Assistant information to align dataset for encoder and decoder training
By exchanging assistant information and using identifiers and reference signals for data collection, the misalignment issue between decoder and encoder models is resolved, improving communication reliability in wireless systems.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-10-04
- Publication Date
- 2026-04-09
AI Technical Summary
Misalignment between training data for decoder and encoder models in wireless communications systems leads to incompatibility and inconsistencies in transmissions.
Exchange of assistant information, including datasets and models, between network and user equipment to align encoder and decoder training, using identifiers and reference signals for data collection.
Improves communication reliability by ensuring alignment between encoder and decoder models, enhancing transmission compatibility and reducing inconsistencies.
Smart Images

Figure CN2024123236_09042026_PF_FP_ABST
Abstract
Description
ASSISTANT INFORMATION TO ALIGN DATASET FOR ENCODER AND DECODER TRAINING
[0001] FIELD OF TECHNOLOGY
[0002] The following relates to wireless communications, including techniques for transmission of assistant information to align dataset for encoder and decoder training.BACKGROUND
[0003] Wireless communications systems are widely deployed to provide various types of communication content such as voice, video, packet data, messaging, broadcast, and so on. These systems may be capable of supporting communication with multiple users by sharing the available system resources (e.g., time, frequency, and power) . Examples of such multiple-access systems include fourth generation (4G) systems such as Long Term Evolution (LTE) systems, LTE-Advanced (LTE-A) systems, or LTE-A Pro systems, and fifth generation (5G) systems which may be referred to as New Radio (NR) systems. These systems may employ technologies such as code division multiple access (CDMA) , time division multiple access (TDMA) , frequency division multiple access (FDMA) , orthogonal FDMA (OFDMA) , or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM) .
[0004] A wireless multiple-access communications system may include one or more base stations, each supporting wireless communication for communication devices, which may be known as user equipment (UE) . In some examples, a UE may encode messages to a network entity, which may be decoded at the network entity for reception.SUMMARY
[0005] The systems, methods, and devices of this disclosure each have several innovative aspects, no single one of which is solely responsible for the desirable attributes disclosed herein.
[0006] A method for wireless communications by a node entity is described. The method may include receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training, transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both, receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection, and performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0007] A node entity for wireless communications is described. The node entity may include one or more memories storing processor executable code, and one or more processors coupled with the one or more memories. The one or more processors may individually or collectively be operable to execute the code to cause the node entity to receive a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training, transmit, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both, receive, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection, and perform the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0008] Another node entity for wireless communications is described. The node entity may include means for receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training, means for transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both, means for receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection, and means for performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0009] A non-transitory computer-readable medium storing code for wireless communications is described. The code may include instructions executable by one or more processors to receive a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training, transmit, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both, receive, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection, and perform the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0010] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the identifier indicates a first dataset associated with developing a decoder, a second dataset for generating a mapping between a set of decoder inputs and a set of decoder outputs associated with the decoder training, a third dataset for performing the encoder training, a fourth dataset for generating a mapping between a set of encoder inputs and a set of encoder outputs associated with the decoder training, or a combination thereof.
[0011] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the identifier includes a pairing identifier indicating a model pair including a first decoder model and a first encoder model, a model identifier indicating the first decoder model or the first encoder model, or both. In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the second message indicates the first decoder model, the first encoder model, or the model pair.
[0012] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the identifier of the first message indicates collected data associated with generation of a first dataset associated with the decoder training and the second message indicates the collected data.
[0013] Some examples of the method, node entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for receiving, based on transmitting the second message, a reference signal configuration indicating the reference signal resources in accordance with the one or more decoder models, the one or more datasets, or both, where receiving the one or more reference signals may be based on receiving the reference signal configuration and performing one or more measurements based on receiving the one or more reference signals to collect data based on the one or more measurement, and where performing the encoder training may be based on receiving the one or more reference signals.
[0014] Some examples of the method, node entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for receiving, prior to receiving the first message, one or more additional reference signals and transmitting data collected from the one or more additional reference signals for use by a network entity to perform the decoder training, where the one or more reference signals received via the reference signal resources may be transmitted in accordance with the decoder training.
[0015] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the one or more additional reference signals may be transmitted in accordance with a first spatial configuration, and the one or more reference signals may be transmitted in accordance with the first spatial configuration.
[0016] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the second message requesting the reference signal resources indicates the identifier.
[0017] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the second message includes a single bit having a first value, the first value indicating the request for the reference signal resources.
[0018] Some examples of the method, node entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for determining a decoder model from a set of decoder models based on the identifier, where performing the encoder training may be based on the determined decoder model.
[0019] Some examples of the method, node entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for receiving the one or more reference signals with a spatial configuration associated with the identifier and corresponding to the decoder training.
[0020] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the spatial configuration includes an analog beamforming configuration, a digital beamforming configuration, an antenna element to port virtualization, a downtilt value, a spatial filter, a spatial relationship, or a combination thereof.
[0021] A method for wireless communications by a node entity is described. The method may include receiving a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity, transmitting a request for the one or more model parameters based on receiving the first message including the identifier, and receiving a second message including the one or more model parameters based on transmitting the request.
[0022] A node entity for wireless communications is described. The node entity may include one or more memories storing processor executable code, and one or more processors coupled with the one or more memories. The one or more processors may individually or collectively be operable to execute the code to cause the node entity to receive a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity, transmit a request for the one or more model parameters based on receiving the first message including the identifier, and receive a second message including the one or more model parameters based on transmitting the request.
[0023] Another node entity for wireless communications is described. The node entity may include means for receiving a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity, means for transmitting a request for the one or more model parameters based on receiving the first message including the identifier, and means for receiving a second message including the one or more model parameters based on transmitting the request.
[0024] A non-transitory computer-readable medium storing code for wireless communications is described. The code may include instructions executable by one or more processors to receive a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity, transmit a request for the one or more model parameters based on receiving the first message including the identifier, and receive a second message including the one or more model parameters based on transmitting the request.
[0025] Some examples of the method, node entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for transmitting the request for the one or more model parameters based on determining that the one or more model parameters corresponding to the identifier may be needed by the node entity.
[0026] Some examples of the method, node entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for receiving, prior to receiving the first message, one or more reference signals associated with the encoder training and the decoder training.
[0027] Some examples of the method, node entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for transmitting data collected from the one or more reference signals for use by a network entity to perform the decoder training and the encoder training, where receiving the first message may be based on transmitting the data.
[0028] In some examples of the method, node entities, and non-transitory computer-readable medium described herein, the request for the one or more model parameters indicates the identifier.
[0029] Details of one or more implementations of the subject matter described in this disclosure are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will become apparent from the description, the drawings, and the claims. Note that the relative dimensions of the following figures may not be drawn to scale.BRIEF DESCRIPTION OF THE DRAWINGS
[0030] FIG. 1 shows an example of a wireless communications system that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0031] FIG. 2 shows an example of a wireless communications system that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0032] FIG. 3 shows an example of a process flow that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0033] FIG. 4 shows an example of a process flow that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0034] FIG. 5 shows an example of a process flow that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0035] FIGs. 6 and 7 show block diagrams of devices that support techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0036] FIG. 8 shows a block diagram of a communications manager that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0037] FIG. 9 shows a diagram of a system including a device that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.
[0038] FIGs. 10 through 12 show flowcharts illustrating methods that support techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure.DETAILED DESCRIPTION
[0039] In some cases, a user equipment (UE) may encode messages for transmission to a network entity, and the network entity may decode the messages to obtain transmission payloads. In some examples, the network entity may transmit one or more reference signals for data collection, and the collected data may be used to perform training for a decoder at the network entity, an encoder at the UE, or both. For example, the UE may receive the one or more reference signals and perform measurements, and the UE may transmit at least some of the data to the network entity, to a training entity, or both, to perform the encoder and decoder training. The data may include training data used to train machine learning models (e.g., artificial intelligence models) , such as an encoder model or a decoder model, validation data, testing data, or a combination thereof. In some cases, however, misalignment between the training data for the decoder and encoder models may cause the generated encoder and decoder to be incompatible, which may cause inconsistencies in transmissions.
[0040] In accordance with examples as described herein, a node entity (e.g., a UE and / or a UE server) and a network entity may exchange assistant information to improve alignment between data used for training and generating encoders and decoders. In some examples, the network entity may transmit information corresponding to a dataset used in network-side training (e.g., decoder training, decoder and encoder training) , such as a dataset used in generating a decoder or encoder (e.g., model parameters) , intermediate datasets (e.g., encoder or decoder inputs and outputs) , or other data. Additionally, or alternatively, the network entity may transmit an indication of one or more models (e.g., a model or model pair) trained during the network-side training. The dataset and one or more models may be indicated using one or more identifiers, such as association identifiers (e.g., for datasets) , model identifiers (e.g., for individual models) , and pairing identifiers (e.g., for model pairs or dataset pairs) . In some examples, the node entity may request one or more reference signals to collect data for encoder training, and the node entity may include the one or more identifiers, thereby facilitating alignment between the data collected via reference signals used for encoder generation at the node entity and decoder generation at the network entity. Accordingly, the generated encoder and decoder may be aligned, improving communication reliability between the node entity (e.g., the UE) and the network entity.
[0041] Aspects of the disclosure are initially described in the context of wireless communications systems. Aspects of the disclosure are additionally described with reference to process flows. Aspects of the disclosure are further illustrated by and described with reference to apparatus diagrams, system diagrams, and flowcharts that relate to techniques for transmission of assistant information to align dataset for encoder and decoder training.
[0042] FIG. 1 shows an example of a wireless communications system 100 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The wireless communications system 100 may include one or more devices, such as one or more network devices (e.g., network entities 105) , one or more UEs 115, and a core network 130. In some examples, the wireless communications system 100 may be a Long Term Evolution (LTE) network, an LTE-Advanced (LTE-A) network, an LTE-A Pro network, a New Radio (NR) network, or a network operating in accordance with other systems and radio technologies, including future systems and radio technologies not explicitly mentioned herein.
[0043] The network entities 105 may be dispersed throughout a geographic area to form the wireless communications system 100 and may include devices in different forms or having different capabilities. In various examples, a network entity 105 may be referred to as a network element, a mobility element, a radio access network (RAN) node, or network equipment, among other nomenclature. In some examples, network entities 105 and UEs 115 may wirelessly communicate via communication link (s) 125 (e.g., a radio frequency (RF) access link) . For example, a network entity 105 may support a coverage area 110 (e.g., a geographic coverage area) over which the UEs 115 and the network entity 105 may establish the communication link (s) 125. The coverage area 110 may be an example of a geographic area over which a network entity 105 and a UE 115 may support the communication of signals according to one or more radio access technologies (RATs) .
[0044] The UEs 115 may be dispersed throughout a coverage area 110 of the wireless communications system 100, and each UE 115 may be stationary, or mobile, or both at different times. The UEs 115 may be devices in different forms or having different capabilities. Some example UEs 115 are illustrated in FIG. 1. The UEs 115 described herein may be capable of supporting communications with various types of devices in the wireless communications system 100 (e.g., other wireless communication devices, including UEs 115 or network entities 105) , as shown in FIG. 1.
[0045] As described herein, a node of the wireless communications system 100, which may be referred to as a network node, or a wireless node, may be a network entity 105 (e.g., any network entity described herein) , a UE 115 (e.g., any UE described herein) , a network controller, an apparatus, a device, a computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, a node may be a UE 115. As another example, a node may be a network entity 105. As another example, a first node may be configured to communicate with a second node or a third node. In one aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a UE 115. In another aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a network entity 105. In yet other aspects of this example, the first, second, and third nodes may be different relative to these examples. Similarly, reference to a UE 115, network entity 105, apparatus, device, computing system, or the like may include disclosure of the UE 115, network entity 105, apparatus, device, computing system, or the like being a node. For example, disclosure that a UE 115 is configured to receive information from a network entity 105 also discloses that a first node is configured to receive information from a second node.
[0046] In some examples, network entities 105 may communicate with a core network 130, or with one another, or both. For example, network entities 105 may communicate with the core network 130 via backhaul communication link (s) 120 (e.g., in accordance with an S1, N2, N3, or other interface protocol) . In some examples, network entities 105 may communicate with one another via backhaul communication link (s) 120 (e.g., in accordance with an X2, Xn, or other interface protocol) either directly (e.g., directly between network entities 105) or indirectly (e.g., via the core network 130) . In some examples, network entities 105 may communicate with one another via a midhaul communication link 162 (e.g., in accordance with a midhaul interface protocol) or a fronthaul communication link 168 (e.g., in accordance with a fronthaul interface protocol) , or any combination thereof. The backhaul communication link (s) 120, midhaul communication links 162, or fronthaul communication links 168 may be or include one or more wired links (e.g., an electrical link, an optical fiber link) or one or more wireless links (e.g., a radio link, a wireless optical link) , among other examples or various combinations thereof. A UE 115 may communicate with the core network 130 via a communication link 155.
[0047] One or more of the network entities 105 or network equipment described herein may include or may be referred to as a base station 140 (e.g., a base transceiver station, a radio base station, an NR base station, an access point, a radio transceiver, a NodeB, an eNodeB (eNB) , a next-generation NodeB or giga-NodeB (either of which may be referred to as a gNB) , a 5G NB, a next-generation eNB (ng-eNB) , a Home NodeB, a Home eNodeB, or other suitable terminology) . In some examples, a network entity 105 (e.g., a base station 140) may be implemented in an aggregated (e.g., monolithic, standalone) base station architecture, which may be configured to utilize a protocol stack that is physically or logically integrated within one network entity (e.g., a network entity 105 or a single RAN node, such as a base station 140) .
[0048] In some examples, a network entity 105 may be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) , which may be configured to utilize a protocol stack that is physically or logically distributed among multiple network entities (e.g., network entities 105) , such as an integrated access and backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance) , or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN) ) . For example, a network entity 105 may include one or more of a central unit (CU) , such as a CU 160, a distributed unit (DU) , such as a DU 165, a radio unit (RU) , such as an RU 170, a RAN Intelligent Controller (RIC) , such as an RIC 175 (e.g., a Near-Real Time RIC (Near-RT RIC) , a Non-Real Time RIC (Non-RT RIC) ) , a Service Management and Orchestration (SMO) system, such as an SMO system 180, or any combination thereof. An RU 170 may also be referred to as a radio head, a smart radio head, a remote radio head (RRH) , a remote radio unit (RRU) , or a transmission reception point (TRP) . One or more components of the network entities 105 in a disaggregated RAN architecture may be co-located, or one or more components of the network entities 105 may be located in distributed locations (e.g., separate physical locations) . In some examples, one or more of the network entities 105 of a disaggregated RAN architecture may be implemented as virtual units (e.g., a virtual CU (VCU) , a virtual DU (VDU) , a virtual RU (VRU) ) .
[0049] The split of functionality between a CU 160, a DU 165, and an RU 170 is flexible and may support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, or any combinations thereof) are performed at a CU 160, a DU 165, or an RU 170. For example, a functional split of a protocol stack may be employed between a CU 160 and a DU 165 such that the CU 160 may support one or more layers of the protocol stack and the DU 165 may support one or more different layers of the protocol stack. In some examples, the CU 160 may host upper protocol layer (e.g., layer 3 (L3) , layer 2 (L2) ) functionality and signaling (e.g., Radio Resource Control (RRC) , service data adaptation protocol (SDAP) , Packet Data Convergence Protocol (PDCP) ) . The CU 160 (e.g., one or more CUs) may be connected to a DU 165 (e.g., one or more DUs) or an RU 170 (e.g., one or more RUs) , or some combination thereof, and the DUs 165, RUs 170, or both may host lower protocol layers, such as layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, and may each be at least partially controlled by the CU 160. Additionally, or alternatively, a functional split of the protocol stack may be employed between a DU 165 and an RU 170 such that the DU 165 may support one or more layers of the protocol stack and the RU 170 may support one or more different layers of the protocol stack. The DU 165 may support one or multiple different cells (e.g., via one or multiple different RUs, such as an RU 170) . In some cases, a functional split between a CU 160 and a DU 165 or between a DU 165 and an RU 170 may be within a protocol layer (e.g., some functions for a protocol layer may be performed by one of a CU 160, a DU 165, or an RU 170, while other functions of the protocol layer are performed by a different one of the CU 160, the DU 165, or the RU 170) . A CU 160 may be functionally split further into CU control plane (CU-CP) and CU user plane (CU-UP) functions. A CU 160 may be connected to a DU 165 via a midhaul communication link 162 (e.g., F1, F1-c, F1-u) , and a DU 165 may be connected to an RU 170 via a fronthaul communication link 168 (e.g., open fronthaul (FH) interface) . In some examples, a midhaul communication link 162 or a fronthaul communication link 168 may be implemented in accordance with an interface (e.g., a channel) between layers of a protocol stack supported by respective network entities (e.g., one or more of the network entities 105) that are in communication via such communication links.
[0050] In some wireless communications systems (e.g., the wireless communications system 100) , infrastructure and spectral resources for radio access may support wireless backhaul link capabilities to supplement wired backhaul connections, providing an IAB network architecture (e.g., to a core network 130) . In some cases, in an IAB network, one or more of the network entities 105 (e.g., network entities 105 or IAB node (s) 104) may be partially controlled by each other. The IAB node (s) 104 may be referred to as a donor entity or an IAB donor. A DU 165 or an RU 170 may be partially controlled by a CU 160 associated with a network entity 105 or base station 140 (such as a donor network entity or a donor base station) . The one or more donor entities (e.g., IAB donors) may be in communication with one or more additional devices (e.g., IAB node (s) 104) via supported access and backhaul links (e.g., backhaul communication link (s) 120) . IAB node (s) 104 may include an IAB mobile termination (IAB-MT) controlled (e.g., scheduled) by one or more DUs (e.g., DUs 165) of a coupled IAB donor. An IAB-MT may be equipped with an independent set of antennas for relay of communications with UEs 115 or may share the same antennas (e.g., of an RU 170) of IAB node (s) 104 used for access via the DU 165 of the IAB node (s) 104 (e.g., referred to as virtual IAB-MT (vIAB-MT) ) . In some examples, the IAB node (s) 104 may include one or more DUs (e.g., DUs 165) that support communication links with additional entities (e.g., IAB node (s) 104, UEs 115) within the relay chain or configuration of the access network (e.g., downstream) . In such cases, one or more components of the disaggregated RAN architecture (e.g., the IAB node (s) 104 or components of the IAB node (s) 104) may be configured to operate according to the techniques described herein.
[0051] In the case of the techniques described herein applied in the context of a disaggregated RAN architecture, one or more components of the disaggregated RAN architecture may be configured to support techniques for transmission of assistant information to align dataset for encoder and decoder training as described herein. For example, some operations described as being performed by a UE 115 or a network entity 105 (e.g., a base station 140) may additionally, or alternatively, be performed by one or more components of the disaggregated RAN architecture (e.g., components such as an IAB node, a DU 165, a CU 160, an RU 170, an RIC 175, an SMO system 180) .
[0052] A UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable terminology, where the “device” may also be referred to as a unit, a station, a terminal, or a client, among other examples. A UE 115 may also include or may be referred to as a personal electronic device such as a cellular phone, a personal digital assistant (PDA) , a tablet computer, a laptop computer, or a personal computer. In some examples, a UE 115 may include or be referred to as a wireless local loop (WLL) station, an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine type communications (MTC) device, among other examples, which may be implemented in various objects such as appliances, vehicles, or meters, among other examples.
[0053] The UEs 115 described herein may be able to communicate with various types of devices, such as UEs 115 that may sometimes operate as relays, as well as the network entities 105 and the network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, among other examples, as shown in FIG. 1.
[0054] The UEs 115 and the network entities 105 may wirelessly communicate with one another via the communication link (s) 125 (e.g., one or more access links) using resources associated with one or more carriers. The term “carrier” may refer to a set of RF spectrum resources having a defined PHY layer structure for supporting the communication link (s) 125. For example, a carrier used for the communication link (s) 125 may include a portion of an RF spectrum band (e.g., a bandwidth part (BWP) ) that is operated according to one or more PHY layer channels for a given RAT (e.g., LTE, LTE-A, LTE-A Pro, NR) . Each PHY layer channel may carry acquisition signaling (e.g., synchronization signals, system information) , control signaling that coordinates operation for the carrier, user data, or other signaling. The wireless communications system 100 may support communication with a UE 115 using carrier aggregation or multi-carrier operation. A UE 115 may be configured with multiple downlink component carriers and one or more uplink component carriers according to a carrier aggregation configuration. Carrier aggregation may be used with both frequency division duplexing (FDD) and time division duplexing (TDD) component carriers. Communication between a network entity 105 and other devices may refer to communication between the devices and any portion (e.g., entity, sub-entity) of a network entity 105. For example, the terms “transmitting, ” “receiving, ” or “communicating, ” when referring to a network entity 105, may refer to any portion of a network entity 105 (e.g., a base station 140, a CU 160, a DU 165, a RU 170) of a RAN communicating with another device (e.g., directly or via one or more other network entities, such as one or more of the network entities 105) .
[0055] Signal waveforms transmitted via a carrier may be made up of multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM) ) . In a system employing MCM techniques, a resource element may refer to resources of one symbol period (e.g., a duration of one modulation symbol) and one subcarrier, in which case the symbol period and subcarrier spacing may be inversely related. The quantity of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both) , such that a relatively higher quantity of resource elements (e.g., in a transmission duration) and a relatively higher order of a modulation scheme may correspond to a relatively higher rate of communication. A wireless communications resource may refer to a combination of an RF spectrum resource, a time resource, and a spatial resource (e.g., a spatial layer, a beam) , and the use of multiple spatial resources may increase the data rate or data integrity for communications with a UE 115.
[0056] The time intervals for the network entities 105 or the UEs 115 may be expressed in multiples of a basic time unit which may, for example, refer to a sampling period of Ts=1 / (Δfmax·Nf) seconds, for which Δfmax may represent a supported subcarrier spacing, and Nf may represent a supported discrete Fourier transform (DFT) size. Time intervals of a communications resource may be organized according to radio frames each having a specified duration (e.g., 10 milliseconds (ms) ) . Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023) .
[0057] Each frame may include multiple consecutively-numbered subframes or slots, and each subframe or slot may have the same duration. In some examples, a frame may be divided (e.g., in the time domain) into subframes, and each subframe may be further divided into a quantity of slots. Alternatively, each frame may include a variable quantity of slots, and the quantity of slots may depend on subcarrier spacing. Each slot may include a quantity of symbol periods (e.g., depending on the length of the cyclic prefix prepended to each symbol period) . In some wireless communications systems, such as the wireless communications system 100, a slot may further be divided into multiple mini-slots associated with one or more symbols. Excluding the cyclic prefix, each symbol period may be associated with one or more (e.g., Nf) sampling periods. The duration of a symbol period may depend on the subcarrier spacing or frequency band of operation.
[0058] A subframe, a slot, a mini-slot, or a symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communications system 100 and may be referred to as a transmission time interval (TTI) . In some examples, the TTI duration (e.g., a quantity of symbol periods in a TTI) may be variable. Additionally, or alternatively, the smallest scheduling unit of the wireless communications system 100 may be dynamically selected (e.g., in bursts of shortened TTIs (sTTIs) ) .
[0059] Physical channels may be multiplexed for communication using a carrier according to various techniques. A physical control channel and a physical data channel may be multiplexed for signaling via a downlink carrier, for example, using one or more of time division multiplexing (TDM) techniques, frequency division multiplexing (FDM) techniques, or hybrid TDM-FDM techniques. A control region (e.g., a control resource set (CORESET) ) for a physical control channel may be defined by a set of symbol periods and may extend across the system bandwidth or a subset of the system bandwidth of the carrier. One or more control regions (e.g., CORESETs) may be configured for a set of the UEs 115. For example, one or more of the UEs 115 may monitor or search control regions for control information according to one or more search space sets, and each search space set may include one or multiple control channel candidates in one or more aggregation levels arranged in a cascaded manner. An aggregation level for a control channel candidate may refer to an amount of control channel resources (e.g., control channel elements (CCEs) ) associated with encoded information for a control information format having a given payload size. Search space sets may include common search space sets configured for sending control information to UEs 115 (e.g., one or more UEs) or may include UE-specific search space sets for sending control information to a UE 115 (e.g., a specific UE) .
[0060] In some examples, a network entity 105 (e.g., a base station 140, an RU 170) may be movable and therefore provide communication coverage for a moving coverage area, such as the coverage area 110. In some examples, coverage areas 110 (e.g., different coverage areas) associated with different technologies may overlap, but the coverage areas 110 (e.g., different coverage areas) may be supported by the same network entity (e.g., a network entity 105) . In some other examples, overlapping coverage areas, such as a coverage area 110, associated with different technologies may be supported by different network entities (e.g., the network entities 105) . The wireless communications system 100 may include, for example, a heterogeneous network in which different types of the network entities 105 support communications for coverage areas 110 (e.g., different coverage areas) using the same or different RATs.
[0061] The wireless communications system 100 may be configured to support ultra-reliable communications or low-latency communications, or various combinations thereof. For example, the wireless communications system 100 may be configured to support ultra-reliable low-latency communications (URLLC) . The UEs 115 may be designed to support ultra-reliable, low-latency, or critical functions. Ultra-reliable communications may include private communication or group communication and may be supported by one or more services such as push-to-talk, video, or data. Support for ultra-reliable, low-latency functions may include prioritization of services, and such services may be used for public safety or general commercial applications. The terms ultra-reliable, low-latency, and ultra-reliable low-latency may be used interchangeably herein.
[0062] In some examples, a UE 115 may be configured to support communicating directly with other UEs (e.g., one or more of the UEs 115) via a device-to-device (D2D) communication link, such as a D2D communication link 135 (e.g., in accordance with a peer-to-peer (P2P) , D2D, or sidelink protocol) . In some examples, one or more UEs 115 of a group that are performing D2D communications may be within the coverage area 110 of a network entity 105 (e.g., a base station 140, an RU 170) , which may support aspects of such D2D communications being configured by (e.g., scheduled by) the network entity 105. In some examples, one or more UEs 115 of such a group may be outside the coverage area 110 of a network entity 105 or may be otherwise unable to or not configured to receive transmissions from a network entity 105. In some examples, groups of the UEs 115 communicating via D2D communications may support a one-to-many (1: M) system in which each UE 115 transmits to one or more of the UEs 115 in the group. In some examples, a network entity 105 may facilitate the scheduling of resources for D2D communications. In some other examples, D2D communications may be carried out between the UEs 115 without an involvement of a network entity 105.
[0063] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an evolved packet core (EPC) or 5G core (5GC) , which may include at least one control plane entity that manages access and mobility (e.g., a mobility management entity (MME) , an access and mobility management function (AMF) ) and at least one user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW) , a Packet Data Network (PDN) gateway (P-GW) , or a user plane function (UPF) ) . The control plane entity may manage non-access stratum (NAS) functions such as mobility, authentication, and bearer management for the UEs 115 served by the network entities 105 (e.g., base stations 140) associated with the core network 130. User IP packets may be transferred through the user plane entity, which may provide IP address allocation as well as other functions. The user plane entity may be connected to IP services 150 for one or more network operators. The IP services 150 may include access to the Internet, Intranet (s) , an IP Multimedia Subsystem (IMS) , or a Packet-Switched Streaming Service.
[0064] The wireless communications system 100 may operate using one or more frequency bands, which may be in the range of 300 megahertz (MHz) to 300 gigahertz (GHz) . Generally, the region from 300 MHz to 3 GHz is known as the ultra-high frequency (UHF) region or decimeter band because the wavelengths range from approximately one decimeter to one meter in length. UHF waves may be blocked or redirected by buildings and environmental features, which may be referred to as clusters, but the waves may penetrate structures sufficiently for a macro cell to provide service to the UEs 115 located indoors. Communications using UHF waves may be associated with smaller antennas and shorter ranges (e.g., less than one hundred kilometers) compared to communications using the smaller frequencies and longer waves of the high frequency (HF) or very high frequency (VHF) portion of the spectrum below 300 MHz.
[0065] The wireless communications system 100 may utilize both licensed and unlicensed RF spectrum bands. For example, the wireless communications system 100 may employ License Assisted Access (LAA) , LTE-Unlicensed (LTE-U) RAT, or NR technology using an unlicensed band such as the 5 GHz industrial, scientific, and medical (ISM) band. While operating using unlicensed RF spectrum bands, devices such as the network entities 105 and the UEs 115 may employ carrier sensing for collision detection and avoidance. In some examples, operations using unlicensed bands may be based on a carrier aggregation configuration in conjunction with component carriers operating using a licensed band (e.g., LAA) . Operations using unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, among other examples.
[0066] A network entity 105 (e.g., a base station 140, an RU 170) or a UE 115 may be equipped with multiple antennas, which may be used to employ techniques such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communications, or beamforming. The antennas of a network entity 105 or a UE 115 may be located within one or more antenna arrays or antenna panels, which may support MIMO operations or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly, such as an antenna tower. In some examples, antennas or antenna arrays associated with a network entity 105 may be located at diverse geographic locations. A network entity 105 may include an antenna array with a set of rows and columns of antenna ports that the network entity 105 may use to support beamforming of communications with a UE 115. Likewise, a UE 115 may include one or more antenna arrays that may support various MIMO or beamforming operations. Additionally, or alternatively, an antenna panel may support RF beamforming for a signal transmitted via an antenna port.
[0067] Beamforming, which may also be referred to as spatial filtering, directional transmission, or directional reception, is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a network entity 105, a UE 115) to shape or steer an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining the signals communicated via antenna elements of an antenna array such that some signals propagating along particular orientations with respect to an antenna array experience constructive interference while others experience destructive interference. The adjustment of signals communicated via the antenna elements may include a transmitting device or a receiving device applying amplitude offsets, phase offsets, or both to signals carried via the antenna elements associated with the device. The adjustments associated with each of the antenna elements may be defined by a beamforming weight set associated with a particular orientation (e.g., with respect to the antenna array of the transmitting device or receiving device, or with respect to some other orientation) .
[0068] In some examples, transmissions by a device (e.g., by a network entity 105 or a UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or beamforming to generate a combined beam for transmission (e.g., from a network entity 105 to a UE 115) . The UE 115 may report feedback that indicates precoding weights for one or more beam directions, and the feedback may correspond to a configured set of beams across a system bandwidth or one or more sub-bands. The network entity 105 may transmit a reference signal (e.g., a cell-specific reference signal (CRS) , a channel state information reference signal (CSI-RS) ) , which may be precoded or unprecoded. The UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., a multi-panel type codebook, a linear combination type codebook, a port selection type codebook) . Although these techniques are described with reference to signals transmitted along one or more directions by a network entity 105 (e.g., a base station 140, an RU 170) , a UE 115 may employ similar techniques for transmitting signals multiple times along different directions (e.g., for identifying a beam direction for subsequent transmission or reception by the UE 115) or for transmitting a signal along a single direction (e.g., for transmitting data to a receiving device) .
[0069] In some examples, to provide channel state information (CSI) feedback, the UE 115 may use machine learning (e.g., artificial intelligence) techniques. For example, in addition or alternatively to PMI or codebook-based feedback, the UE 115 and a network entity 105 may use machine learning techniques to generate an encoder and decoder for signal transmissions. For example, an encoder may perform functions corresponding a PMI searching algorithm (e.g., as used in non-machine learning implementations) , while a decoder may perform functions similar to those of a PMI codebook used to translate CSI reporting bits from the UE 115 into a PMI codeword. In some examples, the encoder may receive, as in puts, a downlink channel matrix (e.g., H, corresponding to a raw channel or a channel pre-whitened by the UE 115 based on a demodulation filter) , one or more downlink precoders (e.g., V) , an interference covariance matrix (e.g., Rnm) , or a combination thereof, to generate a message. The decoder may use the generated message and output the downlink channel matrix, the one or more downlink precoders, the interference covariance matrix, a transmit covariance matric, a raw downlink channel or a whitened downlink channel, or a combination thereof.
[0070] In some examples, the training for the decoder and encoder may be performed by a single entity. For example, the network entity 105 (e.g., or the UE 115 or a training entity, such as a network server) may perform training for both the encoder and decoder, and the network entity 105 (e.g., or another entity) may transmit information to the UE 115 for deployment of the encoder. In some other examples, the encoder may be trained at the UE-side (e.g., by the UE 115 or a server) and the decoder may be trained at the network-side (e.g., by a server or the network entity 105) , and the training may be performed jointly, with collaboration occurring during the training process (e.g., exchanging of activation and gradient for each iteration, model structure, input format alignment, model testing) , or separately, with some collaboration occurring after one of the trainings is performed (e.g., for the decoder or encoder) .
[0071] In some examples, the network entity 105 may transmit one or more reference signals for data collection, and the collected data may be used to perform training for a decoder at the network entity 105, an encoder at the UE 115, or both. For example, the UE 115 may receive the one or more reference signals and perform measurements, and the UE 115 may transmit at least some of the data to the network entity 105, to a training entity, or both, to perform the encoder and decoder training. The data may include training data used to train machine learning models (e.g., artificial intelligence models) , such as an encoder model or a decoder model. In some cases, however, misalignment between the training data for the decoder and encoder models may cause the generated encoder and decoder to be incompatible. Additionally, using a misaligned model trained using a dataset corresponding to a different scenario or configuration than during an inference phase may cause performance degradation during communications.
[0072] In accordance with examples as described herein, a UE 115 and a network entity 105 may exchange assistant information to improve alignment between data used for training and generating encoders and decoders. In some examples, the network entity 105 may transfer a dataset used in network-side training (e.g., decoder training, decoder and encoder training) , such as a dataset used in generating a decoder or encoder (e.g., model parameters) , intermediate datasets (e.g., encoder or decoder inputs and outputs) , or other data. Additionally, or alternatively, the network entity 105 may transfer one or more models (e.g., a model or model pair) trained during the network-side training. The dataset and one or more models may be indicated using one or more identifiers, such as association identifiers (e.g., for datasets) , model identifiers (e.g., for individual models) , and pairing identifiers (e.g., for model pairs or dataset pairs) .
[0073] In some examples, the UE 115 may request one or more reference signals to collect data for encoder training. For example, the network entity 105 may transmit the one or more reference signals based on the request, and the UE 115 may perform measurements and use collected data to perform the encoder training. In some examples, the UE 115 may include the one or more identifiers in the request for the one or more reference signals. As such, the one or more reference signals transmitted by the network entity may be aligned (e.g., use same or similar parameters, such as a same spatial configuration) with previous reference signals transmitted for the decoder training at the network side, thereby facilitating alignment between reference signals used for encoder generation at the UE 115 (e.g., or a server) and decoder generation at the network entity 105 (e.g., or a server) . Accordingly, the generated encoder and decoder may be aligned, improving communication reliability between the UE 115 and the network entity 105.
[0074] FIG. 2 shows an example of a wireless communications system 200 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The wireless communications system 200 may include a network entity 105-a and a UE 115-a, which may be examples of corresponding devices as described herein. In some examples, the wireless communications system 200 may include a network server 205 and a UE server 210 (e.g., training servers) . In some cases, functions performed by the network server 205 may generally be performed by the network entity 105-a, or another network entity 105. Similarly, the UE 115-a may, in some cases, perform functions described with reference to the UE server 210, or the UE server 210 may perform functions described with reference to the UE 115-a. Additionally, or alternatively, a node entity 215 may refer to one or more devices (e.g., a UE 115) that perform functions described with reference to the UE 115-a and the UE server 210.
[0075] In accordance with examples as described herein, the network entity 105-a and the node entity 215 (e.g., the UE 115-a and / or the UE server 210) may be configured to exchange assistant information to facilitate alignment during encoder and decoder training. In some examples, the decoder training at the network-side (e.g., at the network entity 105-a and the network server 205) may occur before the encoder training at the UE-side (e.g., at the UE 115-a and the UE server 210) . The network entity 105-a may transmit assistant information 220 to the UE 115-a to facilitate the encoder training after the decoder training at the network-side. In some cases, the assistant information 220 may be generated by the network server 205 and transmitted to the network entity 105-a for transmission to the UE 115-a, and the UE 115-a may forward the information to the UE server 210. Additionally, or alternatively, the network server 205 may directly transmit the assistant information to the UE server 210.
[0076] The assistant information 220 may include information about one or more datasets used in the decoder training at the network entity 105-a, information about the decoder model (e.g., machine learning model) or model pair (e.g., decoder model and encoder model pair, or decoder model pair) used in the decoder training, a trained decoder or encoder, or a combination thereof. In some examples, the assistant information 220 may include one or more identifiers, which may correspond to datasets, models, or model pairs. For example, the assistant information 220 may include an association identifier corresponding to a dataset used in the network-side training, such as corresponding to a dataset used for decoder model training (e.g., training data) , , an intermediate dataset including a set of decoder inputs and a set of decoder outputs (e.g., ) , an intermediate dataset including a set of encoder inputs and a set of encoder outputs (e.g., {v1, z1} ) , or a combination thereof. Additionally, or alternatively, the assistant information 220 may include a model identifier corresponding to a model (e.g., a decoder model) selected for the decoder, a pairing identifier corresponding to a model pair, or both. In some examples, the pairing identifier may correspond to one or more intermediate data sets associated with the decoder training (e.g., and ) .
[0077] For example, in some cases, the assistant information 220 may indicate one or more decoders generated by the network server 205, one or more intermediate data sets, or both. Additionally, the assistant information 220 may include one or more identifiers, such as an association ID, a pairing identifier, or a model identifier. As such, the UE 115-a and the UE server 210 may perform encoder training based on the assistant information 220. While the wireless communications system 200 illustrates an example where the decoder training at the network-side is performed before the encoder training, in some cases, the encoder training at the UE-side may be performed prior to the decoder training at the network-side. In these cases, the UE server 210 or the UE 115-a may generate assistant information 220 associated with the encoder training, and the UE 115-a may transmit the assistant information 220 to the network entity 105-a for use in the decoder training.
[0078] In some cases, such as if the assistant information 220 includes an intermediate dataset (e.g., {v1, z1} or ) or a trained encoder or decoder, the assistant information 220 may be used to facilitate the UE-side encoder training. For example, the encoder training at the UE 115-a or the UE server 210 may use the shared intermediate dataset or trained encoder to develop a reference decoder that corresponds to the decoder trained by the network server 205 (e.g., same or similar parameters to the NW-side decoder) . Additionally, or alternatively, if a trained decoder is shared by the network entity 105-b, the UE server 210 may develop an encoder that is compatible to the trained decoder.
[0079] In some examples, after receiving the assistant information 220, the UE 115-a may transmit a request 225 for one or more reference signals to the network entity 105-a, which may allow the UE 115-a to collect data to be used in the encoder training. In some cases, the request 225 may originate from the UE server 210, and may be indicated to the UE 115-a for the UE 115-a to request the one or more reference signals from the network entity 105-a. In some examples, the UE 115-a may transmit the request 225 via a sounding request or an uplink control message (e.g., a physical uplink control channel (PUCCH) ) , such as a preconfigured uplink control message (e.g., previously configured by the network entity 105-a) .
[0080] In some examples, the request 225 may indicate at least some of the assistant information 220 indicated by the network entity 105-a. For example, the request 225 may include one or more identifiers, such as the identifiers included with the assistant information 220, which may indicate a configuration (e.g., a spatial configuration) for use by the network entity 105-a in transmission of the one or more reference signals. For example, the configuration may match a configuration used for transmission of one or more reference signals used for collecting data for the decoder training. As such, the request 225 may facilitate alignment between the data collected for the encoder training and the data collected for the decoder training.
[0081] Accordingly, the network entity 105-a may transmit one or more reference signals 230 in accordance with the one or more identifiers (e.g., using a configuration associated with the one or more identifiers) , and the UE 115-a may collect data 235 to be used for the encoder training. The UE 115-a may forward the collected data 235 to the UE server 210, which may perform the encoder training in accordance with the collected data 235 and the assistant information 220.
[0082] In some cases, the encoder training and decoder training may be performed independently, without a model or dataset exchange via the assistant information 220. For example, the network entity 105-a and the network server 205 may train the decoder compatible with a reference encoder (e.g., a fully standardized encoder in a standard) based on data collected by the network entity 105-a (e.g., based on one or more reference signal transmissions) . Similarly, node entity 215 (e.g., the UE 115-a and / or the UE server 210) may train the encoder compatible to a reference decoder (e.g., a fully standardized decoder in a standard) using data collected by the UE 115-a (e.g., based on one or more reference signal transmissions) . The node entity 215 and the network entity 105-a may align the trainings, such as the reference decoder and encoder used, based on transmission of one or more identifiers (e.g., pairing identifiers, association identifiers, such as via the assistant information 220) , or based on applicability reporting.
[0083] In some examples, applicability reporting may include exchange of a list of information, such as one or more identifiers, and may be performed after the encoder and decoder trainings. For example, the network entity 105-a may indicate the one or more identifiers (e.g., pairing identifiers, association identifiers) and the UE 115-may report whether the UE 115-a has trained an encoder corresponding to any of the identifiers indicated in the list. In some examples, the UE 115-a may indicate at least one identifier for which the UE 115-a has trained an encoder, and the network entity 105-a may configure the at least one encoder for inference (e.g., machine learning inference) using the decoder model and encoder model.
[0084] In some cases, the network entity 105-a may indicate one or more identifiers (e.g., via assistant information 220, or via other signaling such as an inquiry message) corresponding to one or more models (e.g., encoder models, decoder models) to be used in the encoder training. The UE 115-a may transmit a response message, for example, if the UE 115-a or the UE server 210 determines a need for a model of the one or more models. For example, if the model has not been previously used by the UE 115-a or the UE server 210 or is not stored in a memory of the UE 115-a or the UE server 210, the UE 115-a may transmit the response message to request the network entity 105-a to transmit the model. The network entity 105-a may transmit the model or one or more model parameters corresponding to the model in response.
[0085] Accordingly, the generated encoder and decoder may be aligned based on the assistant information 220, thereby improving communication reliability between the UE 115-a and the network entity 105-a.
[0086] FIG. 3 shows an example of a process flow 300 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The process flow 300 illustrates communications between a network server 305, a network entity 105-b, a UE 115-b, and a UE server 310, which may be examples of corresponding devices as described herein. In some examples, functions performed by the network server 305 may instead be performed by the network entity 105-b, and functions performed by the UE server 310 may instead be performed by the UE 115-b. Additionally, or alternatively, functions performed by the UE 115-b and the UE server 310 may instead be performed by a node entity 315. In some cases, some steps may be performed in a different order than shown, or some steps may be omitted or added to the process flow 300.
[0087] At 320, the network entity 105-a may transmit one or more reference signals associated with decoder training for a decoder at the network-side. The UE 115-b may receive the one or more reference signals and may measure the one or more reference signals to collect data for the decoder training. In some cases, the one or more reference signals may be transmitted in accordance with a reference signal configuration (e.g., a spatial configuration) , which may correspond to an identifier (e.g., an association identifier) previously configured or provided in a reference signal configuration or reference signal triggering. For example, the identifier may indicate the reference signal configuration, which may include spatial filters or spatial relationships such as analog beamforming, antenna element-to-port virtualization, antenna downtilt values, or other configuration aspects. In some other cases, the reference signal configuration or triggering may not indicate the identifier (e.g., association identifier) .
[0088] At 325, the UE 115-b may transmit the collected data to the network entity 105-b. In some cases, the UE 115-b may transmit all collected data to the network entity 105-b. Alternatively, the UE 115-b may categorize the data, such as based on information indicated by the network entity 105-b (e.g., assistant information) . In some cases, the UE 115-a may include the identifier indicated by the network entity at 320 (e.g., if present) , which may be used to label the data. In some examples, the network entity 105-b may transmit the data received from the UE 115-b to the network server 305. The network entity 105-b may receive data from a plurality of UEs 115, such as based on multiple reference signal transmissions, and the network entity 105-b may transmit the data collected from each UE 115 to the network server 305.
[0089] In some cases, at 330, the UE 115-b may perform data collection based on the one or more reference signals received at 320 for performing the encoder training. For example, the one or more reference signals may be used for data collection for both encoder and decoder training. In some examples, the data collected for the encoder training may be labeled by the UE 115-b using the same identifier (e.g., associated identifier) as the data for network-side decoder training.
[0090] At 335, the network server 305 may perform the decoder training based on the data received from the network entity 105-b. The decoder training may be performed based on the data collected from the plurality of UEs 115. For example, decoder training may be performed using data received from UEs 115 indicating a same identifier. In some examples, the decoder training may include training one or more encoder-decoder pairs. Each decoder may correspond to the actual decoder being trained for use by the network entity 105-b in an inference phase, while each encoder may be a reference model used for the training, which may correspond to the one or more reference signals transmitted at 420.
[0091] In some cases, if the network-side data collection includes (e.g., is associated with) an identifier (e.g., an association identifier) , the network server 305 may train an encoder-decoder pair or a decoder accordingly. For example, the network server 305 may train a specialized decoder or encoder-decoder pair per identifier (e.g., per each association identifier) or may train a common decoder or encoder-decoder pair across multiple identifiers (e.g., association identifiers) . In some cases, NW-side data collection may not include association ID (e.g., indicated in a reference signal configuration or other signaling) , and the network server 305 may train encoder-decoder pairs or decoders based on a categorization of the data collected by the plurality of UEs 115. In some cases, the network server 305 may train a common decoder or encoder-decoder pair for all data collected by the plurality of UEs 115, or the network server 305 may categorize datasets and train specialized decoders or encoder-decoder pairs for each category (e.g., each categorized dataset corresponding to the data collected by the plurality of UEs 115) .
[0092] At 340, the network server 305 may transmit assistant information for encoder training at the UE server 310. In some cases, the assistant information may be transmitted directly to the UE server 310, or may be transmitted via the network entity 105-b and the UE 115-b and forwarded to UE server 310 by the UE 115-b. In some examples, as described herein, the assistant information may include one or more intermediate datasets, and each dataset may be assigned a respective identifier (e.g., a pairing identifier, an associated identifier) . Each dataset may include a set encoder inputs and encoder outputs (e.g., {v1, z1} , {v2, z2} ) , or a set of decoder inputs and decoder outputs (e.g., ) . In some examples, if an association identifier is used, the association identifier may indicate collected dataset information at the network-side used to generate the input and output pairs. a Additionally, or alternatively, if a pairing identifier is used, the pairing identifier may indicate a pair of inputs and outputs, which may correspond to inputs and output pairs of a trained encoder, decoder, or encoder-decoder pair. In some examples, an identifier (e.g., the pairing identifier) may indicate (e.g., provide) category information used in NW-side decoder training. Additionally, or alternatively, the network server 305 may indicate one or more decoders or reference encoders (e.g., generated from the decoder training ) , and each decoder or reference encoder may be given a corresponding identifier (e.g., a model identifier, an associated identifier) included in the assistant information. In some cases, the assistant information may indicate a decoder as part of a decoder-encoder pair (e.g., including a reference encoder) , and an identifier (e.g., a pairing identifier, an associated identifier) may be included in the assistant information corresponding to the decoder-encoder pair. In some examples, the assistant information may indicate an identifier (e.g., an associated identifier) for collected data used to develop each decoder or intermediate dataset (e.g., an identifier corresponding to the data indicated at 325) .
[0093] At 345, the UE 115-b may transmit a request for one or more reference signals to be used in data collection for the encoder training. In some cases, the UE 115-b may transmit the request based on an indication from the UE server 310 that (e.g., additional) data may be used for the encoder training. In some examples, the request may include an identifier, which may match the identifier (e.g., an associated identifier, a pairing identifier) indicated in the assistant information at 340 or the identifier corresponding to the one or more reference signals transmitted at 320. As such, the data collected for the encoder training may be aligned with data collected for the decoder training by signaling the identifier. In some cases, the request for the one or more reference signals may be a single-bit indication (e.g., instead of including an identifier) . In these cases, the network entity 105-b may determine a corresponding identifier (e.g., associated identifier) corresponding to the one or more reference signals. For example, the network entity 105-b may select an identifier indicated in the assistant information at 340, or an identifier corresponding to the reference signals transmitted at 320.
[0094] At 350, the network entity 105-b may transmit the one or more reference signals requested by the UE 115-b for data collection to be used in the encoder training. In some examples, the network entity 105-b may transmit a reference signal configuration, which may include an identifier corresponding to the reference signal configuration, such as the identifier indicated by the UE 115-b or determined by the network entity 105-b at 345. The one or more reference signals may be transmitted in accordance with the identifier. For example, the one or more reference signals may be transmitted using a same configuration (e.g., spatial configuration, spatial relationship, spatial filter, antenna element to port mapping, downtilt, network condition) as the one or more reference signals transmitted at 320. The UE 115-b may measure the one or more reference signals and may collect data for the encoder training. At 355, the UE 115-b may transmit an indication of the data to the UE server 310.
[0095] At 360, the UE server 310 may perform the encoder training. For example, the UE server 310 may perform the encoder training based on the data collected by the UE 115-b from the one or more reference signals transmitted at 350 or at 320 and based on the assistant information transmitted at 340. The UE server 310 may use the collected data corresponding to the same identifier used in the decoder training, as indicated by the assistant information at 340. In some examples, if the assistant information included an indication of a decoder, the encoder training may be performed by freezing the decoder (e.g., refraining from changing the decoder during training) . If the assistant information instead included an intermediate dataset, the UE server 310 may train a reference decoder using the intermediate dataset in accordance with a corresponding identifier (e.g., a paring identifier corresponding to {v1, z1} or ) and use the reference decoder for training of the encoder by freezing the reference decoder. If multiple decoders or intermediate datasets are indicated in the assistant information, the UE server 310 may repeat the process for each decoder or dataset (e.g., in accordance with a second pairing identifier corresponding to {v2, z2} or ) .
[0096] At 365, the UE 115-b and the network entity 105-b may exchange capability information (e.g., UE capability information) and perform applicable condition reporting. For example, the network entity 105-b may indicate a list of identifiers (e.g., pairing identifiers, associated identifiers) to the UE 115-b. The UE 115-b may report whether encoder training has been performed for an encoder corresponding to at least one of the indicated identifiers, and the UE 115-b may report each identifier for which an encoder has been trained. In some cases, the UE 115-b or UE server 310 may directly report the applicable one or more identifiers (e.g., association identifiers or pairing identifiers) if an encoder has been trained associated to these identifiers.
[0097] At 370, the network server 305 may deploy a decoder to the network entity 105-b. Similarly, at 375, the UE server 310 may deploy an encoder to the UE 115-b. The deployment of an encoder or decoder may include transmitting one or more parameters for the encoder or decoder in accordance with the encoder training or the decoder training, respectively.
[0098] At 380, the network entity 105-b may configure one or more identifiers (e.g., pairing identifiers, associated identifiers) to the UE 115-b. The one or more identifiers may be selected from the identifiers indicated by the UE 115-b, at 365, for which an encoder has been trained. The network entity 105-b may use a decoder corresponding to at least one of the one or more identifiers indicated to the UE 115-b for inference, and the UE 115-b may use an encoder corresponding to at least one of the one or more identifiers for inference. As such, the UE 115-b and the network entity 105-b may perform inference training for decoders and encoders in accordance with the indicated identifiers, thereby facilitating alignment during the inference training.
[0099] FIG. 4 shows an example of a process flow 400 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The process flow 400 illustrates communications between a network server 405, a network entity 105-c, a UE 115-c, and a UE server 410, which may be examples of corresponding devices as described herein. In some examples, functions performed by the network server 405 may instead be performed by the network entity 105-c, and functions performed by the UE server 410 may instead be performed by the UE 115-c. Additionally, or alternatively, functions performed by the UE 115-c and the UE server 410 may instead be performed by a node entity 415. In some cases, some steps may be performed in a different order than shown, or some steps may be omitted or added to the process flow 400.
[0100] At 420, the network entity 105-a may transmit one or more reference signals associated with decoder training for a decoder at the network-side. The UE 115-c may receive the one or more reference signals and may measure the one or more reference signals to collect data for the decoder training. In some cases, the one or more reference signals may be transmitted in accordance with a reference signal configuration (e.g., a spatial configuration) , which may correspond to an identifier (e.g., an association identifier) configured or provided in a reference signal configuration or triggering. In some other case, the reference signal configuration or triggering may not indicate an identifier (e.g., an association identifier) .
[0101] At 425, the UE 115-c may transmit the collected data to the network entity 105-c. In some cases, the UE 115-a may include the identifier indicated by the network entity at 420 (e.g., if present) , which may be used to label the data. In some examples, the network entity 105-c may transmit the data received from the UE 115-c to the network server 405. The network entity 105-c may receive data from a plurality of UEs 115, such as based on multiple reference signal transmissions, and the network entity 105-c may transmit the data collected from each UE 115 to the network server 405.
[0102] In some cases, at 430, the UE 115-c may perform data collection based on the one or more reference signals received at 420 for performing the encoder training. For example, the one or more reference signals may be used for data collection for both encoder and decoder training. In some examples, the data collected for the encoder training may be labeled by the UE 115-c using the same identifier (e.g., associated identifier) as the data for network-side decoder training, which may correspond to the one or more reference signals transmitted at 420. In some cases, UE-side data collection at 430 may not occur until after transmission of assistant information and a request for data collection is performed.
[0103] At 435, the network server 405 may perform the decoder training based on the data received from the network entity 105-c. In some examples, the decoder training may include training one or more encoder-decoder pairs. Each decoder may correspond to the actual decoder being trained for use by the network entity 105-c, while each encoder may be a reference model used for the training. In some cases, the network server 405 may train decoder to be compatible with a standardized encoder, decoder, or encoder-decoder pairs. In some examples, there may be one or more encoder, or decoder, or encoder-decoder pairs standardized (e.g., in a standard) . In some cases, the network server 405 may train a common decoder compatible to all the standardized models. In some other examples, NW may train a specialized decoder compatible to each of the standardized models, or a subset thereof. In some other cases, network server 405 may train multiple models to each of the standardized model based on the categorization of the collected data.
[0104] At 440, the network server 405 may transmit one or more identifiers (e.g., a pairing identifier, an associated identifier) associated with the decoder training. In some cases, the identifier may be transmitted directly to the UE server 410, or may be transmitted via the network entity 105-c and the UE 115-c. In some examples, a message may include a first identifier corresponding to a dataset used in the decoder training (e.g., corresponding to the data transmitted at 425) . Additionally, the message may include a second identifier corresponding to one or more models (e.g., a decoder model, an encoder model, or an encoder-decoder pair) from a set of models (e.g., priorly standardized in the specification) configured to the UE 115-c and network entity 105-c. As such, the network entity 105-c may not need to transfer a specific decoder or intermediate dataset corresponding to the decoder, and the network server 405 may instead indicate the decoder from a set of configured decoders using the identifier. In some cases, such as if there is only one configured model, the network server 405 may omit the second identifier. For example, if there is only one model specified in a standard, the network server 405 may only indicate the first identifier (e.g., a dataset association identifier) . If there are multiple models specified in the standard, the network server 405 may only indicate the second identifier (e.g., a pairing identifier or a model identifier) to indicate to the UE-side that the one or more decoders, and which of the one or more models are being used (e.g., the decoder or encoder are developed) . In some cases, if there are multiple decoders standardized, and the network server 405 trains multiple decoders trained on a respective dataset (e.g., a subset of the entire dataset) , the network server 405 may indicates one or more of the first identifier and the second identifier to indicate to the UE-side which model is used for training each of the decoders based on the one or more of the first identifier and the second identifier.
[0105] At 445, the UE 115-c may transmit a request for one or more reference signals to be used in data collection for the encoder training. In some cases, the UE 115-c may transmit the request based on an indication from the UE server 410 that (e.g., additional) data may be used for the encoder training. In some examples, the request may include an identifier, such as the first identifier, the second identifier, or both, indicated at 440. In some cases, the request for the one or more reference signals may be a single-bit indication (e.g., instead of including an identifier) . In these cases, the network entity 105-c may determine a corresponding identifier (e.g., associated identifier) corresponding to the one or more reference signals, such as by selecting the identifier transmitted at 440.
[0106] At 450, the network entity 105-c may transmit the one or more reference signals requested by the UE 115-c for data collection to be used in the encoder training. In some examples, the network entity 105-c may transmit a reference signal configuration, which may include an identifier indicated at 440 (e.g., the first identifier) . The one or more reference signals may be transmitted in accordance with the identifier. For example, the one or more reference signals may be transmitted using a same configuration (e.g., spatial configuration, spatial relationship, spatial filter, antenna element to port mapping, downtilt, network condition) as the one or more reference signals transmitted at 420. The UE 115-c may measure the one or more reference signals and may collect data for the encoder training. At 455, the UE 115-c may transmit an indication of the data to the UE server 410. In some cases, the UE 115-c may collect data via UE-side data collection at 430 based on the one or more reference signals transmitted at 420 triggered for NW-side data collection 425, and the UE 115-c may not receive or collect data for reference signals transmitted at 450. In another case, UE 115-c may have previously obtained the dataset indicated by one or more identifiers transmitted at 440 via UE side data collection performed at 430. As such, UE may not transmit the data collection request at 445, receive the one or more reference signals at 450, or perform additional data collection at 455 if the UE 115-c previously collected the data or obtained a dataset (e.g., indicated by the one or more identifiers) to be used for encoder training.
[0107] At 460, the UE server 410 may perform the encoder training. For example, the UE server 410 may perform the encoder training based on the data collected by the UE 115-c from the one or more reference signals transmitted at 450 or at 420 and based on the one or more identifiers transmitted at 440. For example, the UE 115-c or the UE server 410 may determine a decoder from a set of configured decoders based on the second identifier transmitted at 440, and the UE server 410 may perform the encoder training against the determined decoder.
[0108] At 465, the UE 115-c and the network entity 105-c may exchange capability information (e.g., UE capability information) and perform applicable condition reporting. For example, the network entity 105-c may indicate a list of identifiers (e.g., pairing identifiers, associated identifiers) to the UE 115-c. The UE 115-c may report whether encoder training has been performed for an encoder corresponding to at least one of the indicated identifiers, and the UE 115-c may report each identifier for which an encoder has been trained.
[0109] At 470, the network server 405 may deploy a decoder to the network entity 105-c. Similarly, at 475, the UE server 410 may deploy an encoder to the UE 115-c. The deployment of an encoder or decoder may include transmitting one or more parameters for the encoder or decoder in accordance with the encoder training or the decoder training, respectively.
[0110] At 480, the network entity 105-c may configure one or more identifiers (e.g., pairing identifiers, associated identifiers) to the UE 115-c. The one or more identifiers may be selected from the identifiers indicated by the UE 115-c, at 465, for which an encoder has been trained. The network entity 105-c may use a decoder corresponding to at least one of the one or more identifiers indicated to the UE 115-c for inference, and the UE 115-c may use an encoder corresponding to at least one of the one or more identifiers for inference. As such, the UE 115-c and the network entity 105-c may perform inference training for decoders and encoders in accordance with the indicated identifiers, thereby facilitating alignment during the inference training.
[0111] FIG. 5 shows an example of a process flow 500 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The process flow 500 illustrates communications between a network server 505, a network entity 105-d, and a UE 115-d, which may be examples of corresponding devices as described herein. In some examples, functions performed by the network server 505 may instead be performed by the network entity 105-d. Additionally, or alternatively, functions performed by the UE 115-d may be performed by a node entity, as described herein. In some cases, some steps may be performed in a different order than shown, or some steps may be omitted or added to the process flow 500.
[0112] At 510, the network entity 105-a may transmit one or more reference signals associated with decoder and encoder training. The UE 115-d may receive the one or more reference signals and may measure the one or more reference signals to collect data for the decoder and encoder training.
[0113] At 515, the UE 115-d may transmit the collected data to the network entity 105-d. In some examples, the network entity 105-d may transmit the data received from the UE 115-d to the network server 505. The network entity 105-d may receive data from a plurality of UEs 115, such as based on multiple reference signal transmissions, and the network entity 105-d may transmit the data collected from each UE 115 to the network server 505.
[0114] At 520, the network server 505 may perform the decoder and encoder training based on the data received from the network entity 105-d. In some examples, the decoder and encoder training may be based on data received from the plurality of UEs 115.
[0115] At 525, the network entity 105-d may transmit an inquiry associated with sending a model for inference at the UE 115-d. The inquiry may be based on a transmission from the network server 505 to the network entity 105-d associated with the model. In some examples, the inquiry may include one or more identifiers (e.g., one or more model identifiers, a pairing identifier) associated with one or more models used in the encoder and decoder training. The identifiers may indicate just an encoder model or may indicate an encoder-decoder model pair.
[0116] At 530, the UE 115-d may transmit a model transfer request based on determining that a model transfer is needed. For example, the UE 115-d may determine that at least one model corresponding to an identifier indicated in the inquiry at 525 is not stored at a memory of the UE 115-d or has not been previously used by the UE 115-d (e.g., for inference or for transmission) . In some cases, the UE 115-d may instead indicate that no model transfer is being requested, such as if the UE 115-d has previously used the indicated models corresponding to the one or more identifiers.
[0117] At 535, the network entity 105-d may perform the model transfer based on a request from the UE 115-d at 530. For example, the network entity 105-d may transmit an indication of one or more model parameters that may be used by the UE 115-d to develop (e.g., generate) the model (e.g., the encoder model) for inference.
[0118] As such, by assigning identifiers to encoder and decoder models, the UE 115-d and the network entity 105-d may readily assess whether model transfer is to be performed to proceed with inference at the UE 115-d.
[0119] FIG. 6 shows a block diagram 600 of a device 605 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The device 605 may be an example of aspects of a node entity (e.g., a UE 115 and / or a UE server) as described herein. The device 605 may include a receiver 610, a transmitter 615, and a communications manager 620. The device 605, or one or more components of the device 605 (e.g., the receiver 610, the transmitter 615, the communications manager 620) , may include at least one processor, which may be coupled with at least one memory, to, individually or collectively, support or enable the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses) .
[0120] The receiver 610 may provide a means for receiving information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to techniques for transmission of assistant information to align dataset for encoder and decoder training) . Information may be passed on to other components of the device 605. The receiver 610 may utilize a single antenna or a set of multiple antennas.
[0121] The transmitter 615 may provide a means for transmitting signals generated by other components of the device 605. For example, the transmitter 615 may transmit information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to techniques for transmission of assistant information to align dataset for encoder and decoder training) . In some examples, the transmitter 615 may be co-located with a receiver 610 in a transceiver module. The transmitter 615 may utilize a single antenna or a set of multiple antennas.
[0122] The communications manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be examples of means for performing various aspects of techniques for transmission of assistant information to align dataset for encoder and decoder training as described herein. For example, the communications manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be capable of performing one or more of the functions described herein.
[0123] In some examples, the communications manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry) . The hardware may include at least one of a processor, a digital signal processor (DSP) , a central processing unit (CPU) , an application-specific integrated circuit (ASIC) , a field-programmable gate array (FPGA) or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure. In some examples, at least one processor and at least one memory coupled with the at least one processor may be configured to perform one or more of the functions described herein (e.g., by one or more processors, individually or collectively, executing instructions stored in the at least one memory) .
[0124] Additionally, or alternatively, the communications manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be implemented in code (e.g., as communications management software or firmware) executed by at least one processor (e.g., referred to as a processor-executable code) . If implemented in code executed by at least one processor, the functions of the communications manager 620, the receiver 610, the transmitter 615, or various combinations or components thereof may be performed by a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices (e.g., configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure) .
[0125] In some examples, the communications manager 620 may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 610, the transmitter 615, or both. For example, the communications manager 620 may receive information from the receiver 610, send information to the transmitter 615, or be integrated in combination with the receiver 610, the transmitter 615, or both to obtain information, output information, or perform various other operations as described herein.
[0126] The communications manager 620 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 620 is capable of, configured to, or operable to support a means for receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training. The communications manager 620 is capable of, configured to, or operable to support a means for transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both. The communications manager 620 is capable of, configured to, or operable to support a means for receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection. The communications manager 620 is capable of, configured to, or operable to support a means for performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0127] Additionally, or alternatively, the communications manager 620 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 620 is capable of, configured to, or operable to support a means for receiving a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity. The communications manager 620 is capable of, configured to, or operable to support a means for transmitting a request for the one or more model parameters based on receiving the first message including the identifier. The communications manager 620 is capable of, configured to, or operable to support a means for receiving a second message including the one or more model parameters based on transmitting the request.
[0128] By including or configuring the communications manager 620 in accordance with examples as described herein, the device 605 (e.g., at least one processor controlling or otherwise coupled with the receiver 610, the transmitter 615, the communications manager 620, or a combination thereof) may support techniques for transmission of assistant information that may result in improved communication stability and efficiency.
[0129] FIG. 7 shows a block diagram 700 of a device 705 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The device 705 may be an example of aspects of a device 605 or a UE 115 as described herein. The device 705 may include a receiver 710, a transmitter 715, and a communications manager 720. The device 705, or one or more components of the device 705 (e.g., the receiver 710, the transmitter 715, the communications manager 720) , may include at least one processor, which may be coupled with at least one memory, to support the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses) .
[0130] The receiver 710 may provide a means for receiving information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to techniques for transmission of assistant information to align dataset for encoder and decoder training) . Information may be passed on to other components of the device 705. The receiver 710 may utilize a single antenna or a set of multiple antennas.
[0131] The transmitter 715 may provide a means for transmitting signals generated by other components of the device 705. For example, the transmitter 715 may transmit information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to techniques for transmission of assistant information to align dataset for encoder and decoder training) . In some examples, the transmitter 715 may be co-located with a receiver 710 in a transceiver module. The transmitter 715 may utilize a single antenna or a set of multiple antennas.
[0132] The device 705, or various components thereof, may be an example of means for performing various aspects of techniques for transmission of assistant information to align dataset for encoder and decoder training as described herein. For example, the communications manager 720 may include an identifier manager 725, a request component 730, a data collection component 735, a training component 740, a model parameter component 745, or any combination thereof. The communications manager 720 may be an example of aspects of a communications manager 620 as described herein. In some examples, the communications manager 720, or various components thereof, may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 710, the transmitter 715, or both. For example, the communications manager 720 may receive information from the receiver 710, send information to the transmitter 715, or be integrated in combination with the receiver 710, the transmitter 715, or both to obtain information, output information, or perform various other operations as described herein.
[0133] The communications manager 720 may support wireless communications in accordance with examples as disclosed herein. The identifier manager 725 is capable of, configured to, or operable to support a means for receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training. The request component 730 is capable of, configured to, or operable to support a means for transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both. The data collection component 735 is capable of, configured to, or operable to support a means for receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection. The training component 740 is capable of, configured to, or operable to support a means for performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0134] Additionally, or alternatively, the communications manager 720 may support wireless communications in accordance with examples as disclosed herein. The identifier manager 725 is capable of, configured to, or operable to support a means for receiving a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity. The request component 730 is capable of, configured to, or operable to support a means for transmitting a request for the one or more model parameters based on receiving the first message including the identifier. The model parameter component 745 is capable of, configured to, or operable to support a means for receiving a second message including the one or more model parameters based on transmitting the request.
[0135] FIG. 8 shows a block diagram 800 of a communications manager 820 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The communications manager 820 may be an example of aspects of a communications manager 620, a communications manager 720, or both, as described herein. The communications manager 820, or various components thereof, may be an example of means for performing various aspects of techniques for transmission of assistant information to align dataset for encoder and decoder training as described herein. For example, the communications manager 820 may include an identifier manager 825, a request component 830, a data collection component 835, a training component 840, a model parameter component 845, or any combination thereof. Each of these components, or components or subcomponents thereof (e.g., one or more processors, one or more memories) , may communicate, directly or indirectly, with one another (e.g., via one or more buses) .
[0136] The communications manager 820 may support wireless communications in accordance with examples as disclosed herein. The identifier manager 825 is capable of, configured to, or operable to support a means for receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training. The request component 830 is capable of, configured to, or operable to support a means for transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both. The data collection component 835 is capable of, configured to, or operable to support a means for receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection. The training component 840 is capable of, configured to, or operable to support a means for performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0137] In some examples, the identifier indicates a first dataset associated with developing a decoder, a second dataset for generating a mapping between a set of decoder inputs and a set of decoder outputs associated with the decoder training, a third dataset for performing the encoder training, a fourth dataset for generating a mapping between a set of encoder inputs and a set of encoder outputs associated with the decoder training, or a combination thereof.
[0138] In some examples, the identifier includes a pairing identifier indicating a model pair including a first decoder model and a first encoder model, a model identifier indicating the first decoder model or the first encoder model, or both.
[0139] In some examples, the second message indicates the first decoder model, the first encoder model, or the model pair.
[0140] In some examples, the identifier of the first message indicates collected data associated with generation of a first dataset associated with the decoder training. In some examples, the second message indicates the collected data.
[0141] In some examples, the request component 830 is capable of, configured to, or operable to support a means for receiving, based on transmitting the second message, a reference signal configuration indicating the reference signal resources in accordance with the one or more decoder models, the one or more datasets, or both, where receiving the one or more reference signals is based on receiving the reference signal configuration. In some examples, the data collection component 835 is capable of, configured to, or operable to support a means for performing one or more measurements based on receiving the one or more reference signals to collect data based on the one or more measurement, and where performing the encoder training is based on receiving the one or more reference signals.
[0142] In some examples, the data collection component 835 is capable of, configured to, or operable to support a means for receiving, prior to receiving the first message, one or more additional reference signals. In some examples, the data collection component 835 is capable of, configured to, or operable to support a means for transmitting data collected from the one or more additional reference signals for use by a network entity to perform the decoder training, where the one or more reference signals received via the reference signal resources are transmitted in accordance with the decoder training.
[0143] In some examples, the one or more additional reference signals are transmitted in accordance with a first spatial configuration, and the one or more reference signals are transmitted in accordance with the first spatial configuration.
[0144] In some examples, the second message requesting the reference signal resources indicates the identifier. In some examples, the second message includes a single bit having a first value, the first value indicating the request for the reference signal resources.
[0145] In some examples, the identifier manager 825 is capable of, configured to, or operable to support a means for determining a decoder model from a set of decoder models based on the identifier, where performing the encoder training is based on the determined decoder model.
[0146] In some examples, the data collection component 835 is capable of, configured to, or operable to support a means for receiving the one or more reference signals with a spatial configuration associated with the identifier and corresponding to the decoder training.
[0147] In some examples, the spatial configuration includes an analog beamforming configuration, a digital beamforming configuration, an antenna element to port virtualization, a downtilt value, a spatial filter, a spatial relationship, or a combination thereof.
[0148] Additionally, or alternatively, the communications manager 820 may support wireless communications in accordance with examples as disclosed herein. In some examples, the identifier manager 825 is capable of, configured to, or operable to support a means for receiving a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity. In some examples, the request component 830 is capable of, configured to, or operable to support a means for transmitting a request for the one or more model parameters based on receiving the first message including the identifier. The model parameter component 845 is capable of, configured to, or operable to support a means for receiving a second message including the one or more model parameters based on transmitting the request.
[0149] In some examples, the request component 830 is capable of, configured to, or operable to support a means for transmitting the request for the one or more model parameters based on determining that the one or more model parameters corresponding to the identifier are for use by the node entity.
[0150] In some examples, the data collection component 835 is capable of, configured to, or operable to support a means for receiving, prior to receiving the first message, one or more reference signals associated with the encoder training and the decoder training.
[0151] In some examples, the data collection component 835 is capable of, configured to, or operable to support a means for transmitting data collected from the one or more reference signals for use by a network entity to perform the decoder training and the encoder training, where receiving the first message is based on transmitting the data. In some examples, the request for the one or more model parameters indicates the identifier.
[0152] FIG. 9 shows a diagram of a system 900 including a device 905 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The device 905 may be an example of or include components of a node entity, a device 605, a device 705, a UE 115, or a UE server, or any combination thereof as described herein. The device 905 may communicate (e.g., wirelessly) with one or more other devices (e.g., network entities 105, UEs 115, or a combination thereof) . The device 905 may include components for bi-directional voice and data communications including components for transmitting and receiving communications, such as a communications manager 920, an input / output (I / O) controller, such as an I / O controller 910, a transceiver 915, one or more antennas 925, at least one memory 930, code 935, and at least one processor 940. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., a bus 945) .
[0153] The I / O controller 910 may manage input and output signals for the device 905. The I / O controller 910 may also manage peripherals not integrated into the device 905. In some cases, the I / O controller 910 may represent a physical connection or port to an external peripheral. In some cases, the I / O controller 910 may utilize an operating system such as or another known operating system. Additionally, or alternatively, the I / O controller 910 may represent or interact with a modem, a keyboard, a mouse, a touchscreen, or a similar device. In some cases, the I / O controller 910 may be implemented as part of one or more processors, such as the at least one processor 940. In some cases, a user may interact with the device 905 via the I / O controller 910 or via hardware components controlled by the I / O controller 910.
[0154] In some cases, the device 905 may include a single antenna. However, in some other cases, the device 905 may have more than one antenna, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 915 may communicate bi-directionally via the one or more antennas 925 using wired or wireless links as described herein. For example, the transceiver 915 may represent a wireless transceiver and may communicate bi-directionally with another wireless transceiver. The transceiver 915 may also include a modem to modulate the packets, to provide the modulated packets to one or more antennas 925 for transmission, and to demodulate packets received from the one or more antennas 925. The transceiver 915, or the transceiver 915 and one or more antennas 925, may be an example of a transmitter 615, a transmitter 715, a receiver 610, a receiver 710, or any combination thereof or component thereof, as described herein.
[0155] The at least one memory 930 may include random access memory (RAM) and read-only memory (ROM) . The at least one memory 930 may store computer-readable, computer-executable, or processor-executable code, such as the code 935. The code 935 may include instructions that, when executed by the at least one processor 940, cause the device 905 to perform various functions described herein. The code 935 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, the code 935 may not be directly executable by the at least one processor 940 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some cases, the at least one memory 930 may include, among other things, a basic I / O system (BIOS) which may control basic hardware or software operation such as the interaction with peripheral components or devices.
[0156] The at least one processor 940 may include one or more intelligent hardware devices (e.g., one or more general-purpose processors, one or more DSPs, one or more CPUs, one or more graphics processing units (GPUs) , one or more neural processing units (NPUs) (also referred to as neural network processors or deep learning processors (DLPs) ) , one or more microcontrollers, one or more ASICs, one or more FPGAs, one or more programmable logic devices, discrete gate or transistor logic, one or more discrete hardware components, or any combination thereof) . In some cases, the at least one processor 940 may be configured to operate a memory array using a memory controller. In some other cases, a memory controller may be integrated into the at least one processor 940. The at least one processor 940 may be configured to execute computer-readable instructions stored in a memory (e.g., the at least one memory 930) to cause the device 905 to perform various functions (e.g., functions or tasks supporting techniques for transmission of assistant information to align dataset for encoder and decoder training) . For example, the device 905 or a component of the device 905 may include at least one processor 940 and at least one memory 930 coupled with or to the at least one processor 940, the at least one processor 940 and the at least one memory 930 configured to perform various functions described herein.
[0157] In some examples, the at least one processor 940 may include multiple processors and the at least one memory 930 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions described herein. In some examples, the at least one processor 940 may be a component of a processing system, which may refer to a system (such as a series) of machines, circuitry (including, for example, one or both of processor circuitry (which may include the at least one processor 940) and memory circuitry (which may include the at least one memory 930) ) , or components, that receives or obtains inputs and processes the inputs to produce, generate, or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. For example, the at least one processor 940 or a processing system including the at least one processor 940 may be configured to, configurable to, or operable to cause the device 905 to perform one or more of the functions described herein. Further, as described herein, being “configured to, ” being “configurable to, ” and being “operable to” may be used interchangeably and may be associated with a capability, when executing code 935 (e.g., processor-executable code) stored in the at least one memory 930 or otherwise, to perform one or more of the functions described herein.
[0158] The communications manager 920 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 920 is capable of, configured to, or operable to support a means for receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training. The communications manager 920 is capable of, configured to, or operable to support a means for transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both. The communications manager 920 is capable of, configured to, or operable to support a means for receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection. The communications manager 920 is capable of, configured to, or operable to support a means for performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0159] Additionally, or alternatively, the communications manager 920 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 920 is capable of, configured to, or operable to support a means for receiving a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity. The communications manager 920 is capable of, configured to, or operable to support a means for transmitting a request for the one or more model parameters based on receiving the first message including the identifier. The communications manager 920 is capable of, configured to, or operable to support a means for receiving a second message including the one or more model parameters based on transmitting the request.
[0160] By including or configuring the communications manager 920 in accordance with examples as described herein, the device 905 may support techniques for transmission of assistant information that may result in improved communication reliability, reduced latency, and improved utilization of processing capability.
[0161] In some examples, the communications manager 920 may be configured to perform various operations (e.g., receiving, monitoring, transmitting) using or otherwise in cooperation with the transceiver 915, the one or more antennas 925, or any combination thereof. Although the communications manager 920 is illustrated as a separate component, in some examples, one or more functions described with reference to the communications manager 920 may be supported by or performed by the at least one processor 940, the at least one memory 930, the code 935, or any combination thereof. For example, the code 935 may include instructions executable by the at least one processor 940 to cause the device 905 to perform various aspects of techniques for transmission of assistant information to align dataset for encoder and decoder training as described herein, or the at least one processor 940 and the at least one memory 930 may be otherwise configured to, individually or collectively, perform or support such operations.
[0162] FIG. 10 shows a flowchart illustrating a method 1000 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The operations of the method 1000 may be implemented by a node entity (e.g., a UE 115 and / or a UE server) or its components as described herein. For example, the operations of the method 1000 may be performed by a node entity, a UE 115, a UE server, or any combination thereof as described with reference to FIGs. 1 through 9. In some examples, a node entity may execute a set of instructions to control the functional elements of the node entity to perform the described functions. Additionally, or alternatively, the node entity may perform aspects of the described functions using special-purpose hardware.
[0163] At 1005, the method may include receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training. The operations of 1005 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1005 may be performed by an identifier manager 825 as described with reference to FIG. 8.
[0164] At 1010, the method may include transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both. The operations of 1010 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1010 may be performed by a request component 830 as described with reference to FIG. 8.
[0165] At 1015, the method may include receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection. The operations of 1015 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1015 may be performed by a data collection component 835 as described with reference to FIG. 8.
[0166] At 1020, the method may include performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources. The operations of 1020 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1020 may be performed by a training component 840 as described with reference to FIG. 8.
[0167] FIG. 11 shows a flowchart illustrating a method 1100 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The operations of the method 1100 may be implemented by a node entity (e.g., a UE 115 and / or a UE server) or its components as described herein. For example, the operations of the method 1100 may be performed by a node entity, a UE 115, a UE server, or any combination thereof as described with reference to FIGs. 1 through 9. In some examples, a node entity may execute a set of instructions to control the functional elements of the node entity to perform the described functions. Additionally, or alternatively, the node entity may perform aspects of the described functions using special-purpose hardware.
[0168] At 1105, the method may include receiving a first message including an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training. The operations of 1105 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1105 may be performed by an identifier manager 825 as described with reference to FIG. 8.
[0169] At 1110, the method may include transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both. The operations of 1110 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1110 may be performed by a request component 830 as described with reference to FIG. 8.
[0170] At 1115, the method may include receiving, based on transmitting the second message, a reference signal configuration indicating the reference signal resources in accordance with the one or more decoder models, the one or more datasets, or both, where receiving the one or more reference signals is based on receiving the reference signal configuration. The operations of 1115 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1115 may be performed by a request component 830 as described with reference to FIG. 8.
[0171] At 1120, the method may include receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection. The operations of 1120 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1120 may be performed by a data collection component 835 as described with reference to FIG. 8.
[0172] At 1125, the method may include performing one or more measurements based on receiving the one or more reference signals to collect data based on the one or more measurement, and where performing the encoder training is based on receiving the one or more reference signals. The operations of 1125 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1125 may be performed by a data collection component 835 as described with reference to FIG. 8.
[0173] At 1130, the method may include performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources. The operations of 1130 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1130 may be performed by a training component 840 as described with reference to FIG. 8.
[0174] FIG. 12 shows a flowchart illustrating a method 1200 that supports techniques for transmission of assistant information to align dataset for encoder and decoder training in accordance with one or more aspects of the present disclosure. The operations of the method 1200 may be implemented by a node entity (e.g., a UE 115 and / or a UE server) or its components as described herein. For example, the operations of the method 1200 may be performed by a node entity, a UE 115, a UE server, or any combination thereof as described with reference to FIGs. 1 through 9. In some examples, a node entity may execute a set of instructions to control the functional elements of the node entity to perform the described functions. Additionally, or alternatively, the node entity may perform aspects of the described functions using special-purpose hardware.
[0175] At 1205, the method may include receiving a first message including an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity. The operations of 1205 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1205 may be performed by an identifier manager 825 as described with reference to FIG. 8.
[0176] At 1210, the method may include transmitting a request for the one or more model parameters based on receiving the first message including the identifier. The operations of 1210 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1210 may be performed by a request component 830 as described with reference to FIG. 8.
[0177] At 1215, the method may include receiving a second message including the one or more model parameters based on transmitting the request. The operations of 1215 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1215 may be performed by a model parameter component 845 as described with reference to FIG. 8.
[0178] The following provides an overview of aspects of the present disclosure:
[0179] Aspect 1: A method for wireless communications by a node entity, comprising: receiving a first message comprising an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training; transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both; and receiving, in response to the second message, one or more reference signals via the reference signal resources for performing the data collection; and performing the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.
[0180] Aspect 2: The method of aspect 1, wherein the identifier indicates a first dataset associated with developing a decoder, a second dataset for generating a mapping between a set of decoder inputs and a set of decoder outputs associated with the decoder training, a third dataset for performing the encoder training, a fourth dataset for generating a mapping between a set of encoder inputs and a set of encoder outputs associated with the decoder training, or a combination thereof.
[0181] Aspect 3: The method of any of aspects 1 through 2, wherein the identifier comprises a pairing identifier indicating a model pair comprising a first decoder model and a first encoder model, a model identifier indicating the first decoder model or the first encoder model, or both.
[0182] Aspect 4: The method of aspect 3, wherein the second message indicates the first decoder model, the first encoder model, or the model pair.
[0183] Aspect 5: The method of any of aspects 1 through 4, wherein the identifier of the first message indicates collected data associated with generation of a first dataset associated with the decoder training, and the second message indicates the collected data.
[0184] Aspect 6: The method of any of aspects 1 through 5, further comprising: receiving, based at least in part on transmitting the second message, a reference signal configuration indicating the reference signal resources in accordance with the one or more decoder models, the one or more datasets, or both, wherein receiving the one or more reference signals is based at least in part on receiving the reference signal configuration; and performing one or more measurements based on receiving the one or more reference signals to collect data based on the one or more measurement, and wherein performing the encoder training is based at least in part on receiving the one or more reference signals.
[0185] Aspect 7: The method of any of aspects 1 through 6, further comprising: receiving, prior to receiving the first message, one or more additional reference signals; and transmitting data collected from the one or more additional reference signals for use by a network entity to perform the decoder training, wherein the one or more reference signals received via the reference signal resources are transmitted in accordance with the decoder training.
[0186] Aspect 8: The method of aspect 7, wherein the one or more additional reference signals are transmitted in accordance with a first spatial configuration, and the one or more reference signals are transmitted in accordance with the first spatial configuration.
[0187] Aspect 9: The method of any of aspects 1 through 8, wherein the second message requesting the reference signal resources indicates the identifier.
[0188] Aspect 10: The method of any of aspects 1 through 9, wherein the second message comprises a single bit having a first value, the first value indicating the request for the reference signal resources.
[0189] Aspect 11: The method of any of aspects 1 through 10, further comprising: determining a decoder model from a set of decoder models based at least in part on the identifier, wherein performing the encoder training is based at least in part on the determined decoder model.
[0190] Aspect 12: The method of any of aspects 1 through 11, further comprising: receiving the one or more reference signals with a spatial configuration associated with the identifier and corresponding to the decoder training.
[0191] Aspect 13: The method of aspect 12, wherein the spatial configuration comprises an analog beamforming configuration, a digital beamforming configuration, an antenna element to port virtualization, a downtilt value, a spatial filter, a spatial relationship, or a combination thereof.
[0192] Aspect 14: A method for wireless communications by a node entity, comprising: receiving a first message comprising an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity; transmitting a request for the one or more model parameters based at least in part on receiving the first message comprising the identifier; and receiving a second message comprising the one or more model parameters based at least in part on transmitting the request.
[0193] Aspect 15: The method of aspect 14, further comprising: transmitting the request for the one or more model parameters based at least in part on determining that the one or more model parameters corresponding to the identifier are needed by the node entity.
[0194] Aspect 16: The method of any of aspects 14 through 15, further comprising: receiving, prior to receiving the first message, one or more reference signals associated with the encoder training and the decoder training.
[0195] Aspect 17: The method of aspect 16, further comprising: transmitting data collected from the one or more reference signals for use by a network entity to perform the decoder training and the encoder training, wherein receiving the first message is based at least in part on transmitting the data.
[0196] Aspect 18: The method of any of aspects 14 through 17, wherein the request for the one or more model parameters indicates the identifier.
[0197] Aspect 19: A node entity for wireless communications, comprising one or more memories storing processor-executable code, and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the node entity to perform a method of any of aspects 1 through 13.
[0198] Aspect 20: A node entity for wireless communications, comprising at least one means for performing a method of any of aspects 1 through 13.
[0199] Aspect 21: A non-transitory computer-readable medium storing code for wireless communications, the code comprising instructions executable by one or more processors to perform a method of any of aspects 1 through 13.
[0200] Aspect 22: A node entity for wireless communications, comprising one or more memories storing processor-executable code, and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the node entity to perform a method of any of aspects 14 through 18.
[0201] Aspect 23: A node entity for wireless communications, comprising at least one means for performing a method of any of aspects 14 through 18.
[0202] Aspect 24: A non-transitory computer-readable medium storing code for wireless communications, the code comprising instructions executable by one or more processors to perform a method of any of aspects 14 through 18.
[0203] It should be noted that the methods described herein describe possible implementations. The operations and the steps may be rearranged, or otherwise modified and other implementations are possible. Further, aspects from two or more of the methods may be combined.
[0204] Although aspects of an LTE, LTE-A, LTE-A Pro, or NR system may be described for purposes of example, and LTE, LTE-A, LTE-A Pro, or NR terminology may be used in much of the description, the techniques described herein are applicable beyond LTE, LTE-A, LTE-A Pro, or NR networks. For example, the described techniques may be applicable to various other wireless communications systems such as Ultra Mobile Broadband (UMB) , Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20, Flash-OFDM, as well as other systems and radio technologies not explicitly mentioned herein.
[0205] Information and signals described herein may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.
[0206] The various illustrative blocks and components described in connection with the disclosure herein may be implemented or performed using a general-purpose processor, a DSP, an ASIC, a CPU, a graphics processing unit (GPU) , a neural processing unit (NPU) , an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor but, in the alternative, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration) . Any functions or operations described herein as being capable of being performed by a processor may be performed by multiple processors that, individually or collectively, are capable of performing the described functions or operations.
[0207] The functions described herein may be implemented using hardware, software executed by a processor, firmware, or any combination thereof. If implemented using software executed by a processor, the functions may be stored as or transmitted using one or more instructions or code of a computer-readable medium. Other examples and implementations are within the scope of the disclosure and appended claims. For example, due to the nature of software, functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
[0208] Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one location to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transitory computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM) , flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that may be used to carry or store desired program code means in the form of instructions or data structures and that may be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) , or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of computer-readable medium. Disk and disc, as used herein, include CD, laser disc, optical disc, digital versatile disc (DVD) , floppy disk, and Blu-ray disc. Disks may reproduce data magnetically, and discs may reproduce data optically using lasers. Combinations of the above are also included within the scope of computer-readable media. Any functions or operations described herein as being capable of being performed by a memory may be performed by multiple memories that, individually or collectively, are capable of performing the described functions or operations.
[0209] As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of” or “one or more of” ) indicates an inclusive list such 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) . Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. ”
[0210] As used herein, including in the claims, the article “a” before a noun is open-ended and understood to refer to “at least one” of those nouns or “one or more” of those nouns. Thus, the terms “a, ” “at least one, ” “one or more, ” and “at least one of one or more” may be interchangeable. For example, if a claim recites “a component” that performs one or more functions, each of the individual functions may be performed by a single component or by any combination of multiple components. Thus, the term “a component” having characteristics or performing functions may refer to “at least one of one or more components” having a particular characteristic or performing a particular function. Subsequent reference to a component introduced with the article “a” using the terms “the” or “said” may refer to any or all of the one or more components. For example, a component introduced with the article “a” may be understood to mean “one or more components, ” and referring to “the component” subsequently in the claims may be understood to be equivalent to referring to “at least one of the one or more components. ” Similarly, subsequent reference to a component introduced as “one or more components” using the terms “the” or “said” may refer to any or all of the one or more components. For example, referring to “the one or more components” subsequently in the claims may be understood to be equivalent to referring to “at least one of the one or more components. ”
[0211] The term “determine” or “determining” encompasses a variety of actions and, therefore, “determining” can include calculating, computing, processing, deriving, investigating, looking up (such as via looking up in a table, a database, or another data structure) , ascertaining, and the like. Also, “determining” can include receiving (e.g., receiving information) , accessing (e.g., accessing data stored in memory) , and the like. Also, “determining” can include resolving, obtaining, selecting, choosing, establishing, and other such similar actions.
[0212] In the appended figures, similar components or features may have the same reference label. Further, various components of the same type may be distinguished by following the reference label by a dash and a second label that distinguishes among the similar components. If just the first reference label is used in the specification, the description is applicable to any one of the similar components having the same first reference label irrespective of the second reference label or other subsequent reference label.
[0213] The description set forth herein, in connection with the appended drawings, describes example configurations and does not represent all the examples that may be implemented or that are within the scope of the claims. The term “example” used herein means “serving as an example, instance, or illustration” and not “preferred” or “advantageous over other examples. ” The detailed description includes specific details for the purpose of providing an understanding of the described techniques. These techniques, however, may be practiced without these specific details. In some figures, known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.
[0214] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
A node entity, comprising:one or more memories storing processor-executable code; andone or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the node entity to:receive a first message comprising an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training;transmit, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both;receive, in response to the second message, one or more reference signals via the reference signal resources for performing data collection; andperform the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.The node entity of claim 1, wherein the identifier indicates a first dataset associated with developing a decoder, a second dataset for generating a mapping between a set of decoder inputs and a set of decoder outputs associated with the decoder training, a third dataset for performing the encoder training, a fourth dataset for generating a mapping between a set of encoder inputs and a set of encoder outputs associated with the decoder training, or a combination thereof.The node entity of claim 1, wherein the identifier comprises a pairing identifier indicating a model pair comprising a first decoder model and a first encoder model, a model identifier indicating the first decoder model or the first encoder model, or both.The node entity of claim 3, wherein the second message indicates the first decoder model, the first encoder model, or the model pair.The node entity of claim 1, wherein:the identifier of the first message indicates collected data associated with generation of a first dataset associated with the decoder training, andthe second message indicates the collected data.The node entity of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the node entity to:receive, based at least in part on transmitting the second message, a reference signal configuration indicating the reference signal resources in accordance with the one or more decoder models, the one or more datasets, or both, wherein receiving the one or more reference signals is based at least in part on receiving the reference signal configuration; andperform one or more measurements based on receiving the one or more reference signals to collect data based on the one or more measurement, and wherein performing the encoder training is based at least in part on receiving the one or more reference signals.The node entity of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the node entity to:receive, prior to receiving the first message, one or more additional reference signals; andtransmit data collected from the one or more additional reference signals for use by a network entity to perform the decoder training, wherein the one or more reference signals received via the reference signal resources are transmitted in accordance with the decoder training.The node entity of claim 7, wherein the one or more additional reference signals are transmitted in accordance with a first spatial configuration, and the one or more reference signals are transmitted in accordance with the first spatial configuration.The node entity of claim 1, wherein the second message requesting the reference signal resources indicates the identifier.The node entity of claim 1, wherein the second message comprises a single bit having a first value, the first value indicating the request for the reference signal resources.The node entity of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the node entity to:determine a decoder model from a set of decoder models based at least in part on the identifier, wherein performing the encoder training is based at least in part on the determined decoder model.The node entity of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the node entity to:receive the one or more reference signals with a spatial configuration associated with the identifier and corresponding to the decoder training.The node entity of claim 12, wherein the spatial configuration comprises an analog beamforming configuration, a digital beamforming configuration, an antenna element to port virtualization, a downtilt value, a spatial filter, a spatial relationship, or a combination thereof.A node entity, comprising:one or more memories storing processor-executable code; andone or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the node entity to:receive a first message comprising an identifier, the identifier indicating one or more models, one or more model parameters, or both, associated with decoder training and encoder training for the node entity;transmit a request for the one or more model parameters based at least in part on receiving the first message comprising the identifier; andreceive a second message comprising the one or more model parameters based at least in part on transmitting the request.The node entity of claim 14, wherein the one or more processors are individually or collectively further operable to execute the code to cause the node entity to:transmit the request for the one or more model parameters based at least in part on determining that the one or more model parameters corresponding to the identifier are for use by the node entity.The node entity of claim 14, wherein the one or more processors are individually or collectively further operable to execute the code to cause the node entity to:receive, prior to receiving the first message, one or more reference signals associated with the encoder training and the decoder training.The node entity of claim 16, wherein the one or more processors are individually or collectively further operable to execute the code to cause the node entity to:transmit data collected from the one or more reference signals for use by a network entity to perform the decoder training and the encoder training, wherein receiving the first message is based at least in part on transmitting the data.The node entity of claim 14, wherein the request for the one or more model parameters indicates the identifier.A method for wireless communications by a node entity, comprising:receiving a first message comprising an identifier associated with encoder training at the node entity, the identifier indicating one or more datasets, one or more decoder models, or both, associated with decoder training;transmitting, based on receiving the first message, a second message requesting reference signal resources for use by the node entity to perform data collection to facilitate encoder training or decoder training in accordance with the one or more datasets, the one or more decoder models, or both;receiving, in response to the second message, one or more reference signals via the reference signal resources for performing data collection; andperforming the encoder training using the data collected from the one or more reference signals communicated over the reference signal resources.The method of claim 19, wherein the identifier indicates a first dataset associated with developing a decoder, a second dataset for generating a mapping between a set of decoder inputs and a set of decoder outputs associated with the decoder training, a third dataset for performing the encoder training, a fourth dataset for generating a mapping between a set of encoder inputs and a set of encoder outputs associated with the decoder training, or a combination thereof.
Citation Information
Patent Citations
Data collection procedure and model training
WO2023206512A1
Multi-vendor sequential training
WO2024031622A1
Enhancements for distributed machine learning models in wireless communication systems
WO2024097129A1
Decoder adaptation in machine learning-based wireless communication
WO2024134468A1
Communication method, communication apparatus and communication device
WO2024145797A1