Apparatus and method for identification of a model of a wireless communication system

Abstract

Various aspects of the present disclosure relate to methods, apparatuses, and devices for wireless communication. A first apparatus may determine (702) a first set of information based on input samples and a first index associated with at least one of the input samples or the first set of information, wherein the input samples are determined by the first apparatus or received at the first apparatus, and wherein the first index is based on at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for a second apparatus. The first apparatus may generate (704) one or more datasets, wherein each dataset of the one or more datasets is a subset of the first set of information. The first apparatus may also transmit (706) at least one dataset of the one or more datasets.

Description

APPARATUS AND METHOD FOR IDENTIFICATION OF A MODEL OF A WIRELESS COMMUNICATION SYSTEM TECHNICAL FIELD

[0001] The present disclosure relates to wireless communications, and more specifically to identification of a model of a wireless communication system. BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)). SUMMARY

[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. 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” or “one or both 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.” Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] Various aspects of the present disclosure relate to wireless communications, including improved methods and apparatuses that support identifying a model (e.g., encoder and decoder) of a wireless communication system. A first apparatus (e.g., a base station, a UE, a node of the base station, or a node of the UE, etc.) may determine a first set of information based on input samples and a first index associated with the input samples or the first set of information. The first apparatus may determine the input samples. Additionally, or alternatively, the first apparatus may receive the input samples, for example, from another apparatus (e.g., a base station, a UE, a node of the base station, or a node of the UE, etc.). The first index may be associated with at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for a second apparatus. The first apparatus may generate one or more datasets, wherein each dataset of the one or more datasets is a subset of the first set of information. The first apparatus may also transmit at least one dataset of the one or more datasets. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.

[0006] Figure 2 illustrates an example of a wireless network in accordance with aspects of the present disclosure.

[0007] Figure 3 illustrates an example of a block diagram of a two-sided model in accordance with aspects of the present disclosure.

[0008] Figure 4 illustrates an example of a UE in accordance with aspects of the present disclosure.

[0009] Figure 5 illustrates an example of a processor in accordance with aspects of the present disclosure.

[0010] Figure 6 illustrates an example of a network equipment (NE) in accordance with aspects of the present disclosure.

[0011] Figure 7 illustrates a flowchart of a method performed by a first apparatus in accordance with aspects of the present disclosure.

[0012] Figure 8 illustrates a flowchart of a method performed by a second apparatus in accordance with aspects of the present disclosure.

[0013] Figure 9 illustrates a flowchart of a method performed by a third apparatus in accordance with aspects of the present disclosure. DETAILED DESCRIPTION

[0014] Various aspects of the present disclosure relate to supporting (e.g., configuring, enabling) a two-sided model of a wireless communication system. The two-sided model may be associated with an encoder of a first wireless device which may be referred to as an encoder device) and a decoder of the first wireless device or a second wireless device (which may be referred to as a decoder device). Some functions (e.g., operations, behaviors, features, constraints) of the model may be performed by the first wireless device (e.g., the encoder device) and other functions (e.g., operations, behaviors, features, constraints) of the model may be performed by the first wireless device or the second wireless device (e.g., the decoder device). In some implementations, one or more of the first wireless device (e.g., the encoder device) or the second wireless device (e.g., the decoder device) may manage (e.g., update, adjust, modify) a set of one or more parameters of the two-sided model at a frequency (e.g., rate, pattern, interval). However, in some cases, excessive data may be used, for example, based on a quantity (e.g., amount) of data transferred to update the two-sided model and a frequency (e.g., rate) of the updates.

[0015] By reducing one or more of the transfers including the quantity (e.g., amount) of data for updating the two-sided model or the frequency (e.g., rate) of updating the two-sided model, apparatuses (e.g., wireless devices) performing one or more of encoding or decoding may reduce power consumption, reduce processor usage, reduce data usage, and increase overall system performance.

[0016] Aspects of the present disclosure are described in the context of a wireless communications system.

[0017] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a new radio (NR) network, such as a 5G network, a 5G- Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In otherimplementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.

[0018] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next- generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

[0019] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with an NTN. In some implementations, different geographic coverage areas associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

[0020] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples.

[0021] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a UE-to-UE interface (PC5 interface).

[0022] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., S1, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0023] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a 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)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

[0024] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an S1, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). The PDU session may be an example of alogical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).

[0025] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures). The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

[0026] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., ^=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., ^=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., ^=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., ^=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., ^=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., ^=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0027] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0028] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number(e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., ^=0, ^=1, ^=2, ^=3, ^=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., orthogonal frequency division multiplexing (OFDM) symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., ^=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0029] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz – 7.125 GHz), FR2 (24.25 GHz – 52.6 GHz), FR3 (7.125 GHz – 24.25 GHz), FR4 (52.6 GHz – 114.25 GHz), FR4a or FR4-1 (52.6 GHz – 71 GHz), and FR5 (114.25 GHz – 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

[0030] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., ^=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., ^=1), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., ^=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., ^=2), whichincludes 60 kHz subcarrier spacing; and a fourth numerology (e.g., ^=3), which includes 120 kHz subcarrier spacing.

[0031] Figure 2 illustrates an example of a wireless network 200 in accordance with aspects of the present disclosure. The wireless network 200 may include a NE 102-a (e.g., one embodiment of a NE 102, a gNB), a first UE 104-a (e.g., one embodiment of a UE 104, UE1), a second UE 104-b (e.g., one embodiment of a UE 104, UE2), and a third UE 104-c (e.g., one embodiment of a UE 104, UEK, the third UE 104-c represents any number of additional UEs).

[0032] Specifically, Figure 2 shows one example of the wireless network 200 with one NE 102-a (e.g., may be represented by node ^^and may be equipped with ^ antennas) and ^ UEs104-a, 104-b, 104-c (e.g., may be denoted by ^^, ^^ , ⋯ , ^^ that each have ^ antennas). ^^^^^^may denote a channel at time ^ over frequency band ^, ^ ∈ {1,2, … , ^} , between ^^ and ^^ whichmay form a matrix of size ^ × ^ with complex entries, i.e., ^ ^ ^×^^ ^^^ ∈ ℂ .

[0033] At time ^ and frequency band ^, it may be102-a wants to transmit message ^^^ ^^^ to user ^^ where = {1,2, ⋯ , ^} while it uses " ^^ ^^^ ∈ ℂ^×^ as aprecoding vector. The received signal at ^^, #^^^^^, may be written as:

[0034] #^^ ^^^ = ^^^^^^"^^^^^^^^ ^^^ + %^^^^^,

[0035] where %^^^^^ represents a noise vector at a receiver. In one example, the transmit (Tx)- receive (Rx)be ^^^^^^, #^^^^^.

[0036] To improve an achievable rate of the link, in one example, the NE 102-a selects "^^^^^ that maximizes a received signal-to-interference and noise ratio (SINR). Several different configurations may be used for selection of "^^^^^ where some of the configurations may have some knowledge about ^^^^^^.

[0037] The NE 102-a may get knowledge of ^^^^^^ by direct measurement (e.g., in a time duplex division (TDD) mode and assumingof a channel), or indirectly using information that one of the UEs 104-a, 104-b, and 104-c sends to the NE 102-a (e.g., in a frequency division duplex (FDD) mode). In the indirect method, a large amount of feedback may be used to send accurate information about ^^^^^^. This may require a large amount of data if there are a large number of antennas or / and large frequency bands.

[0038] In one example, a single time slot is analyzed, but the example may be extended to the examples with more than a single time slot. Without loss of generality, ^^^^^^ may be denoted using ^^^.

[0039] ^^^^^ may be defined as a matrix of size ^ × ^ × ^ which is formed by stacking ^^^for all frequency bands (e.g., the entries at ^^&', (, ^)^^^ is equal to ^ ^^ &', ()^^^^. In total, eachUE 104-a, 104-b, and 104-c may provide feedback information about most recent ^ × ^ × ^complex numbers to the NE 102-a.

[0040] A two-sided model is one example described herein to reduce required feedback information where an encoding part (e.g., at the UE) computes a quantized latent representation of the input data, and the decoding part (e.g., at the gNB) gets this latent representation and uses that to reconstruct the desired output. The input data may be data which is based on channel measurements. For example, may be raw channel inputs of ^^or ^^^, or, for example, the precoders that are computed from the channel matrix (e.g., the eigenvector associated with the largest eigen-vector of ^^for each subband).

[0041] Figure 3 illustrates an example of a block diagram of a two-sided model 300 (e.g., NN-based model) in accordance with aspects of the present disclosure. The two-sided model 300 includes a node A 302 (e.g., encoder, encoding model, Me) and a node B 304 (e.g., decoder, decoding model, Md). Figure 3 illustrates only one example of a two-sided model 300, while in other examples the location of the encoder and decoder may be swapped. Input data 306 is provided to the node A 302, then there is a latent representation 308 in communications from the node A 302 to the node B 304, and the node B 304 outputs data 310. In some configurations, the node A 302 is located at the UE 104, and the node B 304 is located at the NE 102, but in other configurations the node A 302 and the node B 304 may be located in other devices.

[0042] In some systems, ^*and ^+may be used for a logical model. Meaning that node A 302 may chose not to use ^*directly and instead develop and use several internal models like ^*^^^, ^*^^^,…, ^*^^^based on some private parameters and decisions. In these cases, onebe that all these internal models should meet at least the performance of pairing original ^*with ^+. With this explanation, the node B 304 may not need to be concerned about what is the actual model used at the node A 302. The same may be correct for ^+and some internal models at the node B 304.

[0043] There may be several methods to train neural network (NN) modules of a two-sided model, including, centralized training, simultaneous training, and separate training. Similarly,updating a two-sided model may be carried out centrally on one entity, on different entities but simultaneously, or separately. In separate training and / or model update, the NN modules of the node , 302 (e.g., UE) and the node ^ 304 (e.g., gNB) may be trained in different training sessions (e.g., no forward or backpropagation path between the two parts). One advantage of separate training may be that the node A 302 and the node ^ 304 may not need to be aware of the internal structure of the NN module of the other side.

[0044] The node A 302 and the node B 304 may decide not to use a single encoder-decoder pair, and instead may construct different encode-decoder pairs which are applicable to different conditions of the node A 302 and / or the node B 304 since the samples of different states may have different statistics compared to other settings, and, therefore, it may be reasonable to construct two different encoder-decoder models for these two cases instead of trying to train a single model that can generalize well to different settings. For example, for channel state information (CSI) feedback systems, it may be beneficial to have separate encoder-decoder pairs for unlicensed mobile access (UMA) environment and indoor environment compared to systems that build a single encoder-decoder pair covering both environments. So, it may be assumed thatit may be beneficial to design ^*&-) − ^+&-), for - = {1,2, … , ^} where the - / 0pair is trained based on a training data collected node A 302 and the node B 304 are in one conditionor a set of conditions. Condition may refer to when the parameters of the node A 302 and the node B 304 are in a certain state.

[0045] If there are multiple models, it may be difficult to differentiate between them and / or activate / deactivate them. Moreover, the node A 302 and the node B 304 may not be willing to reveal some part of their parameters which still affect their conditions.

[0046] In some embodiments described herein, there may be a scheme in which the nodes involved in training and inference can exchange information using which consistency may be achieved between the conditions under which the model has been trained and will be used for inference, while not sending sensitive information of one-side to another side. For example, a UE may create separate models in situations in which it has a low-battery and is outdoors, a low- battery and is indoor, a high-battery and is outdoors, and high-battery and indoor, but it may not be willing to tell the other side that if it has low or high battery level in none of the life cycle management (LCM) stages (e.g., data collection, model training, model inference).

[0047] One way to differentiate different models developed under different conditions is that when a UE and / or a gNB develop a model they decide on an identifier (ID) for that model. ThisID may be used for activation and deactivation of models. The shortcoming of this scheme may be a number of different models that may need to be developed for different modes of operations and their combinations (since some models may be developed to support more than one mode of operations). There may also be a complexity concerning how to exchange information between the nodes and associate them with the model ID such that the internal conditions of the nodes remain transparent to the other side.

[0048] Some systems may use a dataset ID. This may mean that an ID is assigned to each dataset of samples that has been used collected for a model training and then the model ID is constructed based on the ID of the dataset. In such systems, it may not completely be determined how conditions of a node A and node B can be considered in assignment of dataset IDs. Additionally, one dataset may contain samples from different UE and / or gNB conditions, therefore, if a single ID is assigned to a dataset, then creation of different models for different UE and / or gNB conditions based on their associated samples may not be straightforward.

[0049] Examples herein include model identification of multiple models (e.g., different model architecture, different degree of complexity, different model parameterization, different input-output parameter relationships, different preprocessing on the input data, different model output (e.g., size, dimensionality), different quantization, etc.) for a given (or a subset of) dataset based on conditions and / or additional conditions for a first node (e.g., node A 302) and / or a second node (node B 304). The conditions and / or additional conditions for node A and / or node B can include a parameter based on the model characteristic or to identify a characteristic of the model.

[0050] Although the description in the disclosure may be primarily described with respective to two-sided models, the techniques may also be applicable to single-sided models.

[0051] In one example, two-sided models ^1 , 2 = {1,2, … , ^} are trained, wherein each ofthe models are designed for a set of conditions of node A and node B. Each model may include an encoder model ^1 an 1 * d a decoder model ^+residing at a node A and a node B, respectively. It should be noted that the model may be at a single sided node (e.g., there is no ^1 1 * or ^+part). Also, there may be configurations in which the model depends only on the conditions of one side (e.g., only node A or node B). The examples herein may be applied for these configurations as well. It may also be possible that we train different models for the same conditions of node A and node B. For example, a high complexity model and a low complexity model both may be trained based on a single dataset collected under a particular conditions of node A and node B.

[0052] The conditions of node A and node B may be related to some states and / or parameters of each of the node A and the node B, and also may depend on other nodes of the network. These states and / or parameters may be communicated during the UE-capability report communication, UE configuration, measurement configuration and / or reporting, communicated during the initialization, joining, and / or synchronization.

[0053] One example may assume that the UE is in an indoor location, is equipped with 2 Rx antenna ports and has an antenna spacing δ. At the gNB side, the gNB may be equipped with 32 Tx antenna ports over 2 panels, wherein each of the Tx antenna ports is a virtualization of 4 antenna elements.

[0054] As used herein, a condition parameter may correspond to information that is shareable between both a UE side and a NW side, wherein the information is parametrized to one or more parameters. Based on certain examples, the number of antenna ports at the gNB and the UE may be possible condition parameters. It should be noted that condition parameters may also be referred to as metadata.

[0055] Moreover, state information may correspond to information that is not shareable between the UE side and the NW side, e.g., the gNB antenna virtualization and the Rx antenna spacing. More generally, both shareable and non-shareable information may correspond to state information.

[0056] In some examples, to be able to effectively train, pair, and activate a two-sided model, there may be a data collection phase, a training phase, and an inference phase.

[0057] In a data collection phase, the node A may perform the data collection task, and a data collection procedure may have access to a subset of conditions of node A and node B denoted by 345and 346. The actual condition name and / or value may be used or a dummy name and / or value for node A and / or node B may be used in place of the actual condition name and / or value. In some examples, a node specific condition ID indicates a set of node parameters and associated values (e.g., actual condition parameter name and / or value). In some examples, a local condition index and / or ID is associated with a set of local parameters (and values) at a node (e.g., the dummy condition parameter name and / or value, a local condition parameter based on the model characteristic or to identify a characteristic of the model, etc.). In some examples, a node specific condition ID may also indicate a local condition ID.

[0058] Also in the data collection phase, the local condition ID may be shared and / or communicated to another node (e.g., node B) to indicate the local condition at node A withoutsharing the set of local parameters. Assuming that node A is collecting the data, it may also be assumed that the information regarding the subset of conditions of node A and node B may been communicated to node A. In one example, at least a portion of the subset of conditions of node B are communicated to node A prior to the dataset transfer and / or delivery from node A. In another example, at least a portion of the subset of conditions of node B are communicated to node A after the dataset transfer and / or delivery from node A. A similar description may be used if node B is collecting data.

[0059] Under certain assumptions, node A collects samples. As one example, the collected samples may be related to state information of the channel between the node A and the node B. Each or each group of collected samples may be associated with a condition parameter which indicates the condition of node A and / or node B conditions (e.g., node specific condition ID and / or node local condition ID). A mapping table may be used to associate an ID to possible combination and / or pair of the condition (of node A and / or node B), and then that ID may be used as the condition parameter. The mapping table may be communicated with the other side so both sides have the same understanding. The collected samples may be associated with timing information as well.

[0060] The dataset collected by node A may then be constructed as the union of one or a few of the collected samples and the metadata of the dataset may be determined based on the condition parameter of each or each group of collected samples that exist in that dataset. It should be noted that one training dataset may contain samples collected at different node A and / or node B conditions. The collected dataset may be further transmitted to another node. Moreover, the transmitted dataset may be associated with an identification.

[0061] During the collection of samples, node A and / or node B may record state information, namely 75 / 76, which may include one or a few of its own conditions, states, and / or parameters which may not be visible to the data collection procedure. In one example, these set of conditions, states, and / or parameters may correspond to a set of local parameters (and values) and may be associated with a local condition index and / or ID.

[0062] In some examples, training of the two-sided model may be performed. The complete dataset may be constructed from data collected during one or multiple time periods and may be generated from a single or multiple collecting nodes (e.g., node A in the previous section). It should be noted that each sample and / or group of samples in the complete dataset are collected under certain conditions for node A and node B. This information, and the information of 75 / 76(e.g., if possible to have access to), may be used for creation of one or more training datasets for creation of the first part of the model. Moreover, the encoder and decoder model may be trained on a single node or may be trained on two different nodes.

[0063] For example, assume that it is desired to train the decoder part (e.g., node B part) of the model. It may be assumed that the training of the decode part may happened at a node that node B is able to share its state information 76with (e.g., the same node B or a trustworthy physical and / or virtual node associated with node B). The training node may then use the metadata of each dataset, and if possible 76, to partition the whole dataset into a few training datasets, wherein each of them contain samples collected under similar (or not that different) conditions. This may help that the sample of each training dataset remains statistically closer to each other, which may help obtain better convergence of the trained model, models with higher accuracy, or models with lower complexity.

[0064] Each of the training datasets (may include one training dataset) may then be used to train one or multiple models. This model in general may be a two-sided model, a one-sided model, or one side of a two-sided model.

[0065] Moreover, one training dataset may be used to train more than one model. For example, set 9^, may be used to train the first two-sided model if the encoder and decoder backbone structure is based on a convolutional neural network structure, and also the same set 9^may be used to train the second two-sided model if the encoder and decoder backboneis based on a transformer networks.

[0066] The metadata associated with each model may be determined based on the metadata of the datasets used during the training, the state information 75 / 76(if available), and parameters regarding the model. The parameter may directly or indirectly show the different models constructed from the same training dataset (e.g., the model backbone structure).

[0067] In one embodiment, the training datasets may be used to train complete two-sided models. In such scenarios, the complete model may be available. It should be noted that although the two-sided models are mainly trained using a training dataset, it may also be considered that the trained model may satisfy some requirements (e.g., imposed by another entity). For example, there may be a requirement that the output of the encoder model and a predetermined decoder also produce acceptable performance, or a requirement that the decoder may decode the output of the predetermined encoder and produce acceptable results. One way to consider these extra requirements may be to include them in the loss function with a weight during the training.

[0068] In another embodiment, the training datasets may be used to train only one side of the two-sided model. For example, there may be a first case and a second case.

[0069] In a first case, each of the training datasets may be used to train one or multiple decoder models. Although the decoder models are mainly trained using the training dataset, it may also consider that the trained model may satisfy some requirements (e.g., imposed by another entity). For example, there may be a requirement that the trained decoder model and a predetermined encoder also produce acceptable performance, or that the input and / or output of the trained decoder model may also be similar to a predetermined decoder model. One way to consider these extra requirements is to include them in a loss function with a weight during training.

[0070] In a second case, each of the training datasets may be used to train one or multiple encoder models. Although the encoder models are mainly trained using the training dataset, the trained model may satisfy some requirements imposed by another entity as well. For example, there may be a requirement that the trained encoder model and a predetermined decoder also produce acceptable performance, or that the input and / or output of the trained encoder model may be similar to a predetermined encoder model. One way to consider these extra requirements is to include them in the loss function with a weight during the training.

[0071] In these two cases, the other part of the two-sided model may need to be trained.

[0072] In the first case, one or multiple decoder models may already be trained, and a metadata may be associated with each of the decoder models. Assuming that the encoder model (associated with each decoder model) is to be trained on a separate node (e.g., a node other than node B or the node where the decoder model is trained), there may be different options as follows:

[0073] In a first option, information regarding the trained decoder model (or a lower complexity decoder model based on the trained decoder model, e.g., using transfer learning to train a smaller decoder model or a reference decoder model based on the trained decoder model, the reference model may be a model that the other node supports) is transmitted to the other node which does the training of the encoder model.

[0074] In a second option, as during the training of the decoder model, a local encoder model may need to be trained, the information regarding the trained local encoder model (or a lower complexity encoder model based on the local encoder model e.g., using transfer learning to train a smaller encoder model or a reference encoder model based on the trained local encoder model,the reference model may be a model that the other node supports) may be sent to the other node which does the training of the encoder model. The metadata of the local encoder model (or the lower complexity encoder model, or reference encoder model) may be determined based on the metadata of the trained decoder model. In one implementation, it may get the same metadata. It should be noted that the local encoder model may have a different structure than the actual encoder model.

[0075] In some examples, transmission of information regarding a model may have different alternatives:

[0076] In a first alternative, there may be transmission of the actual model (both structure and the trained parameters) and, if needed, its associated metadata. In a second alternative, assuming that model structure is already known at the other side (e.g., standardized model), there may be transmission of the trained parameters only and, if needed, its associated metadata.

[0077] In a third alternative, there may be transmission of a second model (both structure and the trained parameters) and, if needed, its associated metadata where this model is trained to have the same input and / or output relation of the trained model. This option may be useful to not reveal the actual trained model that may be used by the other side, but this information regarding how the model is working may still be given. Moreover, a teacher-student scheme may be used to train the second model using the actual trained model. The associated metadata of the second model may be determined based on the metadata actual trained model. In one implementation, it may get the same metadata.

[0078] In a fourth alternative, assuming that the second model structure is already known at the other side, only the parameters of the second model may be transmitted the other side and, if needed, its associated metadata may be transmitted.

[0079] In a fifth alternative, a dataset containing samples showing the input and / or output or expected output of the model may be generated and then the generated dataset may be transmitted, and, if needed, its associated metadata may be transmitted. The metadata associated with the generated dataset may be determined based on the metadata of the model. In one implementation, it can get the same metadata of the model used for generation of the dataset.

[0080] In a first option, the input of the model is related to the latent representation (generated using, for example, the output of the local encoder model) of the input data (based on the training dataset of the trained decoder model) and the output is the output of the traineddecoder model (e.g., the output of the trained decoder model may be based on the training dataset in a compression use case).

[0081] In a second option, the input data of the model is based on the training dataset of the trained decoder model and output data is based on the output of the trained local encoder model.

[0082] In some examples, the transmitted dataset may be associated with an identification parameter and / or number.

[0083] To reduce overhead, instead of transmission of the whole generated dataset, some parts of the dataset may be indicated to the other node based on the previous datasets which may be signaled and / or transferred between the nodes previously. The dataset IDs of the previous exchanged datasets may be used to identify those datasets. In some examples, the dataset may be created based on a set of training dataset IDs. The latent representation (e.g., input in the first option, output in the second option) may be associated with a output, latent, and / or compression ID. The dataset may be indicated based on at least one (e.g., training dataset ID, output, latent, and / or compression ID) pair. In some examples, a training dataset ID may be associated with multiple output, latent, and / or compression IDs (e.g., for multiple models). In some examples, an output, latent, and / or compression ID may be associated with multiple training dataset IDs (e.g., for a model dataset constructed by aggregating multiple training datasets).

[0084] If a first option is used (e.g., send information regarding the trained decoder model), the node training the encoder model uses the information received for the decoder model to train the local decoder model. For example, it directly considers the received model as its decoder, uses a teacher-student method to train its own decoder model using the received local decoder model, and uses the received dataset to train the decoder such that its input / output relation be as much as possible similar to the input / output relation of the receive dataset. The metadata of the trained local decoder model may be determined based on the received metadata of the model (e.g., using the first through fourth alternatives described herein) or the metadata of the generated dataset (e.g., the fifth alternative). In one implementation, it may get the same metadata it received from the other node. Then the trained local decoder model may be fixed and the node trains the encoder model to match the trained local decoder model. The metadata of the trained encoder model may be determined based of metadata of the trained local decoder model. In one implementation, it may get the same metadata of the trained local decoder model.

[0085] If a second option is used (e.g., send information regarding the local encoder model), the node training the encoder model uses the information received for the local encoder model totrain the encoder model. For example, it may directly consider the received model as its encoder, use a teacher-student method to train its own encoder model using the received encoder model, and / or use the received dataset to train the encoder such that its input / output relation be as much as possible similar to the input / output relation of the receive dataset. The metadata of the trained encoder model may be determined based on the received metadata of the model (e.g., using the first through fourth alternatives described herein) or the metadata of the generated dataset (e.g., the fifth alternative). In one implementation, it may get the same metadata it received from the other node.

[0086] It should be noted that it may be possible to train multiple encoder models for different backbone structures or different state information 75(if available). Therefore, the metadata of each trained encoder model may further contain information regarding the state information 75(if applicable), and parameters regarding the model.

[0087] In certain examples, both encoder and decoder models are trained. It should be noted that the node training the encoder model may further transmit information regarding the trained encoder model to the node that was training the decoder model along with the metadata associated with that encoder model. This information may be sent using any of the five alternatives schemes described herein. The node with the decoder model may use this information to update / retrain its local encoder model, fix it, and then update the decoder model based on the updated / retrained local encoder model. The updated / retrained decoder model may determine its associated metadata based on the metadata it received from the other side. The process explained in the first case may be repeated for a few rounds and may be stopped based on a stopping criteria.

[0088] It should be noted that a combination of different examples described herein may be used. For example, the first alternative may be used for the first option so the UE can have an initial encoder model. Then, if the performance of the resulted two-sided model is not satisfactory (e.g., since the input distribution of the UE is not matching well with the received encoder), the third alternative for the second option may be used. The UE then may train, retrain, and / or update its encoder based on the received decoder model.

[0089] In a second case, one or multiple encoder models are already trained, and a metadata may be associated with each of the encoder models. Assuming that the decoder model (associated with each encoder model) is to be trained on a separate node (e.g., a node other than node A or the node where the encoder model is trained), there may be different options to follow:

[0090] In a first option, information regarding the trained encoder model may be transmitted to the other node which does the training of the decoder model.

[0091] In a second option, as during the training of the encoder model, a local decoder model may need to be trained as well. Then, the information regarding the trained local decoder model may be sent to the other node which does the training of the decoder model. The metadata of the local decoder model may be determined based on the metadata of the trained encoder model. In one implementation, it may get the same metadata. It should be noted that the local decoder model may have a different structure than the actual decoder model.

[0092] Transmission of information regarding a model may have different alternatives similar to what is described in the first case, just for input and output of the model in the fifth alternative, there may be the following differences:

[0093] In the first option, the input data of the model is based on the training dataset of the trained encoder model and output data is based on the output of the trained encoder model. In the second option, the input of the model is related to the latent representation generated using the trained encoder model of the input data (e.g., based on the training dataset used for training of the encoder model) and the output is the expected output of the local decoder model.

[0094] If the first option is used (e.g., send information regarding the trained encoder model), the node training the decoder model uses the information received for the trained encoder model to train the local encoder model. For example, it may directly consider the received model as its local encoder, use a teacher-student method to train its own local encoder model using the received encoder model, and / or use the received dataset to train the local encoder such that its input / output relation be as much as possible similar to the input / output relation of the receive dataset. The metadata of the trained local encoder model may be determined based on the received metadata of the model (e.g., the first through fourth alternatives) or the metadata of the generated dataset (e.g., the fifth alternative). In one implementation, it may get the same metadata it received from the other node. Then the trained local encoder model may be fixed and the node may train the decoder model to match the trained local encoder model. The metadata of the trained decoder model may be determined based on metadata of the trained local encoder model. In one implementation, it may get the same metadata of the trained local encoder model.

[0095] If the second option is used (e.g., send information regarding the local decoder model), the node training the decoder model may use the information received for the localdecoder model to train the decoder model. For example, it may directly consider the received model as its decoder, use a teacher-student method to train its own decoder model using the received decoder model, and / or use the received dataset to train the decoder such that its input / output relation be as much as possible similar to the input / output relation of the receive dataset. The metadata of the trained decoder model may be determined based on the received metadata of the model (e.g., the first through fourth alternatives) or the metadata of the generated dataset (e.g., the fifth alternative). In one implementation, it may get the same metadata it received from the other node.

[0096] It should be noted that it is possible to train multiple decoder models for different backbone structures or different state information 76(if available). Therefore, the metadata of each trained decoder model may further contain information regarding the state information 76(if applicable), and extra parameters regarding the model. In certain examples, both encoder and decoder models may next be trained.

[0097] It should be noted that the node training the decoder model may further transmit information regarding (each of) the trained decoder model to the node that was training the encoder model along with the metadata associated with that decoder model. This information may be sent using any of the five alternatives described herein. The node with the encoder model may use this information to update and / or retrain its local decoder model, fix it, and then update the encoder model based on the updated / retrained local decoder model. The updated / retrained encoder model may determine its associated metadata based on the metadata it received from the other side. The process of the second case may be repeated for a few rounds and may be stopped based on a stopping criteria.

[0098] It should be noted that a combination of these scheme may be used. For example, the first alternative may be used for the first option, so the UE may have an initial encoder model. Then, if the performance of the resulted two-sided model is not satisfactory (e.g., since the input distribution of the UE is not matching well with the received encoder), the third alternative for the second option may be used. The UE then may train, retrain, and / or update its encoder based on the received decoder model.

[0099] In an inference phase, it may be assumed that one or multiple encoder models are trained and stored along with their corresponding metadata in a node A-side node, and also one or multiple decoder models are trained and stored along their corresponding metadata in a node B-side node.

[0100] During the inference phase, in one implementation, the encoder model may be determined based on the current values of 345and / or 346(e.g., node A specific condition ID and / or node A local condition ID, node B specific condition ID and / or node B local condition ID), where 346: is assumed to be communicated with the node A-side node.

[0101] In another implementation, selection of the encoder model may depend on the values of parameters in 75or on parameters determining the encoder model which are included in the metadata of the stored encoder models. In a further implementation, selection of the encoder model may depend on the selection of the decoder model. In this case, the node A-side node receives some information regarding the metadata of the selected decoder model and then selects the encoder model that matches the metadata of the decoder model. The metadata of the selected decoder may provide information regarding 346, parameters related to 76(if possible), and parameters used during training of the decoder model.

[0102] Similarly, the decoder model may be determined as using one or more different implementations. In one implementation, the decoder model may be determined based on the current values of 345and / or 346, where 345: is assumed to be communicated with node B-side node. In another implementation, selection of the decoder model may depend on the values of parameters in 76or on extra parameters determining the decoder model which are included in the metadata of the stored decoder models.

[0103] In a further implementation, selection of the decoder model may depend on the selection of the encoder model. In this case, the node B-side node receives some information regarding the metadata of the selected encoder model and then selects the decoder model that matches the metadata of the encoder model. The metadata of the selected encoder may provide information regarding 345, parameters related to 75(if possible), and parameters used during training of the encoder model.

[0104] In one implementation, the two-sided model is intended for channel state information (CSI) feedback compression, where node A and node B correspond to the UE side and the NW side respectively. With this implementation, the data collection may be based on a first set of DL RSs (e.g., CSI-RS received at the UE based on a configured CSI reporting setting), a CSI resource setting, or a combination thereof. The UE may feed back CSI measurements to the network side based on one or more CSI reports or dataset reports over a physical uplink channel.

[0105] The NW side may collect a plurality of datasets from a plurality of UEs, wherein the plurality of datasets corresponds to a common cell ID, a common TCI state, a common antennaconfiguration, a common CSI reporting setting, a common CSI resource setting, or a combination thereof.

[0106] The NW side may train a first model for CSI prediction or beam management based on the plurality of datasets in addition to the set of conditions and / or parameters, if applicable. The first model may be based on a first model training at the NW side.

[0107] The NW side may signal a model ID or a set of parameters corresponding to the model to the UE side. In one example, all UEs on the UE side are associated with the same model ID or the same set of parameters, whereas, in another example, each UE is associated with a distinct model ID or a distinct set of parameters.

[0108] Each UE in the UE side may use a second set of DL RSs for training a second model, wherein the second model is based on the first model signaled via the NW side. In one example, the second model includes an additional set of layers, wherein the additional set of layers is based on a second model training at the UE.

[0109] Figure 4 illustrates an example of a UE 400 in accordance with aspects of the present disclosure. The UE 400 may include a processor 402, a memory 404, a controller 406, and a transceiver 408. The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0110] The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0111] The processor 402 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, a field programmable gate array (FPGA), or any combination thereof). In some implementations, the processor 402 may be configured to operate the memory 404. In some other implementations, the memory 404 may be integrated into the processor 402. The processor 402 may be configured to execute computer-readable instructions stored in the memory 404 to cause the UE 400 to perform various functions of the present disclosure.

[0112] The memory 404 may include volatile or non-volatile memory. The memory 404 may store computer-readable, computer-executable code including instructions when executed by the processor 402 cause the UE 400 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 404 or another type of memory. 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 place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0113] In some implementations, the processor 402 and the memory 404 coupled with the processor 402 may be configured to cause the UE 400 to perform one or more of the functions described herein (e.g., executing, by the processor 402, instructions stored in the memory 404). For example, the processor 402 may support wireless communication at the UE 400 in accordance with examples as disclosed herein. For example, the processor 402 coupled with the memory 404 may be configured to cause the UE 400 to determine a first set of information based on input samples and a first index associated with the input samples or the first set of information, wherein the input samples are determined by the first apparatus or received at the first apparatus, and wherein the first index is associated with at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for a second apparatus. The UE 400 may also generate one or more datasets, wherein each dataset of the one or more datasets is a subset of the first set of information. The UE 400 may transmit at least one dataset of the one or more datasets.

[0114] The controller 406 may manage input and output signals for the UE 400. The controller 406 may also manage peripherals not integrated into the UE 400. In some implementations, the controller 406 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 406 may be implemented as part of the processor 402.

[0115] In some implementations, the UE 400 may include at least one transceiver 408. In some other implementations, the UE 400 may have more than one transceiver 408. The transceiver 408 may represent a wireless transceiver. The transceiver 408 may include one or more receiver chains 410, one or more transmitter chains 412, or a combination thereof.

[0116] A receiver chain 410 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 410 may include one ormore antennas for receive the signal over the air or wireless medium. The receiver chain 410 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 410 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 410 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0117] A transmitter chain 412 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 412 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 412 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 412 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0118] Figure 5 illustrates an example of a processor 500 in accordance with aspects of the present disclosure. The processor 500 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 500 may include a controller 502 configured to perform various operations in accordance with examples as described herein. The processor 500 may optionally include at least one memory 504, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 500 may optionally include one or more arithmetic-logic units (ALUs) 506. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0119] The processor 500 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 500) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM(SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), and others).

[0120] The controller 502 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 500 to cause the processor 500 to support various operations in accordance with examples as described herein. For example, the controller 502 may operate as a control unit of the processor 500, generating control signals that manage the operation of various components of the processor 500. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

[0121] The controller 502 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 504 and determine subsequent instruction(s) to be executed to cause the processor 500 to support various operations in accordance with examples as described herein. The controller 502 may be configured to track memory address of instructions associated with the memory 504. The controller 502 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 502 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 500 to cause the processor 500 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 502 may be configured to manage flow of data within the processor 500. The controller 502 may be configured to control transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 500.

[0122] The memory 504 may include one or more caches (e.g., memory local to or included in the processor 500 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 504 may reside within or on a processor chipset (e.g., local to the processor 500). In some other implementations, the memory 504 may reside external to the processor chipset (e.g., remote to the processor 500).

[0123] The memory 504 may store computer-readable, computer-executable code including instructions that, when executed by the processor 500, cause the processor 500 to perform various functions described herein. The code may be stored in a non-transitory computer- readable medium such as system memory or another type of memory. The controller 502 and / or the processor 500 may be configured to execute computer-readable instructions stored in thememory 504 to cause the processor 500 to perform various functions. For example, the processor 500 and / or the controller 502 may be coupled with or to the memory 504, the processor 500, the controller 502, and the memory 504 may be configured to perform various functions described herein. In some examples, the processor 500 may include multiple processors and the memory 504 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 herein.

[0124] The one or more ALUs 506 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 506 may reside within or on a processor chipset (e.g., the processor 500). In some other implementations, the one or more ALUs 506 may reside external to the processor chipset (e.g., the processor 500). One or more ALUs 506 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 506 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 506 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 506 may support logical operations such as AND, OR, exclusive-OR (XOR), not-OR (NOR), and not-AND (NAND), enabling the one or more ALUs 506 to handle conditional operations, comparisons, and bitwise operations.

[0125] The processor 500 may support wireless communication in accordance with examples as disclosed herein. The processor 500 may be configured to or operable to support a means for: determining a first set of information based on input samples and a first index associated with the input samples or the first set of information, wherein the input samples are determined by the first apparatus or received at the first apparatus, and wherein the first index is associated with at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for a second apparatus, generating one or more datasets, wherein each dataset of the one or more datasets is a subset of the first set of information, and transmitting at least one dataset of the one or more datasets.

[0126] Figure 6 illustrates an example of a NE 600 in accordance with aspects of the present disclosure. The NE 600 may include a processor 602, a memory 604, a controller 606, and a transceiver 608. The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations thereof or various components thereof may be examples of means forperforming various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0127] The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0128] The processor 602 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 602 may be configured to operate the memory 604. In some other implementations, the memory 604 may be integrated into the processor 602. The processor 602 may be configured to execute computer-readable instructions stored in the memory 604 to cause the NE 600 to perform various functions of the present disclosure. For example, the processor 602 coupled with the memory 604 may be configured to cause the NE 600 to: receive one or more datasets from at least one of a first apparatus or another apparatus, wherein each dataset of the one or more datasets or first samples of each dataset of the one or more datasets are associated with a first index, and wherein the first index is associated with at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for the second apparatus, develop one or more decoder models, wherein each decoder model of the one or more decoder models is based on the one or more datasets or one or more subsets of the one or more datasets, assign a decoder metadata to each decoder model of the one or more decoder models, wherein the decoder metadata is based on at least one of the first index, a second index, and one or more model parameters, and wherein the second index represents the first set of one or more parameters for the second apparatus, and is associated with second samples of the one or more datasets, and transmit a set of model information associated with a model, wherein the model and associated model metadata are associated with the one or more decoder models and the decoder metadata, another model developed to behave similar to the one or more of the decoder models, and wherein another metadata of the another model is determined based on the decoder metadata, or a second model and its associated metadata.

[0129] The memory 604 may include volatile or non-volatile memory. The memory 604 may store computer-readable, computer-executable code including instructions when executed by theprocessor 602 cause the NE 600 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 604 or another type of memory. 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 place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0130] In some implementations, the processor 602 and the memory 604 coupled with the processor 602 may be configured to cause the NE 600 to perform one or more of the functions described herein (e.g., executing, by the processor 602, instructions stored in the memory 604). For example, the processor 602 may support wireless communication at the NE 600 in accordance with examples as disclosed herein.

[0131] The controller 606 may manage input and output signals for the NE 600. The controller 606 may also manage peripherals not integrated into the NE 600. In some implementations, the controller 606 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 606 may be implemented as part of the processor 602.

[0132] In some implementations, the NE 600 may include at least one transceiver 608. In some other implementations, the NE 600 may have more than one transceiver 608. The transceiver 608 may represent a wireless transceiver. The transceiver 608 may include one or more receiver chains 610, one or more transmitter chains 612, or a combination thereof.

[0133] A receiver chain 610 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 610 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 610 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 610 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 610 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0134] A transmitter chain 612 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 612 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques suchas amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 612 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 612 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0135] Figure 7 illustrates a flowchart of a method 700 in accordance with aspects of the present disclosure. The operations of the method 700 may be implemented by a first apparatus (e.g., UE) as described herein. In some implementations, a UE 400 may execute a set of instructions to control the function elements of a processor to perform the described functions.

[0136] At 702, the method may include determining a first set of information based on input samples and a first index associated with at least one of the input samples or the first set of information, wherein the input samples are determined by the first apparatus or received at the first apparatus, and wherein the first index is based on at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for a second apparatus. The operations of 702 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 702 may be performed by a UE as described with reference to Figure 4.

[0137] At 704, the method may include generating one or more datasets, wherein each dataset of the one or more datasets is a subset of the first set of information. The operations of 704 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 704 may be performed by a UE as described with reference to Figure 4.

[0138] At 706, the method may include transmitting at least one dataset of the one or more datasets. The operations of 706 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 706 may be performed by a UE as described with reference to Figure 4.

[0139] Figure 8 illustrates a flowchart of another method 800 in accordance with aspects of the present disclosure. The operations of the method 800 may be implemented by a second apparatus (e.g., NE) as described herein. In some implementations, a NE 600 may execute a set of instructions to control the function elements of a processor to perform the described functions.

[0140] At 802, the method may include receiving one or more datasets from at least one of a first apparatus or another apparatus, wherein each dataset of the one or more datasets or first samples of each dataset of the one or more datasets are associated with a first index, and wherein the first index is associated with at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for the second apparatus. The operations of 802 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 802 may be performed by a NE as described with reference to Figure 6.

[0141] At 804, the method may include developing one or more decoder models, wherein each decoder model of the one or more decoder models is based on the one or more datasets or one or more subsets of the one or more datasets. The operations of 804 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 804 may be performed by a NE as described with reference to Figure 6.

[0142] At 806, the method may include assigning a decoder metadata to each decoder model of the one or more decoder models, wherein the decoder metadata is based on at least one of the first index, a second index, and one or more model parameters, and wherein the second index represents the first set of one or more parameters for the second apparatus, and is associated with second samples of the one or more datasets. The operations of 806 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 806 may be performed by a NE as described with reference to Figure 6.

[0143] At 808, the method may include transmitting a set of model information associated with a model, wherein the model and associated model metadata are associated with the one or more decoder models and the decoder metadata, another model developed to behave similar to the one or more of the decoder models, and wherein another metadata of the another model is determined based on the decoder metadata, or a second model and its associated metadata. The operations of 808 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 808 may be performed by a NE as described with reference to Figure 6.

[0144] Figure 9 illustrates a flowchart of another method 900 in accordance with aspects of the present disclosure. The operations of the method 900 may be implemented by a third apparatus (e.g., NE) as described herein. In some implementations, a NE 600 may execute a set of instructions to control the function elements of a processor to perform the described functions.

[0145] At 902, the method may include developing one or more encoder models, wherein each encoder model of the one or more encoder models is based on the one or more sets of model information. The operations of 902 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 902 may be performed by a NE as described with reference to Figure 6.

[0146] At 904, the method may include assigning an encoder metadata to each encoder model of the one or more encoder models, wherein the encoder metadata is based on at least one of the one or more sets of model information, model metadata of the one or more sets of model information, and one or more encoder model parameters. The operations of 904 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 904 may be performed by a NE as described with reference to Figure 6.

[0147] At 906, the method may include storing the one or more encoder models and the metadata of each encoder model of the one or more encoder models. The operations of 906 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 906 may be performed by a NE as described with reference to Figure 6.

[0148] It should be noted that the methods described herein describe possible implementations, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0149] 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

CLAIMS What is claimed is:

1. A first apparatus, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first apparatus to: determine a first set of information based on input samples and a first index associated with at least one of the input samples or the first set of information, wherein the input samples are determined by the first apparatus or received at the first apparatus, and wherein the first index is based on at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for a second apparatus; generate one or more datasets, wherein each dataset of the one or more datasets is a subset of the first set of information; and transmit at least one dataset of the one or more datasets.

2. The first apparatus of claim 1, wherein the at least one processor is configured to cause the first apparatus to associate each dataset of the one or more datasets with a metadata, an identifier, or both.

3. The first apparatus of claim 2, wherein the at least one processor is configured to cause the first apparatus to transmit the identifier or the metadata associated with each dataset of the one or more datasets.

4. The first apparatus of claim 1, wherein the at least one processor is configured to cause the first apparatus to determine a set of input samples.

5. The first apparatus of claim 4, wherein the set of input samples is based on a channel data representation.

6. The first apparatus of claim 5, wherein the channel data representation is based on one or more reference signals received from the second apparatus.

7. The first apparatus of claim 5, wherein the channel data representation is associated with one or more different transmit (Tx)-receive (Rx) pairs communicated over different frequency bands or different time slots.

8. The first apparatus of claim 1, wherein the first index includes a parameter indicating a measurement time, a measurement period, or both.

9. The first apparatus of claim 1, wherein the first index is based on an identifier determined based on a mapping table associated with different combinations of the first set of one or more parameters for the first apparatus and the second set of one or more parameters for the second apparatus.

10. The first apparatus of claim 9, wherein the at least one processor is configured to cause the first apparatus to transmit the mapping table.

11. The first apparatus of claim 1, wherein the at least one processor is configured to cause the first apparatus to receive the second set of one or more parameters.

12. The first apparatus of claim 1, wherein the at least one processor is configured to cause the first apparatus to generate state information associated with the second apparatus including one or more of: a value of at least one of the second set of one or more parameters; a time slot; or a time duration.

13. The first apparatus of claim 12, wherein the at least one processor is configured to cause the first apparatus to transmit the state information.

14. The first apparatus of claim 1, wherein the first apparatus is a UE or a node at the UE.

15. The first apparatus of claim 1, wherein the first apparatus is a base station or a node at the base station.

16. The first apparatus of claim 1, wherein the second apparatus is a UE or a node at the UE.

17. The first apparatus of claim 1, wherein the second apparatus is a base station or a node at the base station.

18. A processor for wireless communication, comprising: at least one controller coupled with at least one memory and configured to cause the processor to: determine a first set of information based on input samples and a first index associated with at least one of the input samples or the first set of information, wherein the input samples are determined by the processor or received at the processor, and wherein the first index is based on at least one of a first set of one or more parameters for the processor and a second set of one or more parameters for a second apparatus; generate one or more datasets, wherein each dataset of the one or more datasets is a subset of the first set of information; and transmit at least one dataset of the one or more datasets.

19. A second apparatus, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the second apparatus to: receive one or more datasets from at least one of a first apparatus or another apparatus, wherein each dataset of the one or more datasets or first samples of each dataset of the one or more datasets are associated with a first index, and wherein the first index is associated with at least one of a first set of one or more parameters for the first apparatus and a second set of one or more parameters for the second apparatus; develop one or more decoder models, wherein each decoder model of the one or more decoder models is based on the one or more datasets or one or more subsets of the one or more datasets; assign a decoder metadata to each decoder model of the one or more decoder models, wherein the decoder metadata is based on at least one of the first index, a second index, and one or more model parameters, and wherein thesecond index represents the first set of one or more parameters for the second apparatus, and is associated with second samples of the one or more datasets; and transmit a set of model information associated with a model, wherein the model and associated model metadata are associated with the one or more decoder models and the decoder metadata, another model developed to behave similar to the one or more of the decoder models, and wherein another metadata of the another model is determined based on the decoder metadata, or a second model and its associated metadata.

20. A third apparatus, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the third apparatus to: receive one or more sets of model information; develop one or more encoder models, wherein each encoder model of the one or more encoder models is based on the one or more sets of model information; assign an encoder metadata to each encoder model of the one or more encoder models, wherein the encoder metadata is based on at least one of the one or more sets of model information, model metadata of the one or more sets of model information, and one or more encoder model parameters; and store the one or more encoder models and the metadata of each encoder model of the one or more encoder models.

Images