Codebook-based training dataset reporting for channel state information

Abstract

Aspects of the present disclosure relate to codebook-based training dataset reporting for channel state information (CSI). A training data set report corresponding to the CSI based on a precoding matrix indicator (PMI) codebook is generated or acquired. The training dataset report includes a plurality of parameters corresponding to the PMI codebook and weight values associated with the parameters. These parameters are an aggregation of similar training dataset points corresponding to the CSI, and the weight value is an indication of the rate of occurrence of the similar training dataset points. The training dataset report is then sent to another device (e.g., a network entity or UE).

Description

[0001] Related Applications

[0002] This application claims priority to U.S. Patent Application Serial No. 63 / 387,653, entitled "CODEBOOK-BASED TRAINING DATASET REPORTS FOR CHANNEL STATE INFORMATION," filed on December 15, 2022, the disclosure of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] This disclosure relates to wireless communications and, more particularly, to training dataset reports for channel state information (CSI). BACKGROUND ART

[0004] A wireless communication system can include one or more network communication devices (such as base stations), which may also be referred to as eNodeBs (eNBs), next-generation NodeBs (gNBs), or other suitable terms. Each network communication device (such as a base station) can support wireless communication for one or more user communication devices, which may also be referred to as user equipment (UEs) or other suitable terms. A wireless communication system can support wireless communication with one or more user communication devices by utilizing the resources of the wireless communication system (e.g., time resources (e.g., symbols, time slots, subframes, frames, etc.) or frequency resources (e.g., subcarriers, carriers)). Additionally, a wireless communication system can support wireless communication across various radio access technologies, including third-generation (3G) radio access technology, fourth-generation (4G) radio access technology, fifth-generation (5G) radio access technology, and other suitable radio access technologies beyond 5G (e.g., sixth-generation (6G)).

[0005] In a wireless communication system, CSI feedback can be sent from a UE to a base station (e.g., a gNB). The CSI feedback provides an indication of the channel quality at a particular time to the base station. SUMMARY OF THE INVENTION

[0006] The present disclosure relates to a method, apparatus, and system for supporting codebook-based training dataset reporting for CSI. A training dataset report corresponding to CSI based on a precoding matrix indicator (PMI) codebook is generated or obtained. The training dataset report includes a plurality of parameters corresponding to the PMI codebook and weight values associated with these parameters. These parameters are an aggregation of similar training dataset points corresponding to CSI, and the weight values are an indication of the occurrence rate of the similar training dataset points. The training dataset report is then sent to another device (e.g., a network entity or a UE). By using these plurality of parameters and the associated weight values, the size of the training dataset report can be reduced because not all training dataset points need to be individually included in the training dataset.

[0007] Some implementations of the methods and apparatuses described herein may further include: obtaining a training dataset report corresponding to CSI based on a PMI codebook, wherein the training dataset report includes a plurality of parameters corresponding to the PMI codebook, the plurality of parameters being associated with a plurality of weight values; and sending a first signaling indicating the training dataset report to a device.

[0008] In some implementations of the methods and apparatuses described herein, the apparatus includes a user equipment, and the method and apparatus further include transmitting first signaling over a physical uplink channel. Additionally or alternatively, the apparatus includes a UE, and the method and apparatus further include: transmitting first signaling over a physical downlink channel, transmitting the first signaling as part of high layer configuration information, or a combination thereof. Additionally or alternatively, the plurality of parameters includes a first set of code points, and each code point in the first set of code points corresponds to a selected subset of the spatial domain basis index, the frequency domain basis index, the time domain basis index, or a combination thereof. Additionally or alternatively, the first set of code points is a subset of a second set of code points, and each code point in the second set of code points corresponds to a subset of the spatial domain basis index, the frequency domain basis index, the time domain basis index, or a combination thereof. Additionally or alternatively, the plurality of parameters includes a set of entries corresponding to a bitmap that identifies the reported coefficients having non-zero magnitude values. Additionally or alternatively, each entry in the set of entries corresponds to the likelihood that the coefficient has a non-zero magnitude value. Additionally or alternatively, the plurality of parameters includes a set of code points, and each code point in the set of code points corresponds to at least one of the following: a set of coefficient magnitude values and a set of coefficient phase values associated with a plurality of consecutive spatial domain basis indices, a plurality of consecutive frequency domain basis indices, a plurality of consecutive time domain basis indices, or a combination thereof. Additionally or alternatively, each code point in the set of code points is associated with one of two coefficient types, where the first of the two coefficient types is associated with a first set of the spatial domain basis index, the frequency domain basis index, the time domain basis index, or a combination thereof, and where the second of the two coefficient types is associated with a second set of the spatial domain basis index, the frequency domain basis index, the time domain basis index, or a combination thereof. Additionally or alternatively, the first set of the spatial domain basis index, the frequency domain basis index, the time domain basis index is associated with the strongest coefficients having the maximum magnitude values. Additionally or alternatively, the plurality of parameters includes a set of rank indicator values, and each rank indicator value in the set of rank indicator values is associated with a different weight. Additionally or alternatively, the plurality of parameters includes a set of channel quality indicator values, and each channel quality indicator value in the set of channel quality indicator values is associated with a different weight. Additionally or alternatively, the method and apparatus further include: obtaining a CSI report reported based on a training data set, where the CSI report includes parameters corresponding to the following: the spatial domain basis index, the frequency domain basis index, the time domain basis index, a bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, a rank indicator (RI) value, a channel quality indicator (CQI) value, or a combination thereof, and each parameter in the parameters of the CSI report is mapped to a set of values that are encoded via an encoding scheme based on a plurality of weight values included in the training data set report; and transmitting second signaling indicating the CSI report to the device.

[0009] Some implementations of the methods and apparatuses described herein may also include: receiving, from a device, a first signaling indicating a training data set report; and wherein the training data set report corresponds to CSI based on a PMI codebook, and wherein the training data set report includes a plurality of parameters corresponding to the PMI codebook, the plurality of parameters being associated with a plurality of weight values.

[0010] In some implementations of the methods and apparatus described herein, the apparatus includes a user equipment, and the method and apparatus further include receiving a first signaling via a physical uplink channel. Additionally or alternatively, the apparatus includes a user equipment, and the method and apparatus further include causing the apparatus to: receive the first signaling via a physical downlink channel, receive the first signaling as part of high-level configuration information, or a combination thereof. Additionally or alternatively, the plurality of parameters include a first set of code points, and each code point in the first set of code points corresponds to a selected subset of a spatial base index, a frequency base index, a time base index, or a combination thereof. Additionally or alternatively, the first set of code points is a subset of a second set of code points, and each code point in the second set of code points corresponds to a subset of a spatial base index, a frequency base index, a time base index, or a combination thereof. Additionally or alternatively, the plurality of parameters include a set of entries corresponding to a bitmap, the bitmap identifying reported coefficients having non-zero amplitude values. Additionally or alternatively, each entry in the set of entries corresponds to a probability that a coefficient has a non-zero amplitude value. Additionally or alternatively, the plurality of parameters comprises a set of code points, and each code point in the set of code points corresponds to at least one of the following items: a set of coefficient amplitude values and a set of coefficient phase values associated with a plurality of consecutive spatial base indices, a plurality of consecutive frequency base indices, a plurality of consecutive time base indices, or a combination thereof. Additionally or alternatively, each code point in the set of code points is associated with one of two coefficient types, wherein a first coefficient type of the two coefficient types is associated with a first set of spatial base indices, frequency base indices, time base indices, or a combination thereof, and wherein a second coefficient type of the two coefficient types is associated with a second set of spatial base indices, frequency base indices, time base indices, or a combination thereof. Additionally or alternatively, the first set of spatial base indices, frequency base indices, time base indices is associated with the strongest coefficient with the largest amplitude value. Additionally or alternatively, the plurality of parameters comprises a set of rank indicator values, and each rank indicator value in the set of rank indicator values is associated with a different weight. Additionally or alternatively, the plurality of parameters include a set of channel quality indicator values, and each channel quality indicator value in the set of channel quality indicator values is associated with a different weight. Additionally or alternatively, the method and apparatus further include: receiving a second signaling indicating a CSI report from the device; and wherein the CSI report is based on a training data set report, wherein the CSI report includes parameters corresponding to: a spatial domain base index, a frequency domain base index, a time domain base index, a bitmap indicator, a set of indicators corresponding to amplitude values of non-zero coefficients, a set of indicators corresponding to phase values of non-zero coefficients, an RI value, a CQI value, or a combination thereof, and each of the parameters of the CSI report is mapped to a set of values, the set of values being encoded via a coding scheme based on a plurality of weight values included in the training data set report. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 Illustrates an example of a wireless communication system that supports codebook-based training data set reporting for channel state information, according to aspects of the present disclosure.

[0012] Figure 2 Illustrates an aperiodic trigger state that defines a list of CSI report settings.

[0013] Figure 3 Illustrates information elements related to CSI reporting.

[0014] Figure 4 Illustrates information elements for radio resource control (RRC) configuration for radio resources.

[0015] Figure 5 Illustrates a scenario where partial CSI omission for CSI based on physical uplink shared channel (PUSCH) occurs.

[0016] Figure 6 and Figure 7 Illustrates an example of a block diagram of a device that supports codebook-based training data set reporting for channel state information, according to aspects of the present disclosure.

[0017] Figures 8 to 15 Illustrates a flowchart of a method that supports codebook-based training data set reporting for channel state information, according to aspects of the present disclosure. Detailed Description

[0018] CSI feedback in a frequency division duplex (FDD) network is reported by a UE to the network, where the CSI feedback is compressed via a transformation in the spatial domain, frequency domain, or both over a channel using a set of predefined spatial and frequency basis vectors. In addition to the conventional CSI feedback mechanism, CSI acquisition schemes enabled by artificial intelligence / machine learning (AI / ML) can also be used. These AI / ML-enabled schemes will provide a certain feedback from the UE to the network, which corresponds to CSI components that cannot be inferred from the AI / ML model, e.g., CSI components that are statistically independent over time and thus cannot be inferred from training data. Additionally, obtaining ubiquitous training data for AI / ML-enabled schemes allows the robustness of the AI / ML-enabled CSI acquisition scheme to be maintained in the face of changes in the environment that would cause the channel distribution to drift and thus require updating of the AI / ML model.

[0019] Accordingly, CSI feedback techniques including training data are discussed herein, where the training data is aggregated such that similar training data set points are fed back once, associated with a weight coefficient corresponding to the probability (e.g., occurrence rate) of that data set point. The training data set report generation system feeds back parameters identifying these similar training data set points and their weight values in the training data set report. The training data set report generation system may also include a likelihood ratio as to whether a given coefficient corresponding to a channel or a precoding matrix is associated with a non-zero magnitude value, where the likelihood ratio is based on the weight or occurrence rate of a given CSI data point that is part of the training data set point.

[0020] The training data set report generation system may also infer characteristics of the channel distribution based on the training data set such that CSI feedback can utilize a distribution-aware data compression scheme (e.g., Huffman coding). For example, CSI parameters may be encoded such that values with a higher occurrence likelihood are mapped to shorter bit sequences, and CSI parameters are encoded such that values with a lower occurrence likelihood are mapped to longer bit sequences.

[0021] Other solutions for providing CSI feedback for training AI / ML models include CSI reports based on Type-I and Type-II codebooks, and generating CSI reports including all training data set points. The techniques discussed herein reduce the amount of data that needs to be included in the training data set report because all training data set points do not need to be included individually in the training data set report. This reduces the size of the training data set report as well as the amount of time and bandwidth consumed in sending the training data set report. Additionally, the total number of data points collected for CSI is large, but the techniques discussed herein process these data points to generate a smaller number of parameters (and associated weights), thereby reducing the complexity of devices that need to consider a large number of data points when training AI / ML models.

[0022] Aspects of the present disclosure are described in the context of a wireless communication system. Aspects of the present disclosure are further illustrated and described with reference to device diagrams and flowcharts.

[0023] Figure 1FIG. illustrates an example of a wireless communication system 100 in accordance with aspects of the present disclosure that supports codebook-based training data set reporting for channel state information. The wireless communication system 100 may include one or more network entities 102, one or more UEs 104, a core network 106, and a packet data network 108. The wireless communication system 100 may support various radio access technologies. In some implementations, the wireless communication system 100 may be a 4G network, such as an LTE network or an advanced LTE (LTE-A) network. In some other implementations, the wireless communication system 100 may be a 5G network, such as an NR network. In other implementations, the wireless communication system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technologies, including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communication system 100 may support radio access technologies other than 5G. Additionally, the wireless communication system 100 may support technologies such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA).

[0024] One or more network entities 102 may be dispersed throughout a geographic area to form the wireless communication system 100. One or more of the network entities 102 described herein may be or include or may be referred to as network nodes, base stations, network elements, radio access networks (RANs), base transceiver stations, access points, NodeBs, eNodeBs (eNBs), next-generation NodeBs (gNBs), or other suitable terms. The network entity 102 and the UE 104 may communicate via a communication link 110, which may be a wireless or wired connection. For example, the network entity 102 and the UE 104 may perform wireless communication (e.g., receive signaling, send signaling) via the Uu interface.

[0025] The network entity 102 can provide a geographical coverage area 112 for which the network entity 102 can support services (e.g., voice, video, packet data, messaging, broadcasting, etc.) for one or more UEs 104 within the geographical coverage area 112. For example, the network entity 102 and the UE 104 can support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcasting, etc.) according to one or more radio access technologies. In some implementations, the network entity 102 can be mobile, e.g., a satellite associated with a non-terrestrial network. In some implementations, different geographical coverage areas 112 associated with the same or different radio access technologies can overlap, but different geographical coverage areas 112 can be associated with different network entities 102. The information and signals described herein can 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 referred to throughout the description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0026] One or more UEs 104 can be dispersed throughout the geographical area of the wireless communication system 100. The UE 104 can include or can be referred to as a mobile device, wireless device, remote device, remote unit, handheld device, subscriber device, or some other suitable term. In some implementations, the UE 104 can be referred to as a unit, station, terminal, or client, etc. Additionally or alternatively, the UE 104 can be referred to as an Internet of Things (IoT) device, Internet of Everything (IoE) device, or machine type communication (MTC) device, etc. In some implementations, the UE 104 can be stationary in the wireless communication system 100. In some other implementations, the UE 104 can be mobile in the wireless communication system 100.

[0027] One or more UEs 104 can be devices of different forms or with different capabilities. In Figure 1 some examples of the UE 104 are illustrated. As Figure 1 shown, the UE 104 is capable of communicating with various types of devices, such as the network entity 102, other UEs 104, or network devices (e.g., the core network 106, the packet data network 108, a relay device, an integrated access and backhaul (IAB) node, or another network device), as Figure 1 shown. Additionally or alternatively, the UE 104 can support communication with other network entities 102 or UEs 104 that can act as relays in the wireless communication system 100.

[0028] UE 104 may also be able to support wireless communication directly with other UEs 104 via communication link 114. For example, UE 104 may support wireless communication directly with another UE 104 via 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, communication link 114 may be referred to as a sidelink. For example, UE 104 may support wireless communication directly with another UE 104 via the PC5 interface.

[0029] Network entity 102 may support communication with core network 106 or with another network entity 102 or both. For example, network entity 102 may interface with core network 106 via one or more backhaul links 116 (e.g., via S1, N2, N6, or another network interface). Network entities 102 may communicate with each other via backhaul link 116 (e.g., via X2, Xn, or another network interface). In some implementations, network entities 102 may communicate directly with each other (e.g., between network entities 102). In some other implementations, network entities 102 may communicate with each other either directly or indirectly (e.g., via core network 106). In some implementations, one or more network entities 102 may include subcomponents, such as access network entities, which may be examples of access node controllers (ANCs). An ANC may communicate with one or more UEs 104 via one or more other access network transmission entities, which may be referred to as radio heads, intelligent radio heads, or transmission and reception points (TRPs).

[0030] In some implementations, network entity 102 may be configured in a split architecture that may be configured to utilize a protocol stack physically or logically distributed across two or more network entities 102, such as an integrated access 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, network entity 102 may include one or more of the following: a central unit (CU), a distributed unit (DU), a radio unit (RU), a RAN intelligent controller (RIC) (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, or any combination thereof.

[0031] RU can also be referred to as a radio head, intelligent radio head, remote radio head (RRH), remote radio unit (RRU), or transmission and reception point (TRP). One or more components of network entity 102 in a split RAN architecture can be co-located, or one or more components of network entity 102 can be located in distributed locations (e.g., separate physical locations). In some implementations, one or more network entities 102 of the split RAN architecture can be implemented as virtual units (e.g., virtual CU (VCU), virtual DU (VDU), virtual RU (VRU)).

[0032] The functional split between the CU, DU, and RU can be flexible and can support different functions based on the functions performed at the CU, DU, or RU (e.g., network layer functions, protocol layer functions, baseband functions, radio frequency functions, and any combination thereof). For example, a functional split of the protocol stack can be adopted between the CU and the DU such that the CU can support one or more layers of the protocol stack and the DU can support one or more different layers of the protocol stack. In some implementations, the CU can host higher protocol layer (e.g., layer 3 (L3), layer 2 (L2)) functions and signaling (e.g., radio resource control (RRC), service data adaptation protocol (SDAP), packet data convergence protocol (PDCP)). The CU can be connected to one or more DUs or RUs, and one or more DUs or RUs can host lower protocol layers, such as layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, media access control (MAC) layer) functions and signaling, and each layer can be at least partially controlled by the CU.

[0033] Additionally or alternatively, a functional split of the protocol stack can be adopted between the DU and the RU such that the DU can support one or more layers of the protocol stack and the RU can support one or more different layers of the protocol stack. The DU can support one or more different cells (e.g., via one or more RUs). In some implementations, the functional split between the CU and the DU or between the DU and the RU can be within a protocol layer (e.g., for some functions of a protocol layer can be performed by one of the CU, DU, or RU, while other functions of the protocol layer are performed by a different one of the CU, DU, or RU).

[0034] The CU can be further functionally split into a CU control plane (CU-CP) and a CU user plane (CU-UP) function. The CU can be connected to one or more DUs via a midhaul communication link (e.g., F1, F1-c, F1-u), and the DU can be connected to one or more RUs via a fronthaul communication link (e.g., Open fronthaul (FH) interface). In some implementations, the midhaul communication link or the fronthaul communication link can be implemented according to the interface (e.g., channel) between the layers of the protocol stack supported by the corresponding network entities 102 communicating via such a communication link.

[0035] The core network 106 can support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The core network 106 can be an evolved packet core (EPC) or a 5G core (5GC), which can include a control plane entity (e.g., a mobility management entity (MME), an access and mobility management function (AMF)) that manages access and mobility, and a user plane entity (e.g., a serving gateway (S-GW), a packet data network (PDN) gateway (P-GW), or a user plane function (UPF)) that routes packets or interconnects to an external network. In some implementations, the control plane entity can manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearer, signaling bearer, etc.) for one or more UEs 104 served by one or more network entities 102 associated with the core network 106.

[0036] The core network 106 can communicate with the packet data network 108 via one or more backhaul links 116 (e.g., via S1, N2, N6, or another network interface). The packet data network 108 can include an application server 118. In some implementations, one or more UEs 104 can communicate with the application server 118. The UE 104 can establish a session (e.g., a protocol data unit (PDU) session, etc.) with the core network 106 via the network entity 102. The core network 106 can use the established session (e.g., the established PDU session) to route traffic (e.g., control information, data, etc.) between the UE 104 and the application server 118. The PDU session can be an example of a logical connection between the UE 104 and the core network 106 (e.g., one or more network functions of the core network 106).

[0037] In wireless communication system 100, network entity 102 and UE 104 may use the resources of wireless communication system 100 (e.g., time resources (e.g., symbols, time slots, sub - frames, frames, etc.) or frequency resources (e.g., sub - carriers, carriers)) to perform various operations (e.g., wireless communication). In some implementations, network entity 102 and UE 104 may support different resource structures. For example, network entity 102 and UE 104 may support different frame structures. In some implementations, such as in 4G, network entity 102 and UE 104 may support a single frame structure. In some other implementations, such as in 5G and other suitable radio access technologies, network entity 102 and UE 104 may support various frame structures (i.e., multiple frame structures). Network entity 102 and UE 104 may support various frame structures based on one or more digital technologies.

[0038] One or more digital technologies may be supported in wireless communication system 100, and the digital technologies may include sub - carrier spacing and cyclic prefix. The first digital technology (e.g., μ = 0) may be associated with a first sub - carrier spacing (e.g., 15 kHz) and a normal cyclic prefix. The first digital technology (e.g., μ = 0) associated with the first sub - carrier spacing (e.g., 15 kHz) may utilize one time slot per sub - frame. The second digital technology (e.g., μ = 1) may be associated with a second sub - carrier spacing (e.g., 30 kHz) and a normal cyclic prefix. The third digital technology (e.g., μ = 2) may be associated with a third sub - carrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. The fourth digital technology (e.g., μ = 3) may be associated with a fourth sub - carrier spacing (e.g., 120 kHz) and a normal cyclic prefix. The fifth digital technology (e.g., μ = 4) may be associated with a fifth sub - carrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0039] The time interval of resources (e.g., communication resources) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, e.g., a duration of 10 milliseconds (ms). In some implementations, each frame may include multiple sub - frames. For example, each frame may include 10 sub - frames, and each sub - frame may have a duration, e.g., a duration of 1 ms. In some implementations, each frame may have the same duration. In some implementations, each sub - frame of a frame may have the same duration.

[0040] Additionally or alternatively, the time intervals of resources (e.g., communication resources) can be organized according to time slots. For example, a subframe can include a certain number (e.g., quantity) of time slots. Each time slot can include a certain number (e.g., quantity) of symbols (e.g., Orthogonal Frequency Division Multiplexing (OFDM) symbols). In some implementations, the number (e.g., quantity) of time slots for a subframe can depend on the digital technology. For a normal cyclic prefix, a time slot can include 14 symbols. For an extended cyclic prefix (e.g., applicable to a 60 kHz subcarrier spacing), a time slot can include 12 symbols. For both the normal cyclic prefix and the extended cyclic prefix, the relationship between the number of symbols per time slot, the number of time slots per subframe, and the number of time slots per frame can depend on the digital technology. It should be understood that the reference to a first digital technology (e.g., μ = 0) associated with a first subcarrier spacing (e.g., 15 kHz) can be used interchangeably between subframes and time slots.

[0041] In wireless communication system 100, the electromagnetic (EM) spectrum can be split into various categories, frequency bands, frequency channels, etc. based on frequency or wavelength. For example, wireless communication system 100 can support one or more operating frequency bands, such as frequency range name 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, network entity 102 and UE 104 can perform wireless communication on one or more operating frequency bands. In some implementations, FR1 can be used by network entity 102 and UE 104 and other devices or apparatuses for cellular communication services (e.g., control information, data). In some implementations, FR2 can be used by network entity 102 and UE 104 and other devices or apparatuses for short-range, high data rate capabilities.

[0042] FR1 can be associated with one or more digital technologies (e.g., at least three digital technologies). For example, FR1 can be associated with the following: a first digital technology (e.g., μ = 0) that includes a 15 kHz subcarrier spacing; a second digital technology (e.g., μ = 1) that includes a 30 kHz subcarrier spacing; and a third digital technology (e.g., μ = 2) that includes a 60 kHz subcarrier spacing. FR2 can be associated with one or more digital technologies (e.g., at least 2 digital technologies). For example, FR2 can be associated with the following: a third digital technology (e.g., μ = 2) that includes a 60 kHz subcarrier spacing; and a fourth digital technology (e.g., μ = 3) that includes a 120 kHz subcarrier spacing.

[0043] UE 104 includes a training data set report generation system 122 that generates a training data set report 124 sent to network entity 102. Additionally or alternatively, network entity 102 includes a training data set report generation system 122 that generates a training data set report sent to UE 104. The training data set report generation system generates a training data set report that includes a plurality of parameters corresponding to a PMI codebook and weight values associated with these parameters. These parameters are an aggregation of similar training data set points corresponding to CSI, and the weight values are an indication of the occurrence rate of similar training data set points. The training data set report is then sent to another device (e.g., network entity 102). The device that receives the training data set report can then use the training data set report to train an AI / ML model for identifying subsequently received CSI feedback.

[0044] Communication between the devices discussed herein, such as between UE 104 and network entity 102, is performed using any one of a variety of different signaling. For example, such signaling can be any one of a variety of messages, requests, or responses, such as a trigger message, a configuration message, etc. As another example, such signaling can be any one of a variety of signaling media or protocols through which messages are transmitted, such as any combination of the following: Physical Downlink Shared Channel (PDSCH), Physical Downlink Control Channel (PDCCH), Physical Uplink Shared Channel (PUSCH), Physical Uplink Control Channel (PUCCH), Radio Resource Control (RRC), Downlink Control Information (DCI), Uplink Control Information (UCI), Sidelink Control Information (SCI), Medium Access Control Element (MAC-CE), Sidelink Positioning Protocol (SLPP), PC5 Radio Resource Control (PC5-RRC), etc.

[0045] In some wireless communication systems, details of the NR Type-II codebook are provided. For example, assume that the gNB is equipped with a two-dimensional (2D) antenna array, with N1 and N2 antenna ports placed horizontally and vertically for each polarization level, and communication occurs on N3 precoding matrix indicator (PMI) subbands. A PMI subband can include a set of resource blocks, and each resource block includes a set of subcarriers. In this case, 2N1N2 channel state information (CSI) reference signal (RS) ports can be utilized to enable high-resolution downlink (DL) channel estimation for the NR Rel.15 Type-II codebook. To reduce the uplink (UL) feedback overhead, DFT-based CSI compression in the spatial domain can be applied to L dimensions for each polarization, where L < N1N2. Subsequently, the indices of the 2L dimensions can be referred to as spatial domain (SD) basis indices. The magnitude values and phase values of the linear combination coefficients for each subband can be fed back to the gNB as part of the CSI report. The 2N1N2×N3 codebook for each layer l can take the following form

[0046] W l = W1W 2,l

[0047] where W1 is a 2N1N2×2L block diagonal matrix with two identical diagonal blocks (L < N1N2). For example,

[0048]

[0049] and B is an N1N2×L matrix with columns drawn from a 2D oversampled DFT matrix, as shown below.

[0050]

[0051]

[0052]

[0053]

[0054]

[0055] where the superscript T denotes the matrix transpose operation. Note that for the 2D DFT matrix from which matrix B is drawn, O1 and O2 can be assumed to be the oversampling factors. Note that W1 is common across all layers. W 2，l is a 2L×N3 matrix, where the i-th column corresponds to the linear combination coefficients of the 2L beams in the i-th subband. Only the indices of L selected columns of B, as well as the oversampling indices with the O1O2 values, can be reported. Note that W 2，lIt can be independent for different layers.

[0056] In some wireless communication systems, details of the NR Type-II port selection codebook are provided. For example, for the Type-II port selection codebook, K (where K ≤ 2N1N2) beamformed CSI-RS ports can be utilized in DL transmission to reduce complexity. The K×N3 codebook matrix for each layer has the following form

[0057]

[0058] Here, W2 can follow the same structure as the conventional NR Rel.15 Type-II codebook and is layer-specific. is a K×2L block diagonal matrix with two identical diagonal blocks. For example,

[0059]

[0060] And E is a matrix whose columns are standard unit vectors, as follows.

[0061]

[0062] where is the standard unit vector with 1 at the i-th position. Here, d PS is an RRC parameter that takes values from {1, 2, 3, 4} under the condition that d PS ≤ min(K / 2, L), while m PS takes values from and is reported as part of the UL CSI feedback overhead. W1 is common among all layers.

[0063] For K = 16, L = 4, and d PS = 1, the 8 possible realizations of E corresponding to m PS = {0, 1,..., 7} are as follows

[0064]

[0065]

[0066] When d PS = 2, the 4 possible realizations of E corresponding to m PS = {0, 1, 2, 3} are as follows

[0067]

[0068] When d PS = 3, corresponding to m PSThe three possible realizations of E corresponding to = {0, 1, 2} are as follows

[0069]

[0070] When d PS = 4, the two possible realizations of E corresponding to m PS = {0, 1} are as follows

[0071]

[0072] In summary, m PS parametrizes the position of the first 1 in the first column of E, while d PS represents the row offset corresponding to different values of m PS .

[0073] In some wireless communication systems, details of the NR Type-I codebook are provided. For example, the NR Rel.15 Type-I codebook is the baseline codebook for NR and has multiple configurations. The most common utility of the Rel.15 Type-I codebook is a special case of the NR Rel.15 Type-II codebook (with L = 1, RI = 1, 2), where the phase coupling values are reported for each subband, e.g., W 2，l is 2 × N3, with the first row equal to [1, 1,..., 1], and the second row equal to In a specific configuration, e.g., wideband reporting. For RI > 2, different beams are used for each pair of layers. The NR Rel.15 Type-I codebook can be depicted as a low-resolution version of the NR Rel.15 Type-II codebook, with only the spatial beam selection for each layer pair and phase combination.

[0074] In some wireless communication systems, details of the NR Rel.16 Type-I codebook are provided. For example, assume that the gNB is equipped with a two-dimensional (2D) antenna array, with N1 and N2 antenna ports placed for each polarization level in the horizontal and vertical directions, respectively, and communication occurs on N3 PMI subbands. A PMI subband includes a set of resource blocks, and each resource block includes a set of subcarriers. In this case, 2N1N2N3 CSI-RS ports can be utilized to enable high-resolution DL channel estimation for the NR Rel.16 Type-II codebook. To reduce the UL feedback overhead, DFT-based CSI compression in the spatial domain can be applied to L dimensions for each polarization, where L < N1N2. Similarly, additional compression in the frequency domain can be applied, where each beam of the frequency-domain precoding vector is transformed to the delay domain using the inverse DFT matrix, and a subset of the magnitude and phase values of the delay-domain coefficients can be selected and fed back to the gNB as part of the CSI report. The 2N1N2×N3 codebook for each layer takes the following form

[0075]

[0076] where W1 is a 2N1N2×2L block-diagonal matrix with two identical diagonal blocks (L < N1N2). For example,

[0077]

[0078] and B is an N1N2×L matrix with columns drawn from a 2D oversampled DFT matrix, as shown below.

[0079]

[0080]

[0081]

[0082]

[0083]

[0084] where the superscript T denotes the matrix transpose operation. Note that for the 2D DFT matrix from which matrix B is drawn, O1 and O2 are assumed to be the oversampling factors. Note that W1 is common across all layers. W f is an N3×M matrix (M < N3), whose columns are selected from a critically sampled size-N3 DFT matrix, as shown below

[0085]

[0086]

[0087] In some scenarios, the indices of the L selected columns of Report B and the oversampling indices with O1O2 values are reported. Similarly, for W f，l , the indices of the M selected columns in a predefined size-N3 DFT matrix are reported. In the following, the indices of the M dimensions can be referred to as the selected frequency-domain (FD) basis indices. Thus, L and M respectively represent the equivalent spatial and frequency dimensions after compression. In addition, the 2L×M matrix represents the linear combination coefficients (LCC) of the spatial and frequency DFT basis vectors. W f Both can be independently selected for different layers. The magnitude and phase values of approximately β fraction of the 2LM available coefficients are reported to the gNB as part of the CSI report (β < 1). Note that the coefficients with zero magnitude values are indicated via a layer-specific bitmap matrix S of size 2L×M l , where each bit of the bitmap matrix S l indicates whether the coefficient has a zero magnitude value, for which the quantized magnitude and phase values do not need to be reported. Since all non-zero coefficients reported within a layer are normalized with respect to the coefficient with the maximum magnitude value (the strongest coefficient), where the magnitude value and phase value corresponding to the strongest coefficient are set to 1 and 0 respectively, and thus the additional magnitude and phase information for this coefficient is not explicitly reported, and the index indication of the strongest coefficient for each layer can be reported.

[0088] Therefore, for single-layer transmission, compared with reporting the information of 2N1N2×N3 - 1 coefficients, each layer can report at most magnitude and phase values of the coefficients (as well as the indices of the selected L and M DFT vectors), resulting in a significant reduction in the CSI report size.

[0089] For the NR Rel.16 Type-II port selection codebook, K (where K ≤ 2N1N2) beamformed CSI-RS ports can be utilized in DL transmission to reduce complexity. The K×N3 codebook matrix for each layer has the following form

[0090]

[0091] Here, and W 3，l follow the same structure as the conventional NR Rel.16 Type-II codebook, where both are layer-specific. The matrix can be a K×2L block diagonal matrix with the same structure as in the NR Rel.15 Type-II port selection codebook.

[0092] The NR Rel.17 Type-II port selection codebook can follow a structure similar to that of the Rel.15 and Rel.16 port selection codebooks, as follows

[0093]

[0094] However, different from the Rel.15 and Rel.16 Type-II port selection codebooks, the port selection matrix supports freely selecting K ports, or rather, supports selecting K / 2 ports per polarization from N1N2 CSI-RS ports for each polarization, for example bits are used to identify K / 2 selected ports per polarization, where this selection is common across all layers. Here, and W f，l follow the same structure as the regular NR Rel.16 Type-II codebook. However, M can be limited to 1, 2, where the network configures a window of size N = {2, 4} for M = 2. Additionally, unless β = 1, the reporting bitmap is reported, and the UE reports all coefficients for ranks up to a value of 2.

[0095] For the Rel-18 potential Type-II codebook, the time domain corresponding to the time slot is further compressed via a DFT-based transform, where the codebook takes the following form

[0096]

[0097] where W1, W f，l follows the same structure as the Rel-16 Type-II codebook, and W d，l is an N4×Q matrix (Q ≤ N4), with columns selected from a critically sampled size-N4 DFT matrix, as follows

[0098]

[0099]

[0100] Only the indices of Q selected columns of W d，l can be reported. Note that W d，l can be layer-specific. For example, W d，1 ≠W d，2 , or layer-common, i.e., W d，1 =…=W d，RI , where RI corresponds to the total number of layers, and the operator corresponds to the Kronecker matrix product. Here, is a matrix of size 2L×MQ with layer-specific entries that represent the LCC corresponding to the spatial, frequency, and time-domain DFT basis vectors. Therefore, it may be necessary to report a bitmap of size 2L×MQ associated with the Rel-18 Type-II codebook.

[0101] In some scenarios, the codebook reporting is split into two parts based on the priority of the reported information. Each part is encoded separately (Part 1 may have a higher code rate). The list of parameters for the NR Rel.16 Type-II codebook is as follows.

[0102] For the content of CSI reporting:

[0103] Part 1: RI + Channel Quality Indicator (CQI) + Total number of coefficients

[0104] Part 2: SD basis indicator + FD basis indicator / layer + Bitmap / layer + Coefficient magnitude information / layer + Coefficient phase information / layer + Strongest coefficient indicator / layer

[0105] In addition, Part 2 CSI can be decomposed into sub-parts each with different priorities (higher priority information comes first). This division can be implemented to allow for dynamic reporting sizes of the codebook based on the available resources in the uplink phase. In addition, the Type-II codebook can be based on aperiodic CSI reporting and triggered to be reported in the PUSCH via Downlink Control Information (DCI) (with at least one exception). The Type-I codebook can be based on periodic CSI reporting (PUCCH) or semi-persistent CSI reporting (PUSCH or PUCCH) or aperiodic reporting (PUSCH).

[0106] For the priority reporting of Part 2 CSI, multiple CSI reports can be sent using different priorities as shown in Table 1 below. Note that the Rep priority of N CSI reports can be based on the following items:

[0107] 1. A CSI report corresponding to a CSI report configuration for a cell can have a higher priority compared to another CSI report corresponding to another CSI report configuration for the same cell;

[0108] 2. A CSI report intended for a cell can have a higher priority compared to other CSI reports intended for another cell;

[0109] 3. Based on the CSI report content, a CSI report can have a higher priority. For example, a CSI report carrying L1 Reference Signal Received Power (RSRP) information has a higher priority;

[0110] 4. The CSI report can have a high priority based on its type. For example, whether the CSI report is aperiodic, semi-persistent, or periodic, and whether the report is sent via PUSCH or PUCCH can all affect the priority of the CSI report.

[0111] Table 1: Priority Report Levels for Partial 2CSI

[0112]

[0113]

[0114] Therefore, the CSI reports can be prioritized as follows, where the CSI report with a lower identifier (ID) has a higher priority.

[0115] Pri iCSI (y, k, c, s) = 2·N cells ·M s ·y + N cetls ·M s ·k + M s ·c + s

[0116] s: CSI report configuration index, and M s : The maximum number of CSI report configurations

[0117] c: Cell index, and N cells : The number of serving cells

[0118] k: 0 for CSI reports carrying L1-RSRP or L1 signal-to-interference-plus-noise ratio (SINR), otherwise 1

[0119] y: 0 for aperiodic reports, 1 for semi-persistent reports on PUSCH, 2 for semi-persistent reports on PUCCH, and 3 for periodic reports.

[0120] In some scenarios, to trigger an aperiodic CSI report on PUSCH, the UE can use the CSI framework in NR Release 15 to report CSI information to the network. The triggering mechanism between the report settings and the resource settings can be summarized in Table 2 below.

[0121] Table 2: Triggering mechanism between report settings and resource settings

[0122]

[0123] In addition, in some scenarios:

[0124] · The associated resource settings for the CSI report settings have the same time-domain behavior.

[0125] · After being configured by RRC, it can be assumed that periodic CSI-RS / interference management (IM) resources and CSI reports exist and are active.

[0126] · Aperiodic and semi-persistent CSI-RS / IM resources and CSI reports can be explicitly triggered or activated.

[0127] · For aperiodic CSI-RS / IM resources and aperiodic CSI reports, the triggering can be jointly performed by sending DCI format 0-1.

[0128] · Semi-persistent CSI-RS / IM resources and semi-persistent CSI reports can be activated independently.

[0129] Figure 2 The aperiodic trigger state 200 that defines a list of CSI report settings is illustrated. For example, for aperiodic CSI-RS / IM resources and aperiodic CSI reports, the triggering is jointly performed by sending DCI format 0-1. DCI format 0_1 contains a CSI request field (0 to 6 bits). A non-zero request field points to a so-called aperiodic trigger state configured by RRC, as Figure 2 shown. The aperiodic trigger state is in turn defined as a list of up to 16 aperiodic CSI report settings, identified by a CSI report setting identifier (ID), for which the UE calculates CSI simultaneously and sends its CSI on the scheduled PUSCH transmission.

[0130] Figure 3 The information element 300 related to CSI reports is illustrated. The aperiodic trigger state indicates resource set and QCL information. For example, when a CSI report setting is linked to an aperiodic resource setting (e.g., including multiple resource sets), the aperiodic non-zero power (NZP) CSI-RS resource set for channel measurement, the aperiodic CSI-IM resource set (if used), and the aperiodic NZP CSI-RS resource set for IM (if used) to be used for a given CSI report setting are also included in the aperiodic trigger state definition. For aperiodic NZP CSI-RS, the quasi-co-location (QCL) source to be used is also configured in the aperiodic trigger state. The UE believes that the resources for calculating channels and interference can be processed using the same spatial filter, e.g., a filter relative to "QCL-TypeD" quasi-co-location.

[0131] Figure 4The information element 400 for RRC configuration of radio resources is illustrated. For example, the information element 400 may configure NZP-CSI-RS / CSI-IM resources. For example, the information element 400 illustrates (a) the RRC configuration for NZP-CSI-RS resources and (b) the RRC configuration for CSI-IM resources.

[0132] Table 3 summarizes the types of uplink channels for CSI reporting as a function of CSI codebook type.

[0133] Table 3: Uplink Channels for CSI Reporting as a Function of CSI Codebook Type

[0134]

[0135] For aperiodic CSI reporting, PUSCH-based reporting is divided into two CSI parts: CSI part 1 and CSI part 2. The reason is that the size of the CSI payload varies greatly, and thus the worst-case UCI payload size design will result in a large overhead.

[0136] CSI part 1 has a fixed payload size (and can be decoded by the gNB without prior information) and contains the following items:

[0137] · RI for the first codeword (if reported), CSI-RS resource index (CRI) (if reported), and CQI,

[0138] · Multiple non-zero wideband amplitude coefficients for each layer for Type II CSI feedback on PUSCH.

[0139] Figure 5 Scenario 500 for partial CSI omission for PUSCH-based CSI is illustrated. For example, scenario 500 illustrates the reordering of CSI part 2 across CSI reports. CSI part 2 may have a variable payload size that can be derived from the CSI parameters in CSI part 1 and contains the PMI and CQI for the second codeword when RI > 4. For example, if the aperiodic trigger state indicated by DCI format 0_1 defines 3 reporting settings x, y, and z, the aperiodic CSI reporting for CSI part 2 may be ordered as shown in scenario 500.

[0140] As described above, CSI reports can be prioritized according to the following items:

[0141] 1. Time-domain behavior and physical channels, where more dynamic reports have higher priority than less dynamic reports, and PUSCH has higher priority than PUCCH.

[0142] 2. CSI content, where beam reports (e.g., L1-RSRP reports) have priority over regular CSI reports.

[0143] 3. The serving cell to which the CSI corresponds (in the case of carrier aggregation (CA) operation).

[0144] The CSI corresponding to the PCell has priority over the CSI corresponding to the Scell.

[0145] 4. reportConfigID.

[0146] The CSI report may include a CQI report quantity corresponding to the channel quality with a hypothesized maximum target transport block error rate, which indicates the modulation order, code rate, and the corresponding spectral efficiency associated with the modulation order and code rate pair. Examples of the maximum transport block error rate are 0.1 and 0.00001. The modulation order can vary from quadrature phase shift keying (QPSK) to 1024QAM, and the code rate can vary from 30 / 1024 to 948 / 1024. An example of a CQI table for a 4-bit CQI indicator, which identifies the possible CQI values with corresponding modulation order, code rate, and efficiency, is provided in Table 4 as follows Table 4: Example of a 4-bit CQI Table

[0147]

[0148] The CQI value can be reported in two formats: wideband format, where one CQI value corresponding to each PDSCH transport block is reported; and subband format, where in addition to the set of subband CQI values corresponding to the CQI subbands on which the transport block is transmitted, one wideband CQI value is reported for the entire transport block. The CQI subband size is configurable and depends on the number of PRBs in the bandwidth part, as shown in Table 5, as follows:

[0149] Table 5: Configurable Subband Sizes for a Given Bandwidth Part (BWP) Size

[0150] Bandwidth Part (number of PRBs) Subband Size (number of PRBs) 24-72 4、8 73-144 8、16 145-275 16、32

[0151] If the higher layer parameter cqi-BitsPerSubband in CSI-ReportConfig of the CSI report is configured, the subband CQI value is reported in full form, e.g., using 4 bits for each subband CQI based on the CQI table (e.g., Table 4). If the higher layer parameter cqi-BitsPerSubband in CSI-ReportConfig is not configured, for each subband s, a 2-bit subband differential CQI value is reported, defined as:

[0152] -(Multiple) sub - band offset levels = (multiple) sub - band CQI indices - wide - band CQI index.

[0153] The mapping from 2 - bit sub - band differential CQI values to offset levels is shown in Table 6, as follows:

[0154] Table 6: Mapping Subband Differential CQI Values to Offset Levels

[0155] Subband Differential CQI Value Offset Level 0 0 1 1 2 ≥2 3 ≤-1

[0156] For an AI / ML - based CSI framework, there are multiple alternatives for an overview of the AI / ML algorithm functionality, such as:

[0157] 1. The AI / ML model is trained at the UE node. This alternative may seem reasonable because the UE is the node that can use DL pilot signals to seamlessly collect training data for CSI acquisition (e.g., CSI - RS for channel measurement). However, as long as the environment changes, such as a change in the UE's location or orientation, the AI / ML model should be retrained, and each training instance requires a large amount of memory and computational complexity requirements.

[0158] 2. The AI / ML model is trained at the network node. One advantage of this method is that compared to the UE node, the network has greater power and computational capabilities and can thus manage the training of moderately complex AI / ML models and store a large amount of training data. In addition, since network nodes are mostly assumed to be fixed, their coverage areas are expected to be the same, and thus a single AI / ML model can be applicable to UEs within a specific area of the cell for a reasonable period of time. One challenge with this method is related to obtaining training data at the network node, especially for FDD systems where UL / DL channel reciprocity may not hold. Note that the overhead corresponding to the feedback of training data from the UE to the network should be considered as one of the metrics in the metrics for evaluating the efficiency of the AI / ML algorithm.

[0159] In the following, it can be assumed that the AI / ML model is trained at the network because of the advantages corresponding to memory, computation, and cell - centered characteristics calculated by the network - based AI / ML model. The challenges corresponding to obtaining training data corresponding to the DL channel at the network side will be discussed in the next section.

[0160] Assuming that the AI / ML model is trained at the network, several aspects of DL training data acquisition for the network side are discussed to achieve efficient AI / ML modeling.

[0161] 1. To maintain the robustness of the AI / ML model against channel variations, DL training data should be continuously fed back into the network to keep up with environmental changes such as traffic, weather, and mobile scatterers. Note that this may not necessarily correspond to online learning; even for offline learning algorithms, a framework for obtaining new training data corresponding to channel variations should be characterized.

[0162] 2. Based on the current codebook-based DL CSI feedback scheme in NR, CSI is compressed in at least one of the spatial domain or the frequency domain or both. An intuitive approach is to use codebook-based CSI feedback (e.g., Type-I and / or Type-II codebooks) for obtaining training data. One drawback of this method is that the training data will include CSI feedback that has already been compressed via conventional methods, which will have an adverse impact on the inference accuracy of the AI / ML model. For example, if the AI / ML model compares the output of the AI / ML model with the channel corresponding to the CSI feedback to evaluate its own inference accuracy, this evaluation will be inaccurate because it is based on H' (channel estimation based on predefined compression) rather than H (digitally quantized channel without further compression in the spatial or frequency domain). On the other hand, if the UE feeds back training data corresponding to DL CSI feedback without compression in the spatial and / or frequency dimensions, the feedback overhead of the training data will be large, which will defeat the purpose of using the AI / ML model, which is mainly to reduce the overall CSI feedback overhead. Numerically, AI / ML-based CSI feedback aims to minimize the following metric:

[0163]

[0164] where H represents the digital domain representation of the channel matrix. On the other hand, compressing the channel H' (which represents the recovered channel after codebook-based transformation) will result in the following optimized metric

[0165]

[0166] Since H ≠ H', the outputs of these two optimizations may yield different channel estimates.

[0167] For DL CSI acquisition in NR, whether the network operates in FDD mode or time-division duplex (TDD) mode, AI / ML is unlikely to completely replace RS-based CSI feedback for high-resolution precoding design because some channel parameters can vary from one moment to another with no strong correlation across two moments, such as the initial random phase of the channel. Given this, compared with conventional methods, the AI / ML-based CSI framework can be conceived as a means to further reduce CSI feedback overhead, for example, after performing spatial domain transformation, frequency domain transformation, and time domain transformation respectively, reducing the number of main spatial domain basis indices, frequency domain / delay domain basis indices, and time domain / Doppler domain basis indices. Although the current CSI feedback framework has provided a reduction in CSI feedback overhead by leveraging such transformations, if a wider range of transformation techniques are preconfigured, the CSI dimension can be further reduced, where different transformations can be selected for a given UE based on the variation of the channel.

[0168] In some wireless communication systems, the terms antenna, panel, and antenna panel can be used interchangeably. An antenna panel can be hardware for transmitting and / or receiving radio signals at frequencies below 6 GHz (e.g., frequency range 1 (FR1)) or above 6 GHz (e.g., frequency range 2 (FR2) or millimeter wave (mmWave)). In some implementations, the antenna panel can include an array of antenna elements, where each antenna element is connected to hardware such as a phase shifter that allows a control module to apply spatial parameters to the transmission and / or reception of signals. The resulting radiation pattern can be referred to as a beam, which can be either unimodal or not, and can allow the device to amplify signals transmitted or received from a spatial direction.

[0169] In some scenarios, the antenna panel can or cannot be virtualized as an antenna port in the specification. The antenna panel can be connected to the baseband processing module via a radio frequency (RF) chain for each transmission (exit) and reception (entry) direction. The capabilities of the device in terms of the number of antenna panels, its duplexing capabilities, its beamforming capabilities, etc. can be transparent or not transparent to other devices. In some implementations, the capability information can be conveyed via signaling, or in some implementations, the capability information can be provided to the device without the need for signaling. If such information is available to other devices, it can be used for signaling or local decision-making.

[0170] In some scenarios, a device (e.g., UE, node) antenna panel can be a physical or logical antenna array that includes a set of antenna elements or antenna ports (e.g., in-phase / quadrature (I / Q) modulators, analog-to-digital (A / D) converters, local oscillators, phase-shift networks) sharing a common or significant portion of an RF chain. A device antenna panel or “device panel” can be a logical entity that has physical device antennas mapped to the logical entity. The mapping of physical device antennas to the logical entity can depend on the device implementation. Transmitting (receiving or sending) on at least a subset of the antenna elements or antenna ports of the antenna panel that are used for radiating energy (also referred to herein as active elements) requires biasing or powering on the RF chain, which results in current consumption or power consumption in the device associated with the antenna panel (including power amplifier / low-noise amplifier (LNA) power consumption associated with the antenna elements or antenna ports). The phrase “active for radiating energy” used herein does not denote a limitation to the transmit function and also includes the receive function. Thus, an active antenna element for radiating energy can be coupled to a transmitter to transmit radio frequency energy, or to a receiver to receive radio frequency energy, or can generally be coupled to a transceiver to perform its intended function. Transmitting on the active elements of the antenna panel can generate a radiation pattern or beam.

[0171] In some scenarios, depending on the device's own implementation, the “device panel” can have at least one of the following functions as an operational role: an antenna group unit that independently controls its Tx beam, an antenna group unit that independently controls its transmission power, an antenna group unit that independently controls its transmission timing. The “device panel” can be transparent to the gNB. For a certain (certain) situation, the gNB or the network can assume that the mapping between the physical antennas of the device and the logical entity “device panel” will not change. For example, this situation can include until the next update or report from the device, or include a duration during which the gNB assumes the mapping will not change between them. The device can report its capabilities related to the “device panel” to the gNB or the network. The device capabilities can at least include the number of “device panels”. In one implementation, the device can support UL transmission from one beam within the panel; for multiple panels, more than one beam (one beam per panel) can be used for UL transmission. In another implementation, more than one beam per panel can be supported / used for UL transmission.

[0172] In some scenarios, antenna ports are defined such that the channel through which symbols are transmitted on an antenna port can be inferred from the channel through which another symbol is transmitted on the same antenna port.

[0173] Two antenna ports are said to be QCL if the large-scale properties of the channel through which symbols on one antenna port are transmitted can be inferred from the channel through which symbols on the other antenna port are transmitted. The large-scale properties include one or more of the following: delay spread, Doppler spread, Doppler shift, average gain, average delay, and spatial Rx parameters. The two antenna ports can be quasi-collocated with respect to a subset of the large-scale properties, and different subsets of the large-scale properties can be indicated by QCL types. The QCL type can indicate which channel properties are the same between two reference signals (e.g., on two antenna ports). Thus, the reference signals can be linked to each other based on the UE's assumptions about their channel statistics or QCL properties. For example, the qcl-Type can take one of the following values:

[0174] - "QCL-TypeA": {Doppler shift, Doppler spread, average delay, delay spread}

[0175] - "QCL-TypeB": {Doppler shift, Doppler spread}

[0176] - "QCL-TypeC": {Doppler shift, average delay}

[0177] - "QCL-TypeD": {spatial Rx parameters}.

[0178] The spatial Rx parameters can include one or more of the following: angle of arrival (AoA), dominant AoA, average AoA, angular spread, power angular spectrum (PAS) of AoA, average AoD (angle of departure), PAS of AoD, transmit / receive channel correlation, transmit / receive beamforming, spatial channel correlation, etc.

[0179] QCL-TypeA, QCL-TypeB, and QCL-TypeC can apply to all carrier frequencies, but QCL-TypeD can only apply to higher carrier frequencies (e.g., mmWave, FR2 and above), at which the UE may not be able to perform omnidirectional transmission substantially. For example, the UE needs to form a beam for directional transmission. For QCL-TypeD between two reference signals A and B, reference signal A is considered to be spatially collocated with reference signal B, and the UE can assume that reference signals A and B can be received using the same spatial filter (e.g., using the same receive beamforming weights).

[0180] The implemented "antenna port" can be a logical port, which can correspond to a beam (generated by beamforming), or can correspond to a physical antenna on the device. In some implementations, a physical antenna can be directly mapped to a single antenna port, where the antenna port corresponds to the actual physical antenna. Alternatively, after applying complex weights, cyclic delays, or both to the signals on each physical antenna, a set or subset of physical antennas, or an antenna set or antenna array or antenna subarray can be mapped to one or more antenna ports. The set of physical antennas can have antennas from a single module or panel or from multiple modules or panels. The weights can be fixed as in antenna virtualization schemes such as cyclic delay diversity (CDD). The process for deriving antenna ports from physical antennas can be specific to the device implementation and transparent to other devices.

[0181] In some scenarios, the TCI state (transmission configuration indication) associated with a target transmission can indicate parameters for configuring the quasi-collocation relationship between the target RS (e.g., the demodulation (DM) RS port of the target transmission during a transmission occasion) of the target transmission and the (multiple) source reference signals (e.g., synchronization signal block (SSB) / CRI-RS / sounding reference signal (SRS)) with respect to the (multiple) quasi-collocation type parameters indicated in the corresponding TCI state. TCI describes which reference signals are used as QCL sources and which QCL attributes can be derived from each reference signal. The device can receive configurations for multiple transmission configuration indicator states for the serving cell for transmissions on the serving cell. In some of the described implementations, the TCI state includes at least one source RS to provide a reference (assumed by the UE) for determining QCL and / or spatial filters.

[0182] In some scenarios, the spatial relationship information associated with a target transmission can indicate parameters for configuring the spatial settings between the target transmission and a reference RS (e.g., SSB / CSI-RS / SRS). For example, the device can use the same spatial domain filter for receiving the reference RS (e.g., DL RS such as SSB / CSI-RS) to transmit the target transmission. In another example, the device can use the same spatial domain transmission filter for transmitting the reference RS (e.g., UL RS such as SRS) to transmit the target transmission. The device can receive configurations for multiple spatial relationship information configurations for the serving cell for transmissions on the serving cell.

[0183] In some scenarios, if the device is configured with a separate DL / UL TCI via RRC signaling, the UL TCI state is provided. The UL TCI state may include a source reference signal that provides a reference for determining the UL spatial transmission filter for UL transmissions (e.g., dynamically authorized / configured-based authorized PUSCH, dedicated PUCCH resources) in a component carrier (CC) or across a set of configured CC / BWPs.

[0184] In some scenarios, if the device is configured with a joint DL / UL TCI via RRC signaling (e.g., the configuration of the joint TCI or separate DL / UL TC1 is based on RRC signaling), the joint DL / UL TCI state is provided. The joint DL / UL TCI state refers at least to a common source reference RS for determining DL QCL information and the UL spatial transmission filter. The source RS determined from the indicated joint (or common) TCI state provides a QCL Type-D indication (e.g., for the device-specific physical downlink control channel / physical downlink shared channel (PDCCH / PDSCH)), and is used to determine the UL spatial transmission filter for a CC or across a set of configured CC / BWPs (e.g., for UE-specific PUSCH / PUCCH). In one example, the UL spatial transmission filter is derived from the DL QCL Type D RS in the joint TCI state. The spatial setting of the UL transmission can be based on the spatial relationship with the reference of the source RS configured with qcl-Type set to "typeD" in the joint TCI state.

[0185] In an implementation, consider that the channel between the UE and the gNB occupies N SB frequency bands (index n = 0,..., N SB - 1) with P signal paths (index p = 0,..., P - 1), where the gNB is equipped with K antennas (index k = 0,..., K - 1). Then the channel at time index δ can be expressed as follows

[0186]

[0187] g k，p : The complex gain of path p at antenna k

[0188] Δf: The PMI subband spacing

[0189] τ p : The delay of path p

[0190] F c : The carrier frequency

[0191] c: The speed of light

[0192] d: Antenna spacing at the gNB

[0193] θ p : Angular spatial displacement at the gNB antenna array corresponding to path p

[0194] δ: Time index

[0195] v: Relative speed between the gNB and the UE

[0196] Φ p : Angle between the direction of movement and the signal incident direction of path p

[0197] In implementation, the above channel can be parameterized in three dimensions: frequency, space, and time dimensions. To construct a precoder codebook with reasonable CSI feedback overhead, the CSI corresponding to the three dimensions can be compressed. In the Rel.16 e Type-II codebook, both the spatial domain and the frequency domain can be compressed via DFT transforms of the spatial domain and the frequency domain having columns of two-dimensional and one-dimensional DFT matrices respectively, while in the potential Rel-18 e Type-II codebook for high speed, the time domain can be further compressed via a DFT transform in the form of columns of a one-dimensional DFT matrix. Additionally or alternatively, the CSI feedback can be sent in an explicit format (e.g., in the form of explicit channel coefficients) to enhance the CSI feedback resolution. However, the CSI feedback overhead will increase significantly, especially for scenario training dataset transmission, where the CSI feedback includes a large number of training dataset points corresponding to different realizations of the CSI. An AI-based CSI framework is discussed, where statistical CSI training data is reported by aggregating similar training dataset points corresponding to the CSI, and the corresponding weights or occurrence rates of the dataset points are fed back as part of the CSI feedback corresponding to the training data. In addition, the likelihood ratio indicating whether a given coefficient corresponding to the channel or the precoding matrix is associated with a non-zero magnitude value is reported, where the likelihood ratio is based on the weights or occurrence rates of the given CSI data points as part of the training dataset points. Furthermore, the above AI-based CSI framework helps to infer the characteristics of the channel distribution based on the training dataset, such that the CSI feedback can utilize distribution-aware data compression schemes, such as Huffman coding, where the CSI parameters are encoded such that values with higher occurrence probabilities are mapped to shorter bit sequences, while the CSI parameters are encoded such that values with lower occurrence probabilities are mapped to longer bit sequences.

[0198] An indication of CSI training data set transmission can be sent. In one or more implementations, a CSI training data set report is sent from a network node (e.g., a network entity such as a gNB) to a UE. In one example, the CSI training data set report is sent via PDSCH. In another example, the CSI training data set report is sent via PDCCH. In another example, the CSI training data set report is sent via higher layer signaling, e.g., as part of an RRC configuration.

[0199] Additionally or alternatively, a CSI training data set is sent from the UE to a network node (e.g., a network entity such as a gNB). In one example, the CSI training data set report is sent via PUSCH. In another example, the CSI training data set report is sent via PUCCH. In another example, the CSI training data set report is further divided into two parts, the first part of the two parts of the CSI training set report is sent via PUCCH, and the second part of the two parts of the CSI training set report is sent via PUSCH.

[0200] Additionally or alternatively, the CSI training data set report corresponds to a CSI report type configured via a CSI report setting. In one example, the CSI report setting includes a higher layer configuration parameter, where if the CSI report corresponds to the CSI training data set report, the higher layer configuration parameter is set to true. In another example, the CSI training data set report corresponds to a new codebook type of PMI and CSI report, e.g., the CSI training data set report corresponds to a Type-III codebook type.

[0201] Additionally or alternatively, the CSI training data set report is configured via a dedicated higher layer report setting, e.g., a training data report setting or an AI report setting.

[0202] Type-II high-resolution CSI compression can be performed. In one or more implementations, the CSI feedback corresponding to the CSI training data set report is based on the Rel-18 Type-II codebook format, where the parameters corresponding to W1, W f，l 、W d，l 、 or the bitmap corresponding to the LCC of is reported as part of the CSI report based on the training data set. In one example, the matrix W d，l is scalarized to a value of 1, e.g., the codebook format is similar to the Rel-16 Type-II codebook.

[0203] Additionally or alternatively, the configuration value of the parameter corresponding to the number of beams (e.g., L) used for CSI training data set reporting is greater than the value L corresponding to the CSI report based on the Type-II codebook, for example, L=6, 8, 10 under CSI training data set reporting.

[0204] Additionally or alternatively, the configuration value of the parameter corresponding to the number of frequency domain base indices (e.g., M) for CSI training data set reporting is greater than the value M corresponding to the CSI report based on the Type-II codebook, for example, under CSI training data set reporting, M=0.5N3, 0.75N3 or N3.

[0205] Additionally or alternatively, the configuration value of the parameter corresponding to the number of time domain base indices (e.g., Q) for CSI training data set reporting is greater than the value Q corresponding to the CSI report based on the Type-II codebook, for example, under CSI training data set reporting, Q=N4.

[0206] Additionally or alternatively, the configuration value of the parameter corresponding to a portion of the non-zero coefficients (e.g., β) for CSI training data set reporting is greater than the value β corresponding to the CSI report based on the Type-II codebook, for example, under CSI training data set reporting, β=1.

[0207] Additionally or alternatively, an indication of the total number of dataset points included in the CSI training dataset report is reported as part of the CSI training dataset report.

[0208] Additionally or alternatively, an indication of a total number of bits corresponding to a size of a CSI training data set report is reported in a first part of the CSI training data set report, wherein the CSI training data set report comprises a plurality of parts.

[0209] It is also possible to perform a CSI / PMI compression matrix reporting weight. In the CSI training data set report, compression or transformation of the spatial, frequency or time domain base index can be applied. Different implementations are provided below. One or more of these implementations can also be combined.

[0210] In one or more implementations, the CSI training data set report includes a selection corresponding to a subset of a set of possible spatial basis combinations (e.g., beam combinations). In one example, the subset includes In another example, the selected subset of spatial basis combinations is indicated via N' parameters, each parameter having bits of width, where Corresponds to the ceiling operator, for example, the smallest integer value greater than or equal to the parameter x. In another example, the selected subset N' of spatial basis combinations is obtained by having jointly indicated by a single parameter with a bit width of

[0211] Additionally or alternatively, the CSI training data set report includes a selection corresponding to a subset of a set of possible frequency domain basis combinations. In one example, the subset includes N' frequency domain basis combinations from a set of frequency domain basis combinations. In another example, the subset of the selection of the frequency domain basis combinations is indicated by N' parameters, each parameter having a bit width of

[0212] Additionally or alternatively, the CSI training data set report includes a selection corresponding to a subset of a set of possible time domain basis combinations. In one example, the subset includes N' time domain basis combinations from a set of time domain basis combinations. In another example, the subset of the selection of the time domain basis combinations is indicated by N' parameters, each parameter having a bit width of

[0213] Additionally or alternatively, the CSI training data set report includes a selection corresponding to a subset of a set of possible joint spatial / frequency domain basis combinations. In one example, the subset includes N' joint spatial / time domain basis combinations from a set of joint spatial / frequency domain basis combinations. In another example, the subset of the selection of the joint spatial / frequency domain basis combinations is indicated by N' parameters, each parameter having a bit width of

[0214] Additionally or alternatively, the CSI training data set report includes a selection corresponding to a subset of a set of possible joint frequency / time domain basis combinations. In one example, the subset includes N' joint frequency / time domain basis combinations from a set of joint frequency / time domain basis combinations. In another example, the subset of the selection of the joint frequency / time domain basis combinations is indicated by N' parameters, each parameter having a bit width of

[0215] Additionally or alternatively, the CSI training data set report includes selections corresponding to subsets of a set of possible joint spatial / temporal basis combinations. In one example, the subset includes N' joint spatial / temporal basis combinations from a set of joint spatial / temporal basis combinations. In another example, a subset of the selections of joint spatial / frequency basis combinations is indicated via N' parameters, each parameter having a bit width of bits. In another example, the subset N' of the selections of joint spatial / temporal basis combinations is jointly indicated via a single parameter having

[0216] Additionally or alternatively, the CSI training data set report includes selections corresponding to subsets of a set of possible joint spatial / frequency / temporal basis combinations. In another example, the subset includes N' joint spatial / frequency / temporal basis combinations from a set of joint spatial / frequency / temporal basis combinations. In another example, a subset of the selections of joint spatial / frequency / temporal basis combinations is indicated via N' parameters, each parameter having a bit width of bits. In another example, the subset N' of the selections of joint spatial / frequency / temporal basis combinations is jointly indicated via a single parameter having

[0217] Additionally or alternatively, the CSI training data set report includes weights or probabilities corresponding to each subset in an N'-sized subset of basis / basis combinations. In one example, N' parameters are fed back, each parameter corresponding to the weight of each of the N' selected combinations. In another example, each weight parameter value is selected from a codebook of predefined or preconfigured weight values. In another example, the weights are normalized by the size of the data set. In another example, the weights are normalized by the value of the maximum weight, e.g., at least one weight is set to 1.

[0218] A bitmap report of the training data may also be performed. In the CSI training data set report, only a subset of the coefficient values may be associated with non-zero magnitude values. Different implementations are provided below. One or more of these implementations may also be combined.

[0219] In one or more implementations, an indication of non-zero coefficients corresponding to a matrix of coefficients is reported in the CSI training data set report.

[0220] Additionally or alternatively, multiple bitmaps among the K' bitmaps are reported in the CSI training data set report. In one example, different sets of K' bitmaps are reported for each of the N' selected base / base combinations. In another example, a common set of K' bitmaps is reported for all N' selected base / base combinations.

[0221] Additionally or alternatively, a set of parameters having a one-to-one mapping corresponding to the coefficients of a precoding matrix is reported in the CSI training data set report, where each parameter in the set of parameters includes an indication of the likelihood that the corresponding coefficient is quantized to a zero amplitude value. In one example, the indication is in the form of the probability that the coefficient is quantized to a zero amplitude value. An illustration of this example can be found in Table 7 below. This example corresponds to reporting the likelihood that each coefficient of a precoding matrix with L = 6, M = 10 (e.g., of size 12×10 ) has a non-zero value.

[0222] Table 7

[0223]

[0224]

[0225] In another example, the indication is in the form of a function of a likelihood ratio, such as an LLR based on the ratio of the probability that the coefficient is quantized to a zero amplitude value to the probability that the coefficient is quantized to a non-zero amplitude value.

[0226] PMI reporting for the amplitude / phase coefficients of the training data can be performed. The CSI training data set report can include a plurality of non-zero coefficients corresponding to the matrix of coefficients reported in the CSI training data set report For each non-zero coefficient, an amplitude value and a phase value can be reported. Different implementations will be discussed below. One or more of these implementations can also be combined.

[0227] In one or more implementations, multiple amplitude values, multiple phase values, or a combination thereof are jointly encoded as a common indicator value in a set of indicator values. In one example, the multiple amplitude values correspond to a subset of coefficients associated with a common spatial domain base index (e.g., beam index). In another example, the multiple amplitude values correspond to a subset of coefficients associated with a common frequency domain base index (e.g., beam index).

[0228] Additionally or alternatively, two distributions, types, or categories that support an indication of amplitude values, phase values, or a combination thereof, where the selected distribution, type, or category is based on an index of a spatial domain basis, an index of a frequency domain basis, an index of a time domain basis, or a combination thereof. In one example, the first distribution, type, or category corresponds to a spatial domain basis index (e.g., a beam index) associated with the strongest coefficient (e.g., the coefficient with the largest amplitude value), and the second distribution, type, or category corresponds to all spatial domain basis indices not associated with the strongest coefficient. In another example, a first set of multiple sets of amplitude and phase coefficient values is defined according to the first distribution, and a second set of multiple sets of amplitude and phase coefficient values is defined according to the first distribution.

[0229] Additionally or alternatively, at least one distribution, type, or category that supports an indication of amplitude values, phase values, or a combination thereof, where the selected distribution, type, or category is based on a layer index corresponding to the number of layers of a precoding matrix. In one example, the same distribution, type, or category is selected for all layers of the precoding matrix. In another example, a different distribution, type, or category is selected for each layer of the precoding matrix.

[0230] Additionally or alternatively, multiple amplitude values, multiple phase values, or a combination thereof correspond to a set of consecutive basis indices in the spatial domain, frequency domain, or time domain, where the first basis index in the set of consecutive basis indices is indicated by an offset value reported as part of a CSI training data set report. In one example, multiple amplitude values correspond to three consecutive amplitude values, as shown in Table 8 below.

[0231] Table 8

[0232]

[0233] In another example, an offset value is reported that indicates the position of the first value of the reported amplitude values. For example, for multiple amplitude values sharing the same spatial domain basis index with M = 9 frequency domain basis indices, an offset value λ of 8 (or λ = -1 assuming circular offset) corresponds to a set of M = 9 amplitude values, as shown in Table 9 below.

[0234] Table 9

[0235]

[0236] Additionally or alternatively, two classes of amplitude values are reported: a first class of amplitude values corresponds to each coefficient in a set of non-zero coefficients, and a second class of amplitude values corresponds to a common reference value of a group of coefficients with the same polarization value among two polarization values.

[0237] An RI report for the training data can be performed. The CSI training data set report can include a reference to at least one RI value. Different implementations will be discussed below. One or more of these implementations can also be combined.

[0238] In one or more implementations, a set of weight or probability values corresponding to a set of RI values is reported in the CSI training data set report. In one example, the set of weight or probability values corresponds to a selected subset of the set of RI values. In another example, the set of weight or probability values is selected from a codebook of weight or probability values. In another example, the set of weight or probability values is reported for all RI values up to a maximum RI value. For example, given a maximum RI value of 4, the weights corresponding to the set of RI values {1, 2, 3, 4} are provided in Table 10 below.

[0239] Table 10

[0240] RI 1 2 3 4 Weight 0.1 0.6 0.2 0.1

[0241] A CQI report for the training data can be performed. The CSI training data set report can include a reference to at least one CQI value. Different implementations are provided below. One or more of these implementations can also be combined.

[0242] In one or more implementations, a set of weight or probability values corresponding to a set of CQI values is reported in the CSI training data set report. In one example, the set of weight or probability values corresponds to a selected subset of the set of CQI values. In a second example, the set of weight or probability values is selected from a codebook of weight or probability values.

[0243] Additionally or alternatively, a sequence of at least one SB CQI value is indicated via a joint indicator value. In one example, multiple indicators are reported, where each indicator corresponds to multiple SB CQI values. In another example, a weight or probability value is reported for each indicator of the sequence of SB CQI values.

[0244] Additionally or alternatively, the CQI value is associated with one of the following: an RI value, a bitmap, a spatial / frequency / time domain basis combination, a set of amplitude / phase coefficients, or a combination thereof.

[0245] The CSI report can be encoded. Based on the described CSI training data set report, weights corresponding to spatial / frequency / time domain basis transformations, bitmap indications, amplitude / phase coefficients, RI, CQI, or combinations thereof can provide some underlying information corresponding to a precoding matrix / channel distribution. Different implementations will be discussed below. One or more of these implementations can also be combined.

[0246] In one or more implementations, a CSI report computed based on a CSI training data set report includes parameters corresponding to at least one of the following: a spatial / frequency / time domain basis indicator, a bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, an RI value, a CQI value, or a combination thereof.

[0247] Additionally or alternatively, at least one parameter of the CSI report is mapped to a set of values, the set of values being encoded via an encoding scheme of a set of weight or probability values indicated in the training data set report. In one example, the encoding scheme is based on a Huffman encoding scheme, where values with higher weight or probability values are encoded via a smaller number of bits, while values with lower weight or probability values are encoded via a larger number of bits.

[0248] Accordingly, a CSI feedback mechanism is discussed that provides a concise framework for a training data set report corresponding to CSI feedback, where training data is aggregated such that similar training data set points are fed back once, the similar training data set points being associated with a weight coefficient corresponding to the probability or occurrence rate of the data set point. More specifically, reporting statistical CSI training data by aggregating similar training data set points corresponding to CSI is discussed, where the corresponding weight or occurrence rate of the data set point is fed back as part of the CSI feedback corresponding to the training data. Reporting a likelihood ratio of whether a given coefficient corresponding to a channel / precoding matrix is associated with a non-zero magnitude value is also discussed, where the likelihood ratio is based on the weight / occurrence rate of the given CSI data point as part of the training data set point. Inferring characteristics of a channel distribution based on a training data set such that CSI feedback can utilize a distribution-aware data compression scheme, such as Huffman coding, where CSI parameters are encoded such that values with a higher occurrence likelihood are mapped to shorter bit sequences, while CSI parameters are encoded such that values with a lower occurrence likelihood are mapped to longer bit sequences, is also discussed.

[0249] Figure 6FIG. 600 is an example of a block diagram of a device 602 that supports codebook - based training data set reporting for channel state information in accordance with aspects of the present disclosure. The device 602 may be an example of a UE 104 (or network entity 102) as described herein. The device 602 may support wireless communication with one or more network entities 102, UEs 104, or any combination thereof. The device 602 may include components for two - way communication, including components for sending and receiving communications (such as a processor 604, a memory 606, a transceiver 608, and an I / O controller 610). These components may communicate electronically or otherwise be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., a bus).

[0250] The processor 604, the memory 606, the transceiver 608, or various combinations or various components thereof may be examples of components for performing various aspects of the present disclosure described herein. For example, the processor 604, the memory 606, the transceiver 608, or various combinations or components thereof may support methods for performing one or more of the operations described herein.

[0251] In some implementations, the processor 604, the memory 606, the transceiver 608, or various combinations or components thereof may be implemented in hardware (e.g., in communication management circuitry). The hardware may include a processor, a digital signal processor (DSP), an application - specific integrated circuit (ASIC), a field - programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of components configured or otherwise supporting the functions described in the present disclosure. In some implementations, the processor 604 and the memory 606 coupled to the processor 604 may be configured to perform one or more functions described herein (e.g., the processor 604 executes instructions stored in the memory 606).

[0252] For example, in accordance with an example disclosed herein, the processor 604 may support wireless communication at the device 602. The processor 604 may be configured to or otherwise support: obtaining a training data set report corresponding to CSI based on a PMI codebook, where the training data set report includes a plurality of parameters corresponding to the PMI codebook, the plurality of parameters being associated with a plurality of weight values; sending a first signaling to a device indicating the training data set report.

[0253] Additionally or alternatively, processor 604 may be configured to or otherwise support: where the apparatus includes a user equipment, and the processor is further configured to cause the apparatus to transmit first signaling over a physical uplink channel; where the apparatus includes a user equipment, and the processor is further configured to cause the apparatus to: transmit first signaling over a physical downlink channel, transmit the first signaling as part of high layer configuration information, or a combination thereof; where the plurality of parameters includes a first set of code points, and each code point in the first set of code points corresponds to a selected subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; where the first set of code points is a subset of a second set of code points, and each code point in the second set of code points corresponds to a subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; where the plurality of parameters includes a set of entries corresponding to a bitmap that identifies the reported coefficients having non-zero magnitude values; where each entry in the set of entries corresponds to the likelihood that a coefficient has a non-zero magnitude value; where the plurality of parameters includes a set of code points, and each code point in the set of code points corresponds to at least one of the following: a set of coefficient magnitude values and a set of coefficient phase values associated with a plurality of consecutive airspace basis indices, a plurality of consecutive frequency domain basis indices, a plurality of consecutive time domain basis indices, or a combination thereof; where each code point in the set of code points is associated with one of two coefficient types, where the first of the two coefficient types is associated with a first set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof, and where the second of the two coefficient types is associated with a second set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; where the first set of the airspace basis index, the frequency domain basis index, and the time domain basis index is associated with the strongest coefficient having the maximum magnitude value; where the plurality of parameters includes a set of rank indicator values, and each rank indicator value in the set of rank indicator values is associated with a different weight; where the plurality of parameters includes a set of channel quality indicator values, and each channel quality indicator value in the set of channel quality indicator values is associated with a different weight; where the processor is further configured to cause the apparatus to: obtain a CSI report reported based on a training data set, where the CSI report includes parameters corresponding to the following: an airspace basis index, a frequency domain basis index, a time domain basis index, a bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, an RI value, a CQI value, or a combination thereof, and each parameter in the parameters of the CSI report is mapped to a set of values that are encoded via an encoding scheme based on a plurality of weight values included in the training data set report; and transmit second signaling indicating the CSI report to the device.

[0254] For example, according to the examples disclosed herein, the processor 604 may support wireless communication at the device 602. The processor 604 may be configured to or otherwise support components for: obtaining a training data set report corresponding to CSI based on a PMI codebook, where the training data set report includes a plurality of parameters corresponding to the PMI codebook, the plurality of parameters being associated with a plurality of weight values; and sending a first signaling indicating the training data set report to the device.

[0255] Additionally or alternatively, the processor 604 may be configured to or otherwise support: where the method is implemented by a user equipment and further includes transmitting first signaling via a physical uplink channel; where the device includes a user equipment and the method further includes: transmitting first signaling via a physical downlink channel, transmitting the first signaling as part of high layer configuration information, or a combination thereof; where the plurality of parameters includes a first set of code points, and each code point in the first set of code points corresponds to a selected subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; where the first set of code points is a subset of a second set of code points, and each code point in the second set of code points corresponds to a subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; where the plurality of parameters includes a set of entries corresponding to a bitmap that identifies the reported coefficients having non-zero magnitude values; where each entry in the set of entries corresponds to the likelihood that a coefficient has a non-zero magnitude value; where the plurality of parameters includes a set of code points, and each code point in the set of code points corresponds to at least one of: a set of coefficient magnitude values and a set of coefficient phase values associated with a plurality of consecutive airspace basis indices, a plurality of consecutive frequency domain basis indices, a plurality of consecutive time domain basis indices, or a combination thereof; where each code point in the set of code points is associated with one of two coefficient types, where the first coefficient type of the two coefficient types is associated with a first set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof, and where the second coefficient type of the two coefficient types is associated with a second set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; where the first set of the airspace basis index, the frequency domain basis index, and the time domain basis index is associated with the strongest coefficient having the maximum magnitude value; where the plurality of parameters includes a set of rank indicator values, and each rank indicator value in the set of rank indicator values is associated with a different weight; where the plurality of parameters includes a set of channel quality indicator values, and each channel quality indicator value in the set of channel quality indicator values is associated with a different weight; further including: obtaining a CSI report reported based on a training data set, where the CSI report includes parameters corresponding to: an airspace basis index, a frequency domain basis index, a time domain basis index, a bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, an RI value, a CQI value, or a combination thereof, and each parameter in the parameters of the CSI report is mapped to a set of values that are encoded via an encoding scheme based on a plurality of weight values included in the training data set report; and transmitting second signaling indicating the CSI report to the device.

[0256] For example, according to the examples disclosed herein, the processor 604 may support wireless communication. The processor 604 includes at least one controller coupled to at least one memory and is configured or operable to cause the processor to: obtain a training dataset report corresponding to CSI based on a PMI codebook, where the training dataset report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values; send a first signaling indicating the training dataset report to a device.

[0257] The processor 604 may include intelligent hardware devices (e.g., general-purpose processors, DSPs, CPUs, microcontrollers, ASICs, FPGAs, programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some implementations, the processor 604 may be configured to operate a memory array using a memory controller. In some other implementations, the memory controller may be integrated into the processor 604. The processor 604 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 606) to cause the device 602 to perform various functions of the present disclosure.

[0258] The memory 606 may include random access memory (RAM) and read-only memory (ROM). The memory 606 may store computer-readable computer-executable code that includes instructions that, when executed by the processor 604, cause the device 602 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. In some implementations, the code may not be directly executable by the processor 604 but may cause a computer (e.g., when compiled and executed) to perform the functions described herein. In some implementations, the memory 606 may include a basic input / output system (BIOS) that may control basic hardware or software operations, such as interactions with peripheral components or devices.

[0259] The I / O controller 610 may manage the input and output signals of the device 602. The I / O controller 610 may also manage peripheral devices not integrated into the device 602. In some implementations, the I / O controller 610 may represent a physical connection or port to an external peripheral device. In some implementations, the I / O controller 610 may utilize an operating system, such as MS or other known operating systems. In some implementations, the I / O controller 610 may be implemented as part of a processor such as the processor 604. In some implementations, a user may interact with the device 602 via the I / O controller 610 or via a hardware component controlled by the I / O controller 610.

[0260] In some implementations, device 602 may include a single antenna 612. However, in some other implementations, device 602 may have more than one antenna 612 (i.e., multiple antennas), including multiple antenna panels or antenna arrays, which are capable of concurrently transmitting or receiving multiple wireless transmissions. Transceiver 608 may communicate bidirectionally via one or more antennas 612, wired or wireless links, as described herein. For example, transceiver 608 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. Transceiver 608 may also include a modem that is configured to modulate packets, provide the modulated packets to one or more antennas 612 for transmission, and demodulate packets received from one or more antennas 612.

[0261] Figure 7 FIG. 700 illustrates an example of a block diagram of a device 702 that supports codebook-based training data set reporting for channel state information, in accordance with aspects of the present disclosure. Device 702 may be an example of network entity 102 (or UE 104) as described herein. Device 702 may support wireless communication with one or more network entities 102, UEs 104, or any combination thereof. Device 702 may include components for bidirectional communication, including components for sending and receiving communications (such as processor 704, memory 706, transceiver 708, and I / O controller 710). These components may communicate electronically or otherwise be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., a bus).

[0262] Processor 704, memory 706, transceiver 708, or various combinations or various components thereof may be examples of components for performing various aspects of the present disclosure described herein. For example, processor 704, memory 706, transceiver 708, or various combinations or components thereof may support a method for performing one or more of the operations described herein.

[0263] In some implementations, processor 704, memory 706, transceiver 708, or various combinations or components thereof may be implemented in hardware (e.g., in communication management circuitry). The hardware may include a processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, which are configured to or otherwise support components for performing the functions described in the present disclosure. In some implementations, processor 704 and memory 706 coupled to processor 704 may be configured to perform one or more functions described herein (e.g., by processor 704 executing instructions stored in memory 706).

[0264] For example, according to the examples disclosed herein, the processor 704 may support wireless communication at the device 702. The processor 704 may be configured to or otherwise support: receiving, from a device, a first signaling indicating a training data set report; wherein the training data set report corresponds to CSI based on a PMI codebook, wherein the training data set report includes a plurality of parameters corresponding to the PMI codebook, the plurality of parameters being associated with a plurality of weight values.

[0265] Additionally or alternatively, processor 704 may be configured to or otherwise support: wherein the device comprises a user equipment, and the processor is further configured to cause the device to receive first signaling over a physical uplink channel; wherein the device comprises a user equipment, and the processor is further configured to cause the device to: receive first signaling over a physical downlink channel, receive the first signaling as part of high layer configuration information, or a combination thereof; wherein the plurality of parameters comprises a first set of code points, and each code point in the first set of code points corresponds to a selected subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; wherein the first set of code points is a subset of a second set of code points, and each code point in the second set of code points corresponds to a subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; wherein the plurality of parameters comprises a set of entries corresponding to a bitmap that identifies the reported coefficients having non-zero magnitude values; wherein each entry in the set of entries corresponds to the likelihood that a coefficient has a non-zero magnitude value; wherein the plurality of parameters comprises a set of code points, and each code point in the set of code points corresponds to at least one of the following: a set of coefficient magnitude values and a set of coefficient phase values associated with a plurality of consecutive airspace basis indices, a plurality of consecutive frequency domain basis indices, a plurality of consecutive time domain basis indices, or a combination thereof; wherein each code point in the set of code points is associated with one of two coefficient types, wherein the first of the two coefficient types is associated with a first set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof, and wherein the second of the two coefficient types is associated with a second set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof; wherein the first set of the airspace basis index, the frequency domain basis index, and the time domain basis index is associated with the strongest coefficient having the maximum magnitude value; wherein the plurality of parameters comprises a set of rank indicator values, and each rank indicator value in the set of rank indicator values is associated with a different weight; wherein the plurality of parameters comprises a set of channel quality indicator values, and each channel quality indicator value in the set of channel quality indicator values is associated with a different weight; wherein the processor is further configured to cause the device to: receive second signaling from the device indicating a CSI report; wherein the CSI report is reported based on a training data set, and wherein the CSI report comprises parameters corresponding to: an airspace basis index, a frequency domain basis index, a time domain basis index, a bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, an RI value, a CQI value, or a combination thereof, and each parameter in the parameters of the CSI report is mapped to a set of values that are encoded via an encoding scheme based on a plurality of weight values included in the training data set report.

[0266] For example, according to the examples disclosed herein, the processor 704 may support wireless communication at the device 702. The processor 704 may be configured to or otherwise support components for: receiving, from the device, a first signaling indicating a training data set report; and wherein the training data set report corresponds to CSI based on a PMI codebook, and wherein the training data set report includes a plurality of parameters corresponding to the PMI codebook, the plurality of parameters being associated with a plurality of weight values.

[0267] Additionally or alternatively, the processor 704 may be configured to or otherwise support: wherein the device includes a user equipment, and the method further includes receiving first signaling via a physical uplink channel; wherein the method is implemented in the user equipment, and the method further includes: receiving first signaling via a physical downlink channel, receiving the first signaling as part of high-layer configuration information, or a combination thereof; wherein the plurality of parameters includes a first set of code points, and each code point in the first set of code points corresponds to a selected subset of an airspace basis index, a frequency-domain basis index, a time-domain basis index, or a combination thereof; wherein the first set of code points is a subset of a second set of code points, and each code point in the second set of code points corresponds to a subset of an airspace basis index, a frequency-domain basis index, a time-domain basis index, or a combination thereof; wherein the plurality of parameters includes a set of entries corresponding to a bitmap that identifies the reported coefficients having non-zero magnitude values; wherein each entry in the set of entries corresponds to the likelihood that a coefficient has a non-zero magnitude value; additionally or alternatively, the processor 704 may be configured to or otherwise support: wherein the plurality of parameters includes a set of code points, and each code point in the set of code points corresponds to at least one of the following: a set of coefficient magnitude values and a set of coefficient phase values associated with a plurality of consecutive airspace basis indices, a plurality of consecutive frequency-domain basis indices, a plurality of consecutive time-domain basis indices, or a combination thereof; additionally or alternatively, the processor 704 may be configured to or otherwise support: wherein each code point in the set of code points is associated with one of two coefficient types, wherein the first coefficient type of the two coefficient types is associated with a first set of an airspace basis index, a frequency-domain basis index, a time-domain basis index, or a combination thereof, and wherein the second coefficient type of the two coefficient types is associated with a second set of an airspace basis index, a frequency-domain basis index, a time-domain basis index, or a combination thereof; wherein the first set of the airspace basis index, the frequency-domain basis index, and the time-domain basis index is associated with the strongest coefficient having the maximum magnitude value; additionally or alternatively, the processor 704 may be configured to or otherwise support: wherein the plurality of parameters includes a set of rank indicator values, and each rank indicator value in the set of rank indicator values is associated with a different weight; additionally or alternatively, the processor 704 may be configured to or otherwise support: wherein the plurality of parameters includes a set of channel quality indicator values, and each channel quality indicator value in the set of channel quality indicator values is associated with a different weight; receiving second signaling from the device indicating a CSI report;The CSI report is based on a training data set report, and the CSI report includes parameters corresponding to the following: spatial domain basis index, frequency domain basis index, time domain basis index, bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, RI value, CQI value, or a combination thereof, and each parameter in the parameters of the CSI report is mapped to a set of values, and the set of values is encoded via an encoding scheme based on a plurality of weight values included in the training data set report.;

[0268] For example, according to the examples disclosed herein, the processor 704 may support wireless communication. The processor 704 includes at least one controller coupled to at least one memory and is configured to or operable to cause the processor to: receive a first signaling from a device indicating a training data set report; wherein the training data set report corresponds to CSI based on a PMI codebook, and the training data set report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values.

[0269] The processor 704 may include intelligent hardware devices (e.g., general-purpose processor, DSP, CPU, microcontroller, ASIC, FPGA, programmable logic device, discrete gate or transistor logic components, discrete hardware components, or any combination thereof). In some implementations, the processor 704 may be configured to operate a memory array using a memory controller. In some other implementations, the memory controller may be integrated into the processor 704. The processor 704 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 706) to cause the device 702 to perform various functions of the present disclosure.

[0270] The memory 706 may include random access memory (RAM) and read-only memory (ROM). The memory 706 may store computer-readable computer-executable code that includes instructions that, when executed by the processor 704, cause the device 702 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. In some implementations, the code may not be directly executed by the processor 704, but may cause a computer (e.g., when compiled and executed) to perform the functions described herein. In some implementations, the memory 706 may include a basic input / output system (BIOS) that may control basic hardware or software operations, such as interactions with peripheral components or devices.

[0271] The I / O controller 710 may manage the input and output signals of the device 702. The I / O controller 710 may also manage peripheral devices not integrated into the device 702. In some implementations, the I / O controller 710 may represent a physical connection or port to an external peripheral device. In some implementations, the I / O controller 710 may utilize an operating system, such as MS or other known operating systems. In some implementations, the I / O controller 710 may be implemented as part of a processor, such as the processor 704. In some implementations, a user may interact with the device 702 via the I / O controller 710 or via hardware components controlled by the I / O controller 710.

[0272] In some implementations, the device 702 may include a single antenna 712. However, in some other implementations, the device 702 may have more than one antenna 712 (i.e., multiple antennas), including multiple antenna panels or antenna arrays, which are capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 708 may communicate bidirectionally via one or more antennas 712, wired or wireless links, as described herein. For example, the transceiver 708 may represent a wireless transceiver and may communicate bidirectionally with another wireless transceiver. The transceiver 708 may also include a modem that modulates packets, provides the modulated packets to one or more antennas 712 for transmission, and demodulates packets received from one or more antennas 712.

[0273] Figure 8 FIG. illustrates a flowchart of a method 800 that supports codebook-based training data set reporting for channel state information in accordance with aspects of the present disclosure. The operations of method 800 may be implemented by the devices or components described herein. For example, the operations of method 800 may be performed by the UE 104 (or network entity 102) described in reference to Figures 1 to 7 above. In some implementations, the device may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally or alternatively, the device may use dedicated hardware to perform aspects of the described functions.

[0274] At 805, the method may include obtaining a training data set report corresponding to CSI based on a PMI codebook, where the training data set report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values. The operation of 805 may be performed in accordance with the examples described herein. In some implementations, aspects of the operation of 805 may be performed by the device described in reference to Figure 1 above.

[0275] At 810, the method can include sending first signaling to a device indicating a training data set report. The operation of 810 can be performed according to the examples described herein. In some implementations, aspects of the operation of 810 can be performed by the device referenced Figure 1 as described.

[0276] Figure 9 FIG. illustrates a flowchart of a method 900 supporting codebook-based training data set reporting for channel state information in accordance with aspects of the present disclosure. The operations of method 900 can be implemented by a device or components thereof described herein. For example, the operations of method 900 can be performed by the UE 104 (or network entity 102) referenced Figures 1 to 7 as described. In some implementations, the device can execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device can use special purpose hardware to perform aspects of the described functions.

[0277] At 905, the method can include the apparatus including a user equipment. The operation of 905 can be performed according to the examples described herein. In some implementations, aspects of the operation of 905 can be performed by the device referenced Figure 1 as described.

[0278] At 910, the method can include sending the first signaling via a physical uplink channel. The operation of 910 can be performed according to the examples described herein. In some implementations, aspects of the operation of 910 can be performed by the device referenced Figure 1 as described.

[0279] Figure 10 FIG. illustrates a flowchart of a method 1000 supporting codebook-based training data set reporting for channel state information in accordance with aspects of the present disclosure. The operations of method 1000 can be implemented by a device or components thereof described herein. For example, the operations of method 1000 can be performed by the UE 104 (or network entity 102) referenced Figures 1 to 7 as described. In some implementations, the device can execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device can use special purpose hardware to perform aspects of the described functions.

[0280] At 1005, the method can include the apparatus including a user equipment. The operation of 1005 can be performed according to the examples described herein. In some implementations, aspects of the operation of 1005 can be performed by the device referenced Figure 1 as described.

[0281] At 1010, the method may include transmitting first signaling over a physical downlink channel, transmitting the first signaling as part of high layer configuration information, or a combination thereof. The operations at 1010 may be performed in accordance with the examples described herein. In some implementations, aspects of the operations at 1010 may be performed by a device referenced Figure 1 as described.

[0282] Figure 11 FIG. illustrates a flow diagram of a method 1100 that supports codebook-based training data set reporting for channel state information in accordance with aspects of the present disclosure. The operations of method 1100 may be implemented by a device or components thereof described herein. For example, the operations of method 1100 may be performed by a UE 104 (or network entity 102) referenced Figures 1 to 7 as described. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may use special purpose hardware to perform aspects of the described functions.

[0283] At 1105, the method may include obtaining a CSI report based on a training data set report, where the CSI report includes parameters corresponding to: a spatial domain basis index, a frequency domain basis index, a time domain basis index, a bitmap indicator, a set of indicators corresponding to magnitude values of non-zero coefficients, a set of indicators corresponding to phase values of non-zero coefficients, an RI value, a CQI value, or a combination thereof, and each parameter in the parameters of the CSI report is mapped to a set of values that are encoded via an encoding scheme based on a plurality of weight values included in the training data set report. The operations at 1105 may be performed in accordance with the examples described herein. In some implementations, aspects of the operations at 1105 may be performed by a device referenced Figure 1 as described.

[0284] At 1110, the method may include sending second signaling to the device indicating the CSI report. The operations at 1110 may be performed in accordance with the examples described herein. In some implementations, aspects of the operations at 1110 may be performed by a device referenced Figure 1 as described.

[0285] Figure 12 FIG. illustrates a flow diagram of a method 1200 that supports codebook-based training data set reporting for channel state information in accordance with aspects of the present disclosure. The operations of method 1200 may be implemented by a device or components thereof described herein. For example, the operations of method 1200 may be performed by a device referenced Figures 1 to 7The network entity 102 (or UE 104) described above performs. In some implementations, the device may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally or alternatively, the device may use dedicated hardware to perform aspects of the described functions.

[0286] At 1205, the method may include receiving, from a device, first signaling indicating a training data set report. The operation at 1205 may be performed according to the examples described herein. In some implementations, aspects of the operation at 1205 may be performed by the device referenced Figure 1 above.

[0287] At 1210, the method may include the training data set report corresponding to CSI based on a PMI codebook, where the training data set report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values. The operation at 1210 may be performed according to the examples described herein. In some implementations, aspects of the operation at 1210 may be performed by the device referenced Figure 1 above.

[0288] Figure 13 FIG. illustrates a flow chart of a method 1300 supporting codebook-based training data set reporting for channel state information according to aspects of the present disclosure. The operations of method 1300 may be implemented by the devices or components described herein. For example, the operations of method 1300 may be performed by the network entity 102 (or UE 104) referenced Figures 1 to 7 above. The device may execute a set of instructions to control the functional elements of the device to perform the described functions. Additionally or alternatively, the device may use dedicated hardware to perform aspects of the described functions.

[0289] At 1305, the method may include the device including a user equipment. The operation at 1305 may be performed according to the examples described herein. In some implementations, aspects of the operation at 1305 may be performed by the device referenced Figure 1 above.

[0290] At 1310, the method may include receiving, via a physical uplink channel, first signaling. The operation at 1310 may be performed according to the examples described herein. In some implementations, aspects of the operation at 1310 may be performed by the device referenced Figure 1 above.

[0291] Figure 14 FIG. illustrates a flow chart of a method 1400 supporting codebook-based training data set reporting for channel state information according to aspects of the present disclosure. The operations of method 1400 may be implemented by the devices or components described herein. For example, the operations of method 1400 may be performed by the device referencedFigures 1 to 7 The network entity 102 (or UE 104) as described performs. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may use dedicated hardware to perform aspects of the described functions.

[0292] At 1405, the method may include the apparatus including a user equipment. The operation of 1405 may be performed according to the examples described herein. In some implementations, aspects of the operation of 1405 may be performed by reference to Figure 1 the device as described.

[0293] At 1410, the method may include receiving first signaling via a physical downlink channel, receiving the first signaling as part of higher layer configuration information, or a combination thereof. The operation of 1410 may be performed according to the examples described herein. In some implementations, aspects of the operation of 1410 may be performed by reference to Figure 1 the device as described.

[0294] Figure 15 A flowchart of a method 1500 in accordance with aspects of the present disclosure is illustrated, which method supports codebook-based training data set reporting for channel state information. The operations of method 1500 may be implemented by the devices or components described herein. For example, the operations of method 1500 may be performed by reference to Figures 1 to 7 the network entity 102 (or UE 104) as described. In some implementations, the device may execute a set of instructions to control functional elements of the device to perform the described functions. Additionally or alternatively, the device may use dedicated hardware to perform aspects of the described functions.

[0295] At 1505, the method may include receiving first signaling via a physical downlink channel, receiving the first signaling as part of higher layer configuration information, or a combination thereof. The operation of 1505 may be performed according to the examples described herein. In some implementations, aspects of the operation of 1505 may be performed by reference to Figure 1 the device as described.

[0296] At 1510, the method may include a CSI report based on a training data set report, where the CSI report includes parameters corresponding to the following: spatial domain basis index, frequency domain basis index, time domain basis index, bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, RI value, CQI value, or a combination thereof, and each parameter in the CSI report's parameters is mapped to a set of values that are encoded via an encoding scheme based on a plurality of weight values included in the training data set report. The operation of 1510 may be performed according to the examples described herein. In some implementations, aspects of the operation of 1510 may be performed by the device referenced Figure 1 as described.

[0297] It should be noted that the methods described herein describe possible implementations, and the operations and steps may be rearranged or otherwise modified, and other implementations are possible. Additionally, aspects from two or more methods may be combined.

[0298] The various illustrative blocks and components described in conjunction with the present disclosure may be implemented or performed with a general purpose processor, DSP, ASIC, CPU, 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. The general purpose processor may be a microprocessor, but in the alternative, the processor may be any processor, controller, microcontroller, or state machine. The 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).

[0299] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or code. Other examples and implementations are within the scope of the present disclosure and the appended claims. For example, due to the nature of software, the functions described herein may be implemented using software, hardware, firmware, hardwiring, or any combination thereof executed by a processor. The features implementing the functions may also be physically located at various positions, including being distributed such that portions of the functions are implemented at different physical locations.

[0300] A computer-readable medium includes both a non-transitory computer storage medium and a communication medium, where the communication medium includes any medium that facilitates transfer of a computer program from one place to another. The non-transitory storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. By way of example and not limitation, the non-transitory computer-readable medium can include RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory, compact disc (CD) ROM or other optical disc storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to carry or store desired program code means in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor.

[0301] Any connection can be properly termed a computer-readable medium. For example, if software is transmitted using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, from a website, server, or other remote source, 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. As used herein, disk and disc include CD, laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc, where disks typically reproduce data magnetically, while discs reproduce data optically with a laser. Combinations of the above are also included within the scope of computer-readable medium.

[0302] As used herein, and as included in the claims, the "or" used in a list of items (e.g., a list starting with phrases such as "at least one of...", or "one or more of...", or "one or both of...") means 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). Similarly, a list of one or more 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). Additionally, as used herein, the phrase "based on" should not be construed as a reference to a closed set of conditions. For example, an example step described as "based on condition A" can be based on both condition A and condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase "based on" should be interpreted in the same manner as the phrase "at least partially based on". Further, as used herein, and as included in the claims, a "set" can include one or more elements.

[0303] When referring to a network entity, the terms "send", "receive", or "transmit" can refer to any part of a RAN network entity (e.g., a base station, CU, DU, RU) that communicates with another device (e.g., directly or via one or more other network entities).

[0304] The description of example configurations described herein with reference to the drawings does not represent all examples that can be implemented or that are within the scope of the claims. The term "example" as used herein means "serving as an example, instance, or illustration" and not "preferred" or "better than other examples". The detailed description includes specific details to facilitate understanding of the described techniques. However, these techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form to avoid obscuring the concepts of the described examples.

[0305] The description provided herein is to enable a person of ordinary skill in the art to make or use the present disclosure. Various modifications to the present disclosure will be readily apparent to those of ordinary skill in the art, and the general principles defined herein may be applied to other variations without departing from the scope of the present disclosure. Thus, the present disclosure is not limited to the examples and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A device for wireless communication, comprising: at least one memory; and at least one processor, coupled to the at least one memory and configured to cause the device to: obtain a training data set report corresponding to channel state information (CSI) based on a precoding matrix indicator (PMI) codebook, wherein the training data set report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values; send a first signaling indicating the training data set report to a device.

2. The device according to claim 1, wherein the device comprises a user equipment, and the at least one processor is further configured to cause the device to send the first signaling via a physical uplink channel.

3. The device according to claim 1, wherein the device comprises a user equipment, and the at least one processor is further configured to cause the device to: send the first signaling via a physical downlink channel, send the first signaling as part of high layer configuration information, or a combination thereof.

4. The device according to claim 1, wherein the plurality of parameters include a first set of code points, and each code point in the first set of code points corresponds to a selected subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof.

5. The device according to claim 4, wherein the first set of code points is a subset of a second set of code points, and each code point in the second set of code points corresponds to a subset of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof.

6. The device according to claim 1, wherein the plurality of parameters include a set of entries corresponding to a bitmap, and the bitmap identifies the reported coefficients having non-zero amplitude values.

7. The device according to claim 6, wherein each entry in the set of entries corresponds to the likelihood that the coefficient has a non-zero amplitude value.

8. The device according to claim 1, wherein the plurality of parameters include a set of code points, and each code point in the set of code points corresponds to at least one of the following: a set of coefficient amplitude values and a set of coefficient phase values associated with a plurality of consecutive airspace basis indices, a plurality of consecutive frequency domain basis indices, a plurality of consecutive time domain basis indices, or a combination thereof.

9. The device according to claim 8, wherein each code point in the set of code points is associated with one of two coefficient types, wherein the first coefficient type of the two coefficient types is associated with a first set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof, and wherein the second coefficient type of the two coefficient types is associated with a second set of an airspace basis index, a frequency domain basis index, a time domain basis index, or a combination thereof.

10. The device according to claim 9, wherein the first set of the airspace basis index, the frequency domain basis index, and the time domain basis index is associated with the strongest coefficient having the maximum amplitude value.

11. The device according to claim 1, wherein the plurality of parameters include a set of rank indicator values, and each rank indicator value in the set of rank indicator values is associated with a different weight.

12. The apparatus according to claim 1, wherein the plurality of parameters includes a set of channel quality indicator values, and each channel quality indicator value in the set of channel quality indicator values is associated with a different weight.

13. The apparatus according to claim 1, wherein the at least one processor is further configured to cause the apparatus to: obtain a CSI report reported based on the training data set, wherein the CSI report includes parameters corresponding to the following: a spatial domain basis index, a frequency domain basis index, a time domain basis index, a bitmap indicator, a set of indicators corresponding to the magnitude values of non-zero coefficients, a set of indicators corresponding to the phase values of non-zero coefficients, a rank indicator (RI) value, a channel quality indicator (CQI) value, or a combination thereof, and each parameter in the parameters of the CSI report is mapped to a set of values, and the set of values is encoded via an encoding scheme based on the plurality of weight values included in the training data set report; and send a second signaling indicating the CSI report to the device.

14. An apparatus for wireless communication, comprising: at least one memory; and at least one processor, coupled to the at least one memory and configured to cause the apparatus to: receive a first signaling indicating a training data set report from a device; wherein the training data set report corresponds to channel state information (CSI) based on a precoding matrix indicator (PMI) codebook, and the training data set report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values.

15. The apparatus according to claim 14, wherein the plurality of parameters includes a first set of code points, and each code point in the first set of code points corresponds to a selected subset of a spatial domain basis index, a frequency domain basis index, a time domain basis index, or a combination thereof.

16. A method, comprising: obtaining a training data set report corresponding to channel state information (CSI) based on a precoding matrix indicator (PMI) codebook, wherein the training data set report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values; and and sending a first signaling indicating the training data set report to a device.

17. A processor for wireless communication, comprising: at least one controller, coupled to at least one memory and configured to cause the processor to: obtain a training data set report corresponding to channel state information (CSI) based on a precoding matrix indicator (PMI) codebook, wherein the training data set report includes a plurality of parameters corresponding to the PMI codebook, and the plurality of parameters are associated with a plurality of weight values; send a first signaling indicating the training data set report to a device.

18. The processor according to claim 17, wherein the plurality of parameters includes a first set of code points, and each code point in the first set of code points corresponds to a selected subset of a spatial domain basis index, a frequency domain basis index, a time domain basis index, or a combination thereof.

19. The processor according to claim 17, wherein the plurality of parameters includes a set of entries corresponding to a bitmap that identifies the reported coefficients having non-zero magnitude values.

20. The processor according to claim 17, wherein the plurality of parameters includes a set of code points, and each code point in the set of code points corresponds to at least one of: a set of coefficient magnitude values and a set of coefficient phase values associated with a plurality of consecutive spatial domain basis indices, a plurality of consecutive frequency domain basis indices, a plurality of consecutive time domain basis indices, or a combination thereof.

Images