expanded according to the present disclosure (e.g., the UE is configured to receive information from the base station also discloses that the first network node is configured to receive information from the second network node), the broader example of the narrower example may be interpreted in reverse, but in a broad, open-ended manner. In the above example in which the UE is configured to receive information from a base station and the first network node is also disclosed to be configured to receive information from a second network node, the first network node may refer to a first UE configured to receive information, a first base station, a first device, a first equipment, a first computing system, a first set of one or more components, a first processing entity, etc.; and the second network node may refer to a second UE, a second base station, a second device, a second equipment, a second computing system, a second set of one or more components, a second processing entity, etc.

[0129] As described herein, different terms may be used in various aspects to describe the communication of information (e.g., any information, signal, etc.). Disclosure of one communication term includes disclosure of other communication terms. For example, a first network node may be described as being configured to send information to a second network node. In this example and consistent with the present disclosure, disclosure that the first network node is configured to send information to the second network node includes disclosure that the first network node is configured to provide, transmit, output, communicate, or send information to the second network node. Similarly, in this example and consistent with the present disclosure, disclosure that the first network node is configured to send information to the second network node includes disclosure that the second network node is configured to receive, obtain, or decode information provided, transmitted, output, communicated, or sent by the first network node.

[0130] It should be understood by those skilled in the art that any of a variety of different technologies and techniques may be used to represent information and signals. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, light fields or optical particles, or any combination thereof.

[0131] This article is about Figures 1 to 3 and Figures 7 and 8 The components, functional blocks and modules described include processors, electronic devices, hardware devices, electronic components, logical circuits, memories, software codes, firmware codes, etc., or any combination thereof. Software should be broadly interpreted to mean instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, and / or functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language or other terms. In addition, the features discussed herein may be implemented via dedicated processor circuits, via executable instructions, or a combination thereof.

[0132] The technician will further understand that the various exemplary logic boxes, modules, circuits and algorithm steps described in conjunction with the disclosure of this article can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, various exemplary components, boxes, modules, circuits and steps have been roughly described in terms of their functionality. Whether such functions are implemented as hardware or software depends on the specific application and the design constraints proposed to the entire system. Those skilled in the art can implement the described functionality in different ways for each specific application, but such specific implementation decisions should not be interpreted as causing departure from the scope of the present disclosure. The technician will also easily recognize that the order or combination of components, methods or interactions described herein are only examples, and the components, methods or interactions of various aspects of the present disclosure can be combined or performed in a manner other than the manner illustrated and described herein.

[0133] The various illustrative logical components, logic blocks, modules, circuits, and algorithmic processes described in conjunction with the specific implementations disclosed herein may be implemented as electronic hardware, computer software, or a combination of the two. The interchangeability of hardware and software has been generally described in terms of functionality and is illustrated in the various illustrative components, blocks, modules, circuits, and processes described above. Whether such functionality is implemented in hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0134] The hardware and data processing apparatus for implementing the various exemplary logics, logic blocks, modules and circuits described in conjunction with the various aspects disclosed herein may be implemented or executed using a general purpose single-chip or multi-chip processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic component, a discrete hardware component or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, or any conventional processor, controller, microcontroller or state machine. In some specific implementations, a processor may be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in combination with a DSP core, or any other such configuration. In some specific implementations, specific processes and methods may be performed by circuits specific to a given function.

[0135] In one or more aspects, the functions described may be implemented in hardware, digital electronic circuitry, computer software, firmware, including the structures disclosed in this specification and their structural equivalents, or any combination thereof. Specific implementations of the subject matter described in this specification may also be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on computer storage media for execution by data processing apparatus or for controlling the operation of data processing apparatus.

[0136] If implemented in software, the function can be stored as one or more instructions or codes on a computer-readable medium or sent through a computer-readable medium. The process of the method or algorithm disclosed herein can be implemented in a processor executable software module that can reside on a computer-readable medium. Computer-readable media include both computer storage media and communication media, and the communication media include any media that can be implemented to transfer a computer program from one place to another. The storage medium can be any available medium that a computer can access. As an example and not limitation, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be used to store the required program code in the form of an instruction or data structure and can be accessed by a computer. In addition, any connection can be appropriately referred to as a computer-readable medium. Disks and optical disks as used herein include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks and blue discs, wherein disks usually reproduce data magnetically, and optical discs reproduce data optically with lasers. The above combination should also be included in the scope of computer-readable media. Additionally, the operations of a method or algorithm may reside as a code and instruction set, or any combination of code and instruction sets, on a machine-readable medium or computer-readable medium, which may be incorporated into a computer program product.

[0137] Various modifications to the specific implementations described in this disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to some other specific implementations without departing from the spirit or scope of the disclosure. Therefore, the claims are not intended to be limited to the specific implementations shown herein, but are to be consistent with the broadest scope consistent with the disclosure, the principles and novel features disclosed herein.

[0138] Additionally, one of ordinary skill in the art will readily recognize that the terms "upper" and "lower" are sometimes used for ease of describing the drawings and indicate relative positions corresponding to the orientation of the drawings on a correctly oriented page, and may not reflect the correct orientation of any device as implemented.

[0139] Certain features described in this specification in the context of separate implementations may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented in multiple implementations, either individually or in any suitable subcombination. Furthermore, while features may be described above as functioning in certain combinations and even initially claimed as such, one or more features from a claimed combination may in some cases be removed from the combination, and a claimed combination may be directed to subcombinations or variations of subcombinations.

[0140] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be understood as requiring such operations to be performed in the specific order shown or in a sequential order, or to perform all illustrated operations to achieve the desired result. In addition, the accompanying drawings can schematically depict one or more example processes in the form of a flow chart. However, other operations that are not depicted can be combined in the example processes schematically illustrated. For example, one or more additional operations can be performed before, after, simultaneously or between any illustrated operations. In some environments, multitasking and parallel processing are advantageous. In addition, the separation of various system components in the specific implementation described above should not be understood as requiring such separation in all specific implementations, and it should be understood that the program components and systems can generally be integrated together in a single software product or packaged into multiple software products. Additionally, some other specific implementations also fall within the scope of the appended claims. In some cases, the actions described in the claims can be performed in different orders and still achieve the desired result.

[0141] As used herein, including in the claims, the term "or" used in a list of two or more items means that any of the listed items may be employed alone, or any combination of two or more of the listed items may be employed. For example, if a composition is described as containing components A, B, or C, the composition may contain A alone; B alone; C alone; A and B combined; A and C combined; B and C combined; or A, B, and C combined. In addition, as used herein, including in the claims, "or" as used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) or any combination of any of these. The term "substantially" is defined as to a large extent, but not necessarily entirely, what is specified (and includes what is specified; for example, substantially 90 degrees includes 90 degrees, and substantially parallel includes parallel), as understood by one of ordinary skill in the art. In any disclosed implementation, the term "substantially" may be replaced with "within [percentage] of" the specified content, where percentages include 0.1%, 1%, 5%, or 10%. As used herein, the phrase "based on" should not be interpreted as referring to a closed set of information, one or more conditions, one or more factors, etc. In other words, the phrase "based on A" (where "A" can be information, a condition, a factor, etc.) should be interpreted as "based on at least A" unless specifically stated differently. Similarly, as used herein, the phrase "set" should be understood to include the possibility of a set having one member. That is, the phrase "set" should be understood in the same manner as "one or more" or "at least one".

[0142] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Therefore, the disclosure is not intended to be limited to the examples and designs described herein, but to be consistent with the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of wireless communication performed by a first network node, the method comprising: receiving, from a second network node, training information for a first encoder of the first network node, wherein the training information comprises first input information for a second encoder of the second network node and output information corresponding to the first input information; and The first encoder of the first network node is trained using the training information.

2. The method of claim 1 , wherein the first input information and the output information are included in one or more input-output tuples of the training information, wherein the first input information includes channel state feedback (CSF) information, and wherein the output information includes encoded CSF information.

3. The method of claim 1, wherein the first network node comprises a user equipment (UE) vendor specific server and the second network node comprises a base station vendor specific server.

4. The method according to claim 1, further comprising: Encoder parameters generated during training of the first encoder are sent to a third network node, wherein the third network node comprises a user equipment (UE).

5. The method according to claim 1, further comprising: Second input information is sent to the second network node, wherein the first input information includes the second input information.

6. The method according to claim 5, further comprising: The second input information is received from one or more user equipment (UE), wherein the second input information includes one or more measurements of one or more signals transmitted by a base station.

7. The method of claim 5, wherein the first input information further comprises third input information received by the second network node from a third network node, wherein the first network node comprises a first user equipment (UE) vendor specific server, and wherein the third network node comprises a second user equipment (UE) vendor specific server different from the first UE vendor specific server.

8. The method of claim 1 , wherein the first input information comprises second input information received by the second network node from a third network node, wherein the second network node comprises a base station vendor specific server, and wherein the third network node comprises a base station, and wherein the second input information comprises measurement information generated by the third network node.

9. A first network node, the first network node comprising: Memory; and at least one processor coupled to the memory, wherein the at least one processor is configured to: receiving, from a second network node, training information for a first encoder of the first network node, wherein the training information comprises first input information for a second encoder of the second network node and output information corresponding to the first input information; and The first encoder of the first network node is trained using the training information.

10. The first network node of claim 9, wherein the first input information and the output information are included in one or more input-output tuples of the training information.

11. The first network node of claim 9, wherein the first network node comprises a user equipment (UE) vendor specific server and the second network node comprises a base station vendor specific server, wherein the first input information comprises channel state feedback (CSF) information, and wherein and the output information comprises encoded CSF information.

12. The first network node of claim 9, wherein the at least one processor is further configured to: Encoder parameters generated during training of the first encoder are sent to a third network node, wherein the third network node comprises a user equipment (UE).

13. The first network node of claim 9, wherein the at least one processor is further configured to: Second input information is sent to the second network node, wherein the first input information includes the second input information.

14. The first network node of claim 13, wherein the at least one processor is further configured to: The second input information is received from one or more user equipment (UE), wherein the second input information includes one or more measurements of one or more signals transmitted by a base station.

15. The first network node of claim 13, wherein the first input information further comprises third input information received by the second network node from a third network node, wherein the first network node comprises a first user equipment (UE) vendor specific server, and wherein the third network node comprises a second user equipment (UE) vendor specific server different from the first UE vendor specific server.

16. The first network node of claim 9, wherein the first input information comprises second input information received by the second network node from a third network node, wherein the second network node comprises a base station vendor specific server, wherein the third network node comprises a base station, and wherein the second input information comprises measurement information generated by the third network node.

17. A method of wireless communication performed by a first network node, the method comprising: generating training information, wherein the training information comprises first input information for a first encoder of the first network node and output information generated by the first encoder based on the first input information; as well as The training information is sent to a second network node for training a second encoder of the second network node.

18. The method of claim 17, wherein the first input information and the output information are included in one or more input-output tuples of the training information, wherein the first input information includes channel state feedback (CSF) information, and the output information includes encoded CSF information.

19. The method of claim 17, wherein the first network node comprises a base station vendor specific server and the second network node comprises a user equipment (UE) vendor specific server.

20. The method according to claim 17, further comprising: Second input information is received from the second network node, wherein the first input information includes the second input information, wherein the second network node receives the second input information from one or more user equipments (UEs), and wherein the second input information includes one or more measurements of one or more signals sent by a base station.

21. The method according to claim 20, further comprising: Third input information is received from a third network node, wherein the second network node includes a first user equipment (UE) vendor specific server, and wherein the third network node includes a second user equipment (UE) vendor specific server different from the first UE vendor specific server.

22. The method according to claim 17, further comprising Second input information is received from a third network node, wherein the first input information includes the second input information, wherein the third network node includes a base station, and wherein the second input information includes measurement information generated by the third network node.

23. The method according to claim 17, further comprising: training the first encoder using the first input information, wherein generating the training information is performed after training the first encoder; as well as The first input information is used to train a first decoder of the first network node.

24. A first network node, the first network node comprising: Memory; and at least one processor coupled to the memory, wherein the at least one processor is configured to: generating training information, wherein the training information comprises first input information for a first encoder of the first network node and output information generated by the first encoder based on the first input information; as well as The training information is sent to a second network node for training a second encoder of the second network node.

25. The first network node of claim 24, wherein the first input information and the output information are included in one or more input-output tuples of the training information, wherein the first input information includes channel state feedback (CSF) information and the output information includes encoded CSF information.

26. The first network node of claim 24, wherein the first network node comprises a base station vendor specific server and the second network node comprises a user equipment (UE) vendor specific server.

27. The first network node of claim 24, wherein the at least one processor is further configured to: Second input information is received from the second network node, wherein the first input information includes the second input information, wherein the second network node receives the second input information from one or more user equipments (UEs), and wherein the second input information includes one or more measurements of one or more signals sent by a base station.

28. The first network node of claim 27, wherein the at least one processor is further configured to: Third input information is received from a third network node, wherein the second network node includes a first user equipment (UE) vendor specific server, and wherein the third network node includes a second user equipment (UE) vendor specific server different from the first UE vendor specific server.

29. The first network node of claim 24, wherein the at least one processor is further configured to: Second input information is received from a third network node, wherein the first input information includes the second input information, and wherein the third network node includes a base station, and wherein the second input information includes measurement information generated by the third network node.

30. The first network node of claim 24, wherein the at least one processor is further configured to: training the first encoder using the first input information, wherein generating the training information is performed after training the first encoder; and The first input information is used to train a first decoder of the first network node.

Images