Configuration for channel state feedback

Abstract

Various aspects of the present disclosure generally relate to wireless communications. In some aspects, a first device may receive a channel state information (CSI) feedback configuration including an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period. The first device may transmit a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel. Numerous other aspects are provided.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent application claims priority to Greek Patent Application No. 20200100488, entitled “CONFIGURATIONS FOR CHANNELSTATE FEEDBACK”, filed on August 18, 2020 and assigned to the assignee of this application. The disclosure of this prior application is considered part of this patent application and is incorporated into this patent application by reference.

[0003] introduction

[0004] Aspects of the present disclosure relate generally to wireless communications, and to techniques and apparatus for channel state information reporting.

[0005] Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple access technologies that can support communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, time division synchronous code division multiple access (TD-SCDMA) systems, and long term evolution (LTE). LTE / LTE-Advanced is a set of enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard promulgated by the Third Generation Partnership Project (3GPP).

[0006] A wireless network may include several base stations (BSs) that can support communication for several user equipments (UEs). The UE may communicate with the BS via a downlink and an uplink. The downlink (or forward link) refers to the communication link from the BS to the UE, while the uplink (or reverse link) refers to the communication link from the UE to the BS. As will be described in more detail herein, the BS may be referred to as a Node B, a gNB, an Access Point (AP), a Radio Head, a Transmit Receiving Point (TRP), a New Radio (NR) BS, a 5G Node B, and the like.

[0007] The above multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different UEs to communicate at city, country, region, and even global levels. NR (which may also be referred to as 5G) is an enhancement set to the LTE mobile standard promulgated by 3GPP. NR is designed to better support mobile broadband Internet access by improving spectrum efficiency, reducing costs, improving services, utilizing new spectrum, and using orthogonal frequency division multiplexing (OFDM) (CP-OFDM) with cyclic prefix (CP) on the downlink (DL), using CP-OFDM and / or SC-FDM (e.g., also known as discrete Fourier transform spread OFDM (DFT-s-OFDM) on the uplink (UL), and supporting beamforming, multiple input multiple output (MIMO) antenna technology and carrier aggregation. Other open standards are better integrated to better support mobile broadband Internet access. However, as the demand for mobile broadband access continues to grow, there is a need for further improvements in LTE and NR technologies. Preferably, these improvements should be applicable to other multiple access technologies and telecommunication standards that adopt these technologies.

[0008] Overview

[0009] In some aspects, a method of performing wireless communications by a first device includes receiving a channel state information (CSI) feedback configuration. The CSI feedback configuration includes an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period. The method also includes transmitting a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0010] In some aspects, a method of performing wireless communications by a first device includes: receiving a CSI feedback configuration. The CSI feedback configuration includes an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI. The method includes: transmitting the first CSF; and refraining from transmitting the second CSF based at least in part on the CSI feedback configuration.

[0011] In some aspects, a method of performing wireless communications by a second device includes transmitting a CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. The method includes receiving a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0012] In some aspects, a method of performing wireless communications by a second device includes transmitting a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI. The method includes receiving the first CSF.

[0013] In some aspects, a first device for wireless communication includes: a memory; and one or more processors coupled to the memory. The memory and the one or more processors are configured to: receive a CSI feedback configuration, the CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. The memory and the one or more processors may be configured to: transmit a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0014] In some aspects, a first device for wireless communication includes: a memory; and one or more processors coupled to the memory. The memory and the one or more processors are configured to: receive a CSI feedback configuration, the CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI. The memory and the one or more processors may transmit the first CSF; and refrain from transmitting the second CSF based at least in part on the CSI feedback configuration.

[0015] In some aspects, a second device for wireless communication includes: a memory and one or more processors coupled to the memory. The memory and the one or more processors are configured to: transmit a CSI feedback configuration, the CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. The memory and the one or more processors may receive a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0016] In some aspects, a second device for wireless communication includes: a memory and one or more processors coupled to the memory. The memory and the one or more processors are configured to: transmit a CSI feedback configuration, the CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first channel state feedback CSF including neural network-based CSI. The memory and the one or more processors may be configured to: receive the first CSF.

[0017] In some aspects, a non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set including one or more instructions that, when executed by one or more processors of a first device, causes the first device to: receive a CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. The one or more instructions also cause the first device to: transmit a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0018] In some aspects, a non-transitory computer-readable medium stores an instruction set for wireless communication, the instruction set including one or more instructions that, when executed by one or more processors of a first device, causes the first device to: receive a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI. The one or more instructions cause the first device to: transmit the first CSF; and refrain from transmitting the second CSF based at least in part on the CSI feedback configuration.

[0019] In some aspects, a non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set including one or more instructions that, when executed by one or more processors of a second device, causes the second device to: transmit a CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. The one or more instructions cause the second device to: receive a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0020] In some aspects, a non-transitory computer-readable medium stores an instruction set for wireless communication, the instruction set including one or more instructions that, when executed by one or more processors of a second device, causes the second device to: transmit a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI. The one or more instructions cause the second device to: receive the first CSF.

[0021] In some aspects, an apparatus for wireless communication includes: means for receiving a CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. The apparatus includes means for transmitting a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0022] In some aspects, an apparatus for wireless communication includes: means for receiving a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI. The apparatus includes means for transmitting the first CSF; and means for refraining from transmitting the second CSF based at least in part on the CSI feedback configuration.

[0023] In some aspects, an apparatus for wireless communication includes: means for transmitting a CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. The apparatus also includes means for receiving a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0024] In some aspects, an apparatus for wireless communication includes: means for transmitting a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI. The apparatus includes means for receiving the first CSF.

[0025] Aspects generally include methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, wireless communication devices, and / or processing systems as substantially described with reference to and as illustrated in the accompanying drawings and specification.

[0026] The foregoing has broadly outlined the features and technical advantages of examples according to the present disclosure in an effort to make the following detailed description better understood. Additional features and advantages will be described hereinafter. The disclosed concepts and specific examples can be easily used as a basis for modifying or designing other structures for implementing the same purpose as the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, both in terms of their organization and method of operation, and the associated advantages will be better understood by considering the following description in conjunction with the accompanying drawings. Each of the accompanying drawings is provided for illustration and description purposes and does not define limitations on the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to understand the above-stated features of the present disclosure in detail, the above briefly summarized content may be described in more detail with reference to various aspects, some of which are illustrated in the accompanying drawings. However, it should be noted that the accompanying drawings only illustrate certain typical aspects of the present disclosure and should not be considered to limit its scope, as the description may allow for other equally effective aspects. The same reference numerals in different drawings may identify the same or similar elements.

[0029] Figure 1 is a diagram illustrating an example of a wireless network according to the present disclosure.

[0030] Figure 2 is a diagram illustrating an example in which a base station and a user equipment (UE) are in communication in a wireless network according to the present disclosure.

[0031] Figure 3 is a diagram illustrating an example of an encoding apparatus and a decoding apparatus using previously stored channel state information according to the present disclosure.

[0032] Figure 4 is a diagram illustrating an example associated with an encoding device and a decoding device according to the present disclosure.

[0033] Figure 5-8 is a diagram illustrating an example associated with using a neural network to encode and decode a data set for uplink communication according to the present disclosure.

[0034] Fig. 9 is a diagram illustrating an example associated with a configuration for providing channel state feedback (CSF) using a neural network according to the present disclosure.

[0035] Figure 10-13 is a diagram illustrating an example associated with a configuration for providing a CSF using a neural network according to the present disclosure.

[0036] Fig.14 and 15 is an example of an apparatus for wireless communication according to the present disclosure.

[0037] Fig.16 and 17 is a diagram illustrating an example of a hardware implementation for an apparatus employing a processing system.

[0038] Fig.18 and 19 is a diagram illustrating an example of an implementation of code and circuitry for an apparatus.

[0039] Fig. 20 and 21 is a diagram illustrating an example process associated with using a neural network to encode a data set for uplink communication in accordance with the present disclosure.

[0040] Detailed Description

[0041] A coding device operating in a network may measure reference signals, etc., to report to a network entity. For example, the coding device may measure reference signals during a beam management process to implement channel state feedback (CSF), may measure the received power of reference signals from a serving cell and / or a neighbor cell, may measure signal strength of an inter-radio access technology (e.g., WiFi) network, may measure sensor signals for detecting the location of one or more objects within an environment, etc. However, reporting such information to a base station may consume communication and / or network resources.

[0042] In some aspects described herein, a coding device (e.g., a UE, a base station, a transmit reception point (TRP), a network device, a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc.) may train one or more neural networks to learn the dependence of measured qualities on individual parameters, isolate these measured qualities through various layers (also referred to as "operations") of the one or more neural networks, and compress the measurements in a manner that limits compression losses. In some aspects, the coding device may use the properties of the number of bits being compressed to construct a process for extracting and compressing each feature (also referred to as a dimension) that affects the number of bits. In some aspects, the number of bits may be associated with sampling of one or more reference signals and / or may indicate channel state information. For example, the coding device may encode the measurements using one or more extraction operations and compression operations associated with the neural network to produce compressed measurements, wherein the one or more extraction operations and compression operations are based at least in part on a set of features of the measurements.

[0043] The encoding device may transmit the compressed measurements to a network entity such as a server, a TRP, another UE, a base station, etc. Although the examples described herein cite a base station as a decoding device, the decoding device may be any network entity. A network entity may be referred to as a "decoding device".

[0044] The decoding device may decode the compressed measurement using one or more decompression operations and reconstruction operations associated with the neural network. The one or more decompression and reconstruction operations may be based at least in part on a feature set of the compressed data set to produce a reconstructed measurement. The decoding device may use the reconstructed measurement as channel state information feedback.

[0045] As described herein, a coding device operating in a network may measure a reference signal, etc., to report to a decoding device. For example, a coding device may receive a neural network-based channel state information (CSI) reference signal (CSI-RS). The coding device may measure the neural network-based CSI based at least in part on the CSI-RS. The neural network-based CSI may include any number of different features, characteristics, etc. The neural network-based CSI may compress the channel information associated with the CSI-RS in a more comprehensive form than, for example, type-II CSI or type-I CSI. Type I CSI is a beam selection scheme in which the coding device selects the best beam index and sends the CSI information to the decoding device. Type II CSI is a beam combining scheme in which the coding device also calculates the best linear combination of coefficients of various beams on a subband basis (e.g., configured subbands) and sends back the beam index and coefficients for combining beams. For example, in type II CSI, the subband size may be fixed for all subbands, which results in a limited granularity. The neural network-based CSI may facilitate greater granularity by facilitating the provision of information about the entire channel. Neural network based CSI may also be specified to compress certain subbands with higher or lower accuracy.

[0046] In some aspects, neural network-based CSI may also facilitate multi-user (MU) multiple-input multiple-output (MU-MIMO) operations at a decoding device by facilitating provision of information about channels and interference, thereby enabling the decoding device to manage and group users, etc. Reporting CSF based on machine learning may facilitate the use of neural network-based CSI, more robust type-II CSI, etc. However, in a typical scenario, one type of CSI feedback may be scheduled and / or requested shortly after the encoding device has transmitted the same type or another type of CSI feedback. As a result, signaling overhead for transmission of redundant information may be increased, which may reduce efficiency and uplink resource availability.

[0047] According to various aspects of the technology and equipment described herein, the coding device may be configured to save a CSF corresponding to a first reference signal within a specified time period. The coding device may use the saved CSF to facilitate the transmission of a differential CSF, which is based at least in part on a second reference signal. In some aspects, the coding device may be configured to suppress the transmission of an additional CSF within a specified time period after transmitting a neural network-based CSF. In some aspects, a neural network may be used to compress and encode channel information and interference information to provide a robust CSF so that the information sent in the initial CSF may be sufficient within a specified time period, or so that the information may be supplemented by a differential CSF instead of a full CSF transmission. As a result, the various aspects described herein can facilitate the reduction of uplink traffic overhead, thereby increasing uplink resource availability while providing a robust CSI to a decoding device to facilitate traffic management. Various aspects of the present disclosure are described more fully below with reference to the accompanying drawings. However, the present disclosure may be implemented in many different forms and should not be interpreted as being limited to any specific structure or function given throughout the present disclosure. On the contrary, these aspects are provided to make the present disclosure thorough and complete, and they will fully convey the scope of the present disclosure to those skilled in the art. Based on the teachings herein, those skilled in the art will appreciate that the scope of the present disclosure is intended to cover any aspect of the present disclosure disclosed herein, whether it is implemented independently of any other aspect of the present disclosure or implemented in combination. For example, any number of aspects set forth herein may be used to implement a device or practice method. In addition, the scope of the present disclosure is intended to cover such devices or methods practiced using supplements or other other structures, functionality, or structures and functionality as the various aspects of the present disclosure set forth herein. It should be understood that any aspect of the present disclosure disclosed herein may be implemented by one or more elements of the claims.

[0048] Several aspects of telecommunication systems will now be presented with reference to various devices and techniques. These devices and techniques will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented using hardware, software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0049] It should be noted that while various aspects may be described herein using terminology generally associated with 5G or new radio (NR) radio access technology (RAT), various aspects of the present disclosure may be applied to other RATs, such as 3G RAT, 4G RAT, and / or RATs beyond 5G (e.g., 6G).

[0050] Figure 11 is a diagram illustrating an example of a wireless network 100 according to the present disclosure. The wireless network 100 may be a 5G (NR) network and / or an LTE network, etc. or may include elements thereof. The wireless network 100 may include several base stations 110 (shown as BS110a, BS 110b, BS 110c, and BS 110d) and other network entities. A base station (BS) is an entity that communicates with a user equipment (UE) and may also be referred to as an NR BS, a B node, a gNB, a 5G B node (NB), an access point, a transmission reception point (TRP), etc. Each BS may provide communication coverage for a specific geographic area. In 3GPP, the term "cell" may refer to a coverage area of ​​a BS and / or a BS subsystem serving the coverage area, depending on the context in which the term is used.

[0051] A BS may provide communication coverage for a macro cell, a pico cell, a femto cell, and / or another type of cell. A macro cell may cover a relatively large geographic area (e.g., several kilometers in radius) and may allow unrestricted access by UEs with service subscriptions. A pico cell may cover a relatively small geographic area and may allow unrestricted access by UEs with service subscriptions. A femto cell may cover a relatively small geographic area (e.g., a residence) and may allow restricted access by UEs associated with the femto cell (e.g., UEs in a closed subscriber group (CSG)). A BS for a macro cell may be referred to as a macro BS. A BS for a pico cell may be referred to as a pico BS. A BS for a femto cell may be referred to as a femto BS or a home BS. In Figure 1 In the example shown in , BS 110a may be a macro BS for macro cell 102a, BS 110b may be a pico BS for pico cell 102b, and BS 110c may be a femto BS for femto cell 102c. A BS may support one or more (e.g., three) cells. The terms "eNB", "base station", "NR BS", "gNB", "TRP", "AP", "B node", "5G NB", and "cell" may be used interchangeably herein.

[0052] In some examples, the cell may not necessarily be stationary, and the geographic area of ​​the cell may move depending on the location of the mobile BS. In some examples, the BSs may be interconnected to each other and / or to one or more other BSs or network nodes (not shown) in the wireless network 100 via various types of backhaul interfaces, such as direct physical connections or virtual networks, using any suitable transport network.

[0053] The wireless network 100 may also include a relay station. A relay station is an entity that can receive transmissions of data from an upstream station (e.g., a BS or a UE) and send transmissions of the data to a downstream station (e.g., a UE or a BS). A relay station may also be a UE that can relay transmissions for other UEs. Figure 1 In the example shown in , relay BS 110d may communicate with macro BS 110a and UE 120d to facilitate communication between BS 110a and UE 120d. A relay BS may also be referred to as a relay station, relay base station, relay, or the like.

[0054] In some aspects, the wireless network 100 may include one or more non-terrestrial network (NTN) deployments, where non-terrestrial wireless communication devices may include UEs (interchangeably referred to herein as "non-terrestrial UEs"), BSs (interchangeably referred to herein as "non-terrestrial BSs" and "non-terrestrial base stations"), relay stations (interchangeably referred to herein as "non-terrestrial relay stations"), etc. As used herein, "NTN" may refer to a network to which access is facilitated by non-terrestrial UEs, non-terrestrial BSs, non-terrestrial relay stations, etc.

[0055] The wireless network 100 may include any number of non-terrestrial wireless communication devices. The non-terrestrial wireless communication devices may include satellites, unmanned aircraft system (UAS) platforms, and the like. Satellites may include low earth orbit (LEO) satellites, medium earth orbit (MEO) satellites, geostationary orbit (GEO) satellites, high elliptical orbit (HEO) satellites, and the like. UAS platforms may include high altitude platform stations (HAPS), and may include balloons, airships, airplanes, and the like. The non-terrestrial wireless communication devices may be part of an NTN that is separate from the wireless network 100. Alternatively, the NTN may be part of the wireless network 100. The satellite may communicate directly and / or indirectly with other entities in the wireless network 100 using satellite communications. Other entities may include UEs (e.g., terrestrial UEs and / or non-terrestrial UEs), other satellites in one or more NTN deployments, other types of BSs (e.g., stationary or ground-based BSs), relay stations, one or more components and / or devices included in the core network of the wireless network 100, and the like.

[0056] The wireless network 100 may be a heterogeneous network including different types of BSs, such as a macro BS, a pico BS, a femto BS, a relay BS, etc. These different types of BSs may have different transmit power levels, different coverage areas, and different effects on interference in the wireless network 100. For example, a macro BS may have a high transmit power level (e.g., 5 to 40 watts), while a pico BS, a femto BS, and a relay BS may have a lower transmit power level (e.g., 0.1 to 2 watts).

[0057] A network controller 130 may be coupled to a set of BSs and may provide coordination and control of these BSs. The network controller 130 may communicate with each BS via a backhaul. The BSs may also communicate with each other directly or indirectly, for example, via a wireless or wired backhaul.

[0058] UE 120 (e.g., 120a, 120b, 120c) may be dispersed throughout the wireless network 100, and each UE may be stationary or mobile. UE may also be referred to as an access terminal, terminal, mobile station, subscriber unit, station, etc. UE may be a cellular phone (e.g., a smart phone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device or equipment, a biometric sensor / device, a wearable device (smart watch, smart clothing, smart glasses, smart wristband, smart jewelry (e.g., smart ring, smart bracelet)), an entertainment device (e.g., a music or video device, or a satellite radio), a vehicle component or sensor, a smart meter / sensor, an industrial manufacturing equipment, a global positioning system device, or any other suitable device configured to communicate via a wireless or wired medium.

[0059] Some UEs may be considered as machine type communication (MTC) devices, or evolved or enhanced machine type communication (eMTC) UEs. MTC and eMTC UEs include, for example, robots, drones, remote devices, sensors, meters, monitors, and / or location tags, which may communicate with a base station, another device (e.g., a remote device), or some other entity. A wireless node may provide connectivity to or to a network (e.g., a wide area network, such as the Internet or a cellular network) via, for example, a wired or wireless communication link. Some UEs may be considered as Internet of Things (IoT) devices, and / or may be implemented as NB-IoT (narrowband Internet of Things) devices. Some UEs may be considered as client equipment (CPE). UE 120 may be included inside a housing that houses components of UE 120, such as a processor component and / or a memory component. In some aspects, a processor component and a memory component may be coupled together. For example, a processor component (e.g., one or more processors) and a memory component (e.g., a memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0060] In general, any number of wireless networks may be deployed in a given geographic area. Each wireless network may support a specific RAT and may operate on one or more frequencies. RAT may also be referred to as radio technology, air interface, etc. Frequency may also be referred to as carrier, frequency channel, etc. Each frequency may support a single RAT in a given geographic area to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks may be deployed.

[0061] In some aspects, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly (e.g., without using base station 110 as an intermediary to communicate with each other) using one or more side link channels. For example, UE 120 may communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols or vehicle-to-infrastructure (V2I) protocols), and / or mesh networks. In some aspects, UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by base station 110.

[0062] The devices of the wireless network 100 may communicate using an electromagnetic spectrum that may be subdivided into various categories, bands, channels, etc. based on frequency or wavelength. For example, the devices of the wireless network 100 may communicate using an operating band having a first frequency range (FR1) and / or may communicate using an operating band having a second frequency range (FR2), the first frequency range (FR1) may span 410 MHz to 7.125 GHz, and the second frequency range (FR2) may span 24.25 GHz to 52.6 GHz. Frequencies between FR1 and FR2 are sometimes referred to as mid-band frequencies. Although a portion of FR1 is greater than 6 GHz, FR1 is often referred to as a "sub-6 GHz band". Similarly, FR2 is often referred to as a "millimeter wave" band, although it is different from the extremely high frequency (EHF) band (30 GHz–300 GHz) identified as a "millimeter wave" band by the International Telecommunication Union (ITU). Thus, unless otherwise specifically stated, it should be understood that the term sub-"6 GHz" and the like, if used herein, may broadly refer to frequencies less than 6 GHz, frequencies within FR1, and / or mid-band frequencies (e.g., greater than 7.125 GHz). Similarly, unless otherwise specifically stated, it should be understood that the term "millimeter wave" and the like, if used herein, may broadly refer to frequencies within the EHF band, frequencies within FR2, and / or mid-band frequencies (e.g., less than 24.25 GHz). It is contemplated that the frequencies included in FR1 and FR2 may be modified, and that the techniques described herein are applicable to those modified frequency ranges.

[0063] like Figure 1 As shown in , UE 120 may include a communication manager 140. As described in more detail elsewhere herein, the communication manager 140 may receive a channel state information (CSI) feedback configuration, the CSI feedback configuration including an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; and transmit a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel. In some aspects, the communication manager 140 may receive a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI; transmit the first CSF; and refrain from transmitting the second CSF based at least in part on the CSI feedback configuration. Additionally or alternatively, the communication manager 140 may perform one or more other operations described herein.

[0064] In some aspects, base station 110 may include communication manager 150. As described in greater detail elsewhere herein, communication manager 150 may transmit a CSI feedback configuration including an indication to preserve a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period; and receive a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel. In some aspects, communication manager 150 may transmit a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI; and receive the first CSF. Additionally or alternatively, communication manager 150 may perform one or more other operations described herein.

[0065] As indicated above, Figure 1 This is provided as an example only. Other examples may differ from those described herein. Figure 1 Examples described.

[0066] Figure 2 is a diagram illustrating an example 200 of a base station 110 and a UE 120 in communication in a wireless network 100 according to the present disclosure. The base station 110 may be equipped with T antennas 234a through 234t, and the UE 120 may be equipped with R antennas 252a through 252r, where in general T≥1 and R≥1.

[0067] At the base station 110, the transmit processor 220 may receive data for one or more UEs from the data source 212, select one or more modulation and coding schemes (MCS) for each UE based at least in part on a channel quality indicator (CQI) received from the UE, process (e.g., encode and modulate) the data for the UE based at least in part on the MCS selected for each UE, and provide data symbols for all UEs. The transmit processor 220 may also process system information (e.g., for semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper layer signaling), and provide overhead symbols and control symbols. The transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS) or demodulation reference signals (DMRS)) and synchronization signals (e.g., primary synchronization signals (PSS) or secondary synchronization signals (SSS)). A transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., precoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols, where applicable, and may provide T output symbol streams to T modulators (MODs) 232a through 232t. Each modulator 232 may process a respective output symbol stream (e.g., for OFDM) to obtain an output sample stream. Each modulator 232 may further process (e.g., convert to analog, amplify, filter, and upconvert) the output sample stream to obtain a downlink signal. The T downlink signals from modulators 232a through 232t may be transmitted via T antennas 234a through 234t, respectively.

[0068] At UE 120, antennas 252a to 252r may receive downlink signals from base station 110 and / or other base stations and may provide received signals to demodulators (DEMODs) 254a to 254r, respectively. Each demodulator 254 may condition (e.g., filter, amplify, downconvert, and digitize) the received signal to obtain input samples. Each demodulator 254 may further process the input samples (e.g., for OFDM) to obtain received symbols. A MIMO detector 256 may obtain received symbols from all R demodulators 254a to 254r, perform MIMO detection on the received symbols where applicable, and provide detected symbols. A receive processor 258 may process (e.g., demodulate and decode) the detected symbols, provide decoded data for UE 120 to a data sink 260, and provide decoded control information and system information to a controller / processor 280. The term "controller / processor" may refer to one or more controllers, one or more processors, or a combination thereof. The channel processor may determine a reference signal received power (RSRP) parameter, a received signal strength indicator (RSSI) parameter, a reference signal received quality (RSRQ) parameter, and / or a CQI parameter.In some aspects, one or more components of UE 120 may be included in a housing.

[0069] The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292. The network controller 130 may include, for example, one or more devices in a core network. The network controller 130 may communicate with the base station 110 via the communication unit 294.

[0070] Antennas (e.g., antennas 234a to 234t and / or antennas 252a to 252r) may include, or may be included within, one or more antenna panels, antenna groups, antenna element sets, and / or antenna arrays, etc. Antenna panels, antenna groups, antenna element sets, and / or antenna arrays may include one or more antenna elements. Antenna panels, antenna groups, antenna element sets, and / or antenna arrays may include coplanar antenna element sets and / or non-coplanar antenna element sets. Antenna panels, antenna groups, antenna element sets, and / or antenna arrays may include antenna elements within a single housing and / or antenna elements within multiple housings. Antenna panels, antenna groups, antenna element sets, and / or antenna arrays may include antenna elements coupled to one or more transmission and / or reception components (such as Figure 2 One or more antenna elements of one or more components).

[0071] On the uplink, at the UE 120, a transmit processor 264 may receive and process data from a data source 262 and control information (e.g., for reports including RSRP, RSSI, RSRQ, and / or CQI) from a controller / processor 280. The transmit processor 264 may also generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be precoded by a TX MIMO processor 266, where applicable, further processed by modulators 254a through 254r (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to the base station 110. In some aspects, the modulator and demodulator (e.g., MOD / DEMOD 254) of the UE 120 may be included in a modem of the UE 120. In some aspects, the UE 120 includes a transceiver. The transceiver may include any combination of antenna(s) 252, modulator and / or demodulator 254, MIMO detector 256, receive processor 258, transmit processor 264, and / or TX MIMO processor 266. The transceiver may be used by a processor (e.g., controller / processor 280) and memory 282 to perform aspects of any of the methods described herein.

[0072] At the base station 110, uplink signals from the UE 120 and other UEs may be received by the antenna 234, processed by the demodulator 232, detected by the MIMO detector 236 where applicable, and further processed by the receive processor 238 to obtain decoded data and control information sent by the UE 120. The receive processor 238 may provide the decoded data to the data sink 239 and the decoded control information to the controller / processor 240. The base station 110 may include a communication unit 244 and communicate with the network controller 130 via the communication unit 244. The base station 110 may include a scheduler 246 to schedule the UE 120 for downlink and / or uplink communications. In some aspects, the modulator and demodulator (e.g., MOD / DEMOD 232) of the base station 110 may be included in a modem of the base station 110. In some aspects, the base station 110 includes a transceiver. The transceiver may include any combination of antenna(s) 234, modulator and / or demodulator 232, MIMO detector 236, receive processor 238, transmit processor 220, and / or TX MIMO processor 230. The transceiver may be used by a processor (e.g., controller / processor 240) and memory 242 to perform aspects of any of the methods described herein.

[0073] The controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2Any other component(s) of the base station 110 may perform one or more techniques associated with configuration for providing channel state feedback (CSF), as described in more detail elsewhere herein. For example, the controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2 Any other component of the Fig.10 The process of 1000 Fig.11 Process 1100, Fig.12 The process 1200 Fig.13 1300, and / or operations of other processes as described herein. Memories 242 and 282 may store data and program codes for base station 110 and UE 120, respectively. In some aspects, memory 242 and / or memory 282 may include: a non-transitory computer-readable medium storing one or more instructions (e.g., code, program code, etc.) for wireless communication. For example, the one or more instructions, when executed (e.g., directly, or after compilation, conversion, interpretation, etc.) by one or more processors of base station 110 and / or UE 120, may cause the one or more processors, UE 120, and / or base station 110 to perform or direct, for example Fig.10 The process of 1000 Fig.11 Process 1100, Fig.12 The process 1200 Fig.13 In some aspects, executing instructions may include running instructions, converting instructions, compiling instructions, and / or interpreting instructions, among other things.

[0074] In some aspects, UE 120 may include: means for receiving a CSI feedback configuration, the CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period; means for transmitting a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel; etc. In some aspects, UE 120 may include: means for receiving a CSI feedback configuration, the CSI feedback configuration including an indication to suppress transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI; means for transmitting the first CSF; means for suppressing transmitting the second CSF based at least in part on the CSI feedback configuration; etc. Additionally or alternatively, UE 120 may include means for performing one or more other operations described herein. In some aspects, such means may include a communications manager 140. Additionally or alternatively, such means may include in conjunction with Figure 2One or more other components of the UE 120 are depicted, such as a controller / processor 280, a transmit processor 264, a TX MIMO processor 266, a MOD 254, an antenna 252, a DEMOD 254, a MIMO detector 256, a receive processor 258, and the like.

[0075] In some aspects, the base station 110 may include: means for transmitting a CSI feedback configuration, the CSI feedback configuration including an indication to preserve a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period; means for receiving a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel; etc. In some aspects, the base station 110 may include: means for transmitting a CSI feedback configuration, the CSI feedback configuration including an indication to suppress transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI; means for receiving the CSF; etc. Additionally or alternatively, the base station 110 may include means for performing one or more other operations described herein. In some aspects, such means may include a communications manager 150. In some aspects, such means may include in combination Figure 2 One or more other components of the base station 110 are depicted, such as antenna 234, DEMOD 232, MIMO detector 236, receive processor 238, controller / processor 240, transmit processor 220, TX MIMO processor 230, MOD 232, antenna 234, and the like.

[0076] although Figure 2 The blocks in the 200 and 210 are illustrated as distinct components, but the functions described above with respect to these blocks may be implemented using a single hardware, software, or combined component or a combination of various components. For example, the functions described with respect to the transmit processor 264, the receive processor 258, and / or the TX MIMO processor 266 may be performed by or under the control of the controller / processor 280.

[0077] As indicated above, Figure 2 This is provided as an example only. Other examples may differ from those described herein. Figure 2 Examples described.

[0078] Figure 3 An example of an encoding device 300 and a decoding device 350 using previously stored channel state information (CSI) according to the present disclosure is illustrated. Figure 3 An encoding device 300 (eg, UE 120 ) having a CSI instance encoder 310 , a CSI sequence encoder 320 , and a memory 330 is shown. Figure 3Also shown is a decoding device 350 (eg, BS 110) having a CSI sequence decoder 360, a memory 370, and a CSI instance decoder 380.

[0079] In some aspects, the encoding device 300 and the decoding device 350 may utilize the correlation of CSI instances over time (temporal aspect) or a sequence of CSI instances to perform a series of channel estimates. The encoding device 300 and the decoding device 350 may save and use previously stored CSI and only encode and decode CSI changes from previous instances. This may provide less CSI feedback overhead and improve performance. The encoding device 300 may also be able to encode more accurate CSI, and the neural network may be trained with more accurate CSI.

[0080] like Figure 3 As shown in , the CSI instance encoder 310 may encode the CSI instance into an intermediate coded CSI for each DL channel estimate in the DL channel estimate sequence. The CSI instance encoder 310 (eg, a feed-forward network) may use a neural network encoder weight θ. The intermediate coded CSI may be represented as The CSI sequence encoder 320 (e.g., a long short-term memory (LSTM) network) may determine a previously encoded CSI instance h(t-1) from the memory 330 and compare the intermediate encoded CSI m(t) with the previously encoded CSI instance h(t-1) to determine a change n(t) in the encoded CSI. The change n(t) may be a portion of the channel estimate that is new and may not have been predicted by the decoding device 350. The encoded CSI at this point may be Representation. The CSI sequence encoder 320 may provide the change n(t) on a physical uplink shared channel (PUSCH) or a physical uplink control channel (PUCCH), and the encoding device may transmit the change (e.g., information indicating the change) n(t) as encoded CSI to the decoding device 350 on a UL channel. Because the change is smaller than the entire CSI instance, the encoding device 300 may send a smaller payload for the encoded CSI on the UL channel while including more detailed information about the change in the encoded CSI. The CSI sequence encoder 320 may generate the encoded CSI h(t) based at least in part on the intermediate encoded CSI m(t) and at least a portion of the previously encoded CSI instance h(t-1). The CSI sequence encoder 320 may save the encoded CSI h(t) in the memory 330.

[0081] The CSI sequence decoder 360 may receive the encoded CSI on the PUSCH or PUCCH. The CSI sequence decoder 360 may determine that only a change n(t) of the CSI is received as the encoded CSI. The CSI sequence decoder 360 may determine the intermediate encoded CSI m(t) based at least in part on the encoded CSI and at least a portion of a previous intermediate encoded CSI instance h(t-1) from the memory 370 and the change. The CSI instance decoder 380 may decode the intermediate decoded CSI m(t) into decoded CSI. The CSI sequence decoder 360 and the CSI instance decoder 380 may use the neural network decoder weights φ. The intermediate decoded CSI may be determined by The CSI sequence decoder 360 may generate a decoded CSI h(t) based at least in part on the intermediate decoded CSI m(t) and at least a portion of the previously decoded CSI instance h(t-1). The decoding device 350 may reconstruct a DL channel estimate from the decoded CSI h(t), and the reconstructed channel estimate may be represented as The CSI sequence decoder 360 may store the decoded CSI h(t) in the memory 370 .

[0082] Because the change n(t) is less than the entire CSI instance, the encoding device 300 can send a smaller payload on the UL channel. For example, if the DL channel has little change from the previous feedback due to the low Doppler or less movement of the encoding device 300, the output of the CSI sequence encoder can be quite compact. In this way, the encoding device 300 can take advantage of the correlation of the channel estimate over time. In some aspects, because the output is small, the encoding device 300 can include more detailed information about the change in the encoded CSI. In some aspects, the encoding device 300 may transmit an indication (e.g., a flag) about the encoded CSI being encoded in time (CSI change) to the decoding device 350. Alternatively, the encoding device 300 may transmit an indication that the encoded CSI is encoded independently of any previously encoded CSI feedback. The decoding device 350 can decode the encoded CSI without using a previously decoded CSI instance. In some aspects, a device (which may include the encoding device 300 or the decoding device 350) can use a CSI sequence encoder and a CSI sequence decoder to train a neural network model.

[0083] In some aspects, CSI may be a function of a channel estimate (referred to as a channel response) H and interference N. There may be a variety of ways to convey H and N. For example, encoding device 300 may encode CSI as N -1 / 2H. The encoding device 300 may encode H and N separately. The encoding device 300 may partially encode H and N separately, and then jointly encode the two partially encoded outputs. It may be advantageous to encode H and N separately. Interference and channel variations may occur on different time scales. In low Doppler scenarios, the channel may be stable, but interference may still change faster due to traffic or scheduler algorithms. In high Doppler scenarios, the channel may change faster than the scheduler grouping of the UE. In some aspects, a device (which may include the encoding device 300 or the decoding device 350) may use separately encoded H and N to train a neural network model.

[0084] In some aspects, the reconstructed DL channel The DL channel H may be reflected truthfully, and this may be referred to as explicit feedback. In some aspects, Only the information required for the decoding device 350 to derive the rank and precoding may be captured. CQI may be fed back separately. In a time-coded scenario, CSI feedback may be expressed as m(t) or n(t). Similar to type-II CSI feedback, m(t) may be constructed as a concatenation of a rank index (RI), a beam index, and a coefficient representing an amplitude or phase. In some aspects, m(t) may be a quantized version of a real-valued vector. The beam may be predefined (not obtained through training), or may be part of the training (e.g., part of θ and φ and communicated to the encoding device 300 or the decoding device 350).

[0085] In some aspects, the decoding device 350 and the encoding device 300 may maintain multiple encoder and decoder networks, each targeting a different payload size (to achieve a different accuracy-to-UL overhead tradeoff). For each CSI feedback, depending on the reconstruction quality and the uplink budget (e.g., PUSCH payload size), the encoding device 300 may select or the decoding device 350 may instruct the encoding device 300 to select one of the encoders to construct the encoded CSI. The encoding device 300 may send an index of the encoder and the CSI based at least in part on the encoder selected by the encoding device 300. Similarly, the decoding device 350 and the encoding device 300 may maintain multiple encoder and decoder networks to cope with different antenna geometries and channel conditions. Note that although some operations are described with respect to the decoding device 350 and the encoding device 300, these operations may also be performed by another device as part of the preconfiguration of the encoder and decoder weights and / or structures.

[0086] As indicated above, Figure 3 Other examples may differ from those provided for Figure 3 Examples described.

[0087] Figure 44 is a diagram illustrating an example 400 associated with an encoding device and a decoding device according to the present disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on data to compress the data. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed data to determine information.

[0088] As used herein, a "layer" of a neural network is used to represent an operation on input data. For example, a convolutional layer, a fully connected layer, etc. represent associated operations on the data input into the layer. A convolution AxB operation refers to an operation that converts several input features A into several output features B. "Kernel size" refers to the number of adjacent coefficients that are combined in one dimension.

[0089] As used herein, "weights" are used to refer to one or more coefficients used in operations for combining individual rows and / or columns of input data in each layer. For example, a fully connected layer operation may have an output y that is determined at least in part based on the product of the input matrix x and the weight A (which may be a matrix) and the sum of the bias value B (which may be a matrix). The term "weight" may be used herein to refer generally to both weights and bias values.

[0090] As shown in example 400, the encoding device may perform a convolution operation on the samples. For example, the encoding device may receive a set of bits structured as a 2x64x32 data set, which indicates IQ samples for tap features (e.g., associated with multipath timing offsets) and spatial features (e.g., associated with different antennas of the encoding device). The convolution operation may be a 2x2 operation with kernel sizes of 3 and 3 for the data structure. The output of the convolution operation may be input to a batch normalization (BN) layer, followed by a LeakyReLu activation, thereby giving an output data set with a size of 2x64x32. The encoding device may perform a flattening operation to flatten the bits into a 4096-bit vector. The encoding device may apply a fully connected operation with a size of 4096xM to a 4096-bit vector to output an M-bit payload. The encoding device may transmit an M-bit payload to a decoding device.

[0091] The decoding device may apply a fully connected operation with size Mx4096 to the M-bit payload to output a 4096-bit vector. The decoding device may reshape the 4096-bit vector to have size 2x64x32. The decoding device may apply one or more RefineNet operations to the reshaped bit vector. For example, the RefineNet operation may include: applying a 2x8 convolution operation (e.g., with kernel sizes of 3 and 3), whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output data set having a size of 8x64x32; applying an 8x16 convolution operation (e.g., with kernel sizes of 3 and 3), whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output data set having a size of 16x64x32; and / or applying a 16x2 convolution operation (e.g., with kernel sizes of 3 and 3), whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output data set having a size of 2x64x32. The decoding device may also apply a 2x2 convolution operation with kernel sizes of 3 and 3 to generate a decoded and / or reconstructed output.

[0092] As indicated above, Figure 4 This is provided as an example only. Other examples may differ from those described herein. Figure 4 Examples described.

[0093] As described herein, a coding device operating in a network may measure reference signals, etc., to report to a decoding device. For example, a UE may measure reference signals during a beam management process to report channel state feedback (CSF), may measure the received power of reference signals from a serving cell and / or a neighbor cell, may measure the signal strength of an inter-radio access technology (e.g., WiFi) network, may measure sensor signals for detecting the location of one or more objects within an environment, and the like.

[0094] In some aspects described herein, a coding device (e.g., a UE) may train one or more neural networks to learn the dependencies of measured qualities on individual parameters, isolate these measured qualities through various layers (also referred to as "operations") of the one or more neural networks, and compress the measurements in a manner that limits compression losses.

[0095] In some aspects, the encoding device may use the properties of the number of bits being compressed to construct a process for extracting and compressing each feature (also referred to as a dimension) that affects the number of bits. In some aspects, the number of bits may be associated with sampling of one or more reference signals and / or may indicate channel state information.

[0096] Based at least in part on using a neural network to encode and decode a data set for uplink communication, the encoding device can transmit the CSF with a reduced payload. This can save network resources that might otherwise have been used to transmit the full data set as sampled by the encoding device.

[0097] Figure 5 is a diagram illustrating an example 500 associated with using a neural network to encode and decode a data set for uplink communication according to the present disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information, such as a CSF.

[0098] In some aspects, the encoding device may identify features to be compressed. In some aspects, the encoding device may perform a first type of operation in a first dimension associated with the features to be compressed. The encoding device may perform a second type of operation in other dimensions (e.g., in all other dimensions). For example, the encoding device may perform a fully connected operation on a first dimension and perform convolution (e.g., point-by-point convolution) in all other dimensions.

[0099] In some aspects, reference numerals identify operations that include multiple neural network layers and / or operations. The neural networks of the encoding device and the decoding device may be formed by the concatenation of one or more of the recited operations.

[0100] As indicated by reference numeral 505, the encoding device may perform spatial feature extraction on the data. As indicated by reference numeral 510, the encoding device may perform tap domain feature extraction on the data. In some aspects, the encoding device may perform tap domain feature extraction before performing spatial feature extraction. In some aspects, the extraction operation may include multiple operations. For example, the multiple operations may include one or more convolution operations that may be activated or inactive, one or more fully connected operations, etc. In some aspects, the extraction operation may include a residual neural network (ResNet) operation.

[0101] As indicated by reference numeral 515, the encoding device may compress the one or more features that have been extracted. In some aspects, the compression operation may include one or more operations, such as one or more convolution operations, one or more fully connected operations, etc. After compression, the bit count of the output may be less than the bit count of the input.

[0102] As indicated by reference numeral 520, the encoding device may perform a quantization operation. In some aspects, the encoding device may perform the quantization operation after flattening the output of the compression operation and / or performing a fully connected operation after flattening the output.

[0103] As indicated by reference numeral 525, the encoding device may perform feature decompression. As indicated by reference numeral 530, the decoding device may perform tap domain feature reconstruction. As indicated by reference numeral 535, the decoding device may perform spatial feature reconstruction. In some aspects, the decoding device may perform spatial feature reconstruction before performing tap domain feature reconstruction. After the reconstruction operation, the decoding device may output a reconstructed version of the input of the encoding device.

[0104] In some aspects, the decoding device may perform operations in the reverse order of the operations performed by the encoding device. For example, if the encoding device follows the operation (a, b, c, d), the decoding device may follow the reverse operation (D, C, B, A). In some aspects, the decoding device may perform operations that are completely symmetrical to the operations of the encoding device. This can reduce the number of bits required for neural network configuration at the UE. In some aspects, the decoding device may perform additional operations in addition to the operations of the encoding device (e.g., convolution operations, fully connected operations, ResNet operations, etc.). In some aspects, the decoding device may perform operations that are asymmetrical to the operations of the encoding device.

[0105] Based at least in part on the use of a neural network by the coding device to encode a data set for uplink communication, the coding device (e.g., a UE) can transmit the CSF with a reduced payload. This can save network resources that might otherwise have been used to transmit the complete data set as sampled by the coding device.

[0106] As indicated above, Figure 5 This is provided as an example only. Other examples may differ from those described herein. Figure 5 Examples described.

[0107] Figure 6 6 is a diagram illustrating an example 600 associated with using a neural network to encode and decode a data set for uplink communication according to the present disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information, such as a CSF.

[0108] As shown by example 600, the encoding device may receive samples from the antennas. For example, the encoding device may receive a data set of size 64x64 based at least in part on the number of antennas, the number of samples per antenna, and the tap characteristics.

[0109] The encoding device may perform spatial feature extraction, short-time (tap) feature extraction, etc. In some aspects, this may be achieved using a 1-dimensional convolution operation that is fully connected in the spatial dimension (to extract spatial features) and a simple convolution with a small kernel size (e.g., 3) in the tap dimension (to extract short tap features). The output from this 64xW 1-dimensional convolution operation may be a Wx64 matrix.

[0110] The encoding device may perform one or more ResNet operations. The one or more ResNet operations may further refine the spatial features and / or the temporal features. In some aspects, the ResNet operation may include multiple operations associated with the features. For example, the ResNet operation may include multiple (e.g., 3) 1-dimensional convolution operations, skip connections (e.g., between the input of the ResNet and the output of the ResNet to avoid applying a 1-dimensional convolution operation), a summation operation of a path through multiple 1-dimensional convolution operations and a path through a skip connection, etc. In some aspects, the plurality of 1-dimensional convolution operations may include: a Wx256 convolution operation with a kernel size of 3, whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output data set of size 256x64; a 256x512 convolution operation with a kernel size of 3, whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output data set of size 512x64; a 512xW convolution operation with a kernel size of 3, whose output has a BN data set of size Wx64. The output from the one or more ResNet operations may be a Wx64 matrix.

[0111] The encoding device may perform a WxV convolution operation on the output from one or more ResNet operations. The WxV convolution operation may include a point-by-point (e.g., tap-by-tap) convolution operation. The WxV convolution operation may compress the spatial features into a reduced dimension for each tap. The WxV convolution operation has an input of W features and an output of V features. The output from the WxV convolution operation may be a Vx64 matrix.

[0112] The encoding device may perform a flattening operation to flatten the Vx64 matrix into a 64V element vector. The encoding device may perform a 64VxM fully connected operation to further compress the space-time feature data set into a low-dimensional vector of size M for transmission over the air to the decoding device. The encoding device may perform quantization before transmitting the low-dimensional vector of size M over the air to map the samples for transmission to discrete values ​​for the low-dimensional vector of size M.

[0113] The decoding device may perform an Mx64V fully connected operation to decompress a low-dimensional vector of size M into a space-time feature data set. The decoding device may perform a reshaping operation to reshape the 64V element vector into a 2-dimensional Vx64 matrix. The decoding device may perform a VxW (with a kernel of 1) convolution operation on the output from the reshaping operation. The VxW convolution operation may include a point-by-point (e.g., tap-by-tap) convolution operation. The VxW convolution operation may decompress the spatial features from the reduced dimension for each tap. The VxW convolution operation has an input of V features and an output of W features. The output from the VxW convolution operation may be a Wx64 matrix.

[0114] The decoding device may perform one or more ResNet operations. The one or more ResNet operations may further decompress spatial features and / or temporal features. In some aspects, the ResNet operation may include multiple (e.g., 3) 1-dimensional convolution operations, skip connections (e.g., to avoid applying 1-dimensional convolution operations), summation operations of paths through multiple convolution operations and paths through skip connections, etc. The output from the one or more ResNet operations may be a Wx64 matrix.

[0115] The decoding device may perform spatial and temporal feature reconstruction. In some aspects, this may be achieved using a 1-dimensional convolution operation that is fully connected in the spatial dimension (to reconstruct spatial features) and a simple convolution with a small kernel size (e.g., 3) in the tap dimension (to reconstruct short tap features). The output from the 64xW convolution operation may be a 64x64 matrix.

[0116] In some aspects, the values ​​of M, W, and / or V may be configurable to adjust the weight of a feature, payload size, etc.

[0117] As indicated above, Figure 6 This is provided as an example only. Other examples may differ from those described herein. Figure 6 Examples described.

[0118] Figure 7is a diagram illustrating an example 700 associated with using a neural network to encode and decode a data set for uplink communication according to the present disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information, such as a CSF. As shown by example 700, features may be compressed and decompressed in sequence. For example, an encoding device may extract and compress features associated with an input to produce a payload, and then a decoding device may extract and compress features associated with the payload to reconstruct the input. The encoding and decoding operations may be symmetric (as shown) or asymmetric.

[0119] As shown by example 700, the encoding device may receive samples from the antennas. For example, the encoding device may receive a data set of size 256x64 based at least in part on the number of antennas, the number of samples per antenna, and the tap characteristics. The encoding device may reshape the data into a (64x64x4) data set.

[0120] The encoding device may perform 2-dimensional 64x128 convolution operations (with kernel sizes of 3 and 1). In some aspects, the 64x128 convolution operations may perform spatial feature extraction associated with the decoding device antenna dimension, short-time (tap) feature extraction associated with the decoding device (e.g., base station) antenna dimension, etc. In some aspects, this may be achieved using a 2D convolution layer that is fully connected in the decoding device antenna dimension, has a small kernel size (e.g., 3) in the tap dimension, and has a simple convolution operation with a small kernel size (e.g., 1) in the encoding device antenna dimension. The output from the 64xW convolution operation may be a matrix of size (128x64x4).

[0121] The encoding device may perform one or more ResNet operations. The one or more ResNet operations may further refine the spatial features associated with the decoding device and / or the temporal features associated with the decoding device. In some aspects, the ResNet operation may include multiple operations associated with the features. For example, the ResNet operation may include multiple (e.g., 3) 2D convolution operations, skip connections (e.g., between the input of the ResNet and the output of the ResNet to avoid applying a 2D convolution operation), a summation operation of a path through multiple 2D convolution operations and a path through a skip connection, etc. In some aspects, the plurality of 2-dimensional convolution operations may include: a Wx2W convolution operation with kernel sizes of 3 and 1, whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output dataset of size 2Wx64xV; a 2Wx4W convolution operation with kernel sizes of 3 and 1, whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output dataset of size 4Wx64xV; a 4WxW convolution operation with kernel sizes of 3 and 1, whose output has a BN dataset of size (128x64x4). The output from the one or more ResNet operations may be a matrix of size (128x64x4).

[0122] The encoding device may perform a 2-dimensional 128xV convolution operation (with kernel sizes of 1 and 1) on the output from the one or more ResNet operations. The 128xV convolution operation may include a point-by-point (e.g., tap-by-tap) convolution operation. The WxV convolution operation may compress the spatial features associated with the decoding device into a reduced dimension for each tap. The output from the 128xV convolution operation may be a matrix of size (4x64xV).

[0123] The encoding device may perform a 2-dimensional 4x8 convolution operation (with kernel sizes of 3 and 1). In some aspects, the 4x8 convolution operation may perform spatial feature extraction associated with the encoding device antenna dimensions, short-term (tap) feature extraction associated with the encoding device antenna dimensions, etc. The output from the 4x8 convolution operation may be a matrix of size (8x64xV).

[0124] The encoding device may perform one or more ResNet operations. The one or more ResNet operations may further refine the spatial features associated with the encoding device and / or the temporal features associated with the encoding device. In some aspects, the ResNet operation may include multiple operations associated with the features. For example, the ResNet operation may include multiple (e.g., 3) 2D convolution operations, skip connections (e.g., to avoid applying 2D convolution operations), summation operations of paths through multiple 2D convolution operations and paths through skip connections, etc. The output from the one or more ResNet operations may be a matrix of size (8x64xV).

[0125] The encoding device may perform a 2-dimensional 8xU convolution operation (with kernel sizes of 1 and 1) on the output from the one or more ResNet operations. The 8xU convolution operation may include a point-by-point (e.g., tap-by-tap) convolution operation. The 8xU convolution operation may compress the spatial features associated with the decoding device into a reduced dimension for each tap. The output from the 128xV convolution operation may be a matrix of size (Ux64xV).

[0126] The encoding device may perform a flattening operation to flatten a matrix of size (Ux64xV) into a 64UV element vector. The encoding device may perform a 64UVxM fully connected operation to further compress the 2-dimensional space-time feature data set into a low-dimensional vector of size M for transmission over the air to the decoding device. The encoding device may perform quantization before transmitting the low-dimensional vector of size M over the air to map the samples for transmission to discrete values ​​for the low-dimensional vector of size M.

[0127] The decoding device may perform an Mx64UV fully connected operation to decompress a low-dimensional vector of size M into a spatial-temporal feature data set. The decoding device may perform a reshaping operation to reshape the 64UV element vector into a matrix of size (Ux64xV). The decoding device may perform a 2-dimensional Ux8 (with a kernel of 1,1) convolution operation on the output from the reshaping operation. The Ux8 convolution operation may include a point-by-point (e.g., tap-by-tap) convolution operation. The Ux8 convolution operation may decompress the spatial features from the reduced dimension for each tap. The output from the Ux8 convolution operation may be a data set of size (8x64xV).

[0128] The decoding device may perform one or more ResNet operations. The one or more ResNet operations may further decompress the spatial features and / or temporal features associated with the encoding device. In some aspects, the ResNet operation may include multiple (e.g., 3) 2D convolution operations, skip connections (e.g., to avoid applying 2D convolution operations), summation operations of paths through multiple 2D convolution operations and paths through skip connections, etc. The output from the one or more ResNet operations may be a data set of size (8x64xV).

[0129] The decoding device may perform a 2-dimensional 8x4 convolution operation (with kernel sizes of 3 and 1). In some aspects, the 8x4 convolution operation may perform spatial feature reconstruction in the antenna dimension of the encoding device, as well as short-term feature reconstruction, etc. The output from the 8x4 convolution operation may be a data set of size (Vx64x4).

[0130] The decoding device may perform a 2-dimensional Vx128 (with a kernel of 1) convolution operation on the output from the 2-dimensional 8x4 convolution operation to reconstruct the tap features and spatial features associated with the decoding device. The Vx128 convolution operation may include a point-by-point (e.g., tap-by-tap) convolution operation. The Vx128 convolution operation may decompress the spatial features associated with the decoding device antenna from the reduced dimension for each tap. The output from the Ux8 convolution operation may be a matrix of size (128x64x4).

[0131] The decoding device may perform one or more ResNet operations. The one or more ResNet operations may further decompress the spatial features and / or temporal features associated with the decoding device. In some aspects, the ResNet operation may include multiple (e.g., 3) 2D convolution operations, skip connections (e.g., to avoid applying 2D convolution operations), summation operations of paths through multiple 2D convolution operations and paths through skip connections, etc. The output from the one or more ResNet operations may be a matrix of size (128x64x4).

[0132] The decoding device may perform a 2-dimensional 128x64 convolution operation (with kernel sizes of 3 and 1). In some aspects, the 128x64 convolution operation may perform spatial feature reconstruction associated with the decoding device antenna dimensions, short-term feature reconstruction, etc. The output from the 128x64 convolution operation may be a data set of size (64x64x4).

[0133] In some aspects, the values ​​of M, V, and / or U may be configurable to adjust feature weights, payload sizes, etc. For example, the value of M may be 32, 64, 128, 256, or 512, the value of V may be 16, and / or the value of U may be 1.

[0134] As indicated above, Figure 7 This is provided as an example only. Other examples may differ from those described herein. Figure 7 Examples described.

[0135] Figure 8 8 is a diagram illustrating an example 800 associated with using a neural network to encode and decode a data set for uplink communication according to the present disclosure. An encoding device (e.g., UE 120, encoding device 300, etc.) may be configured to perform one or more operations on samples (e.g., data) received via one or more antennas of the encoding device to compress the samples. A decoding device (e.g., base station 110, decoding device 350, etc.) may be configured to decode the compressed samples to determine information, such as a CSF. The encoding device and decoding device operations may be asymmetric. In other words, the decoding device may have a greater number of layers than the decoding device.

[0136] As shown by example 800, the encoding device may receive samples from the antennas. For example, the encoding device may receive a data set of size 64x64 based at least in part on the number of antennas, the number of samples per antenna, and the tap characteristics.

[0137] The coding device may perform a 64xW convolution operation (with a kernel size of 1). In some aspects, the 64xW convolution operation may be fully connected in the antenna, may be a convolution in the tap, and the like. The output from the 64xW convolution operation may be a Wx64 matrix. The coding device may perform one or more WxW convolution operations (with a kernel size of 1 or 3). The output from one or more WxW convolution operations may be a Wx64 matrix. The coding device may perform a convolution operation (with a kernel size of 1). In some aspects, one or more WxW convolution operations may perform spatial feature extraction, short-time (tap) feature extraction, and the like. In some aspects, the WxW convolution operation may be a series of 1-dimensional convolution operations.

[0138] The encoding device may perform a flattening operation to flatten the Wx64 matrix into a 64W element vector. The encoding device may perform a 4096xM fully connected operation to further compress the space-time feature data set into a low-dimensional vector of size M for transmission over the air to the decoding device. The encoding device may perform quantization before transmitting the low-dimensional vector of size M over the air to map the samples for transmission to discrete values ​​for the low-dimensional vector of size M.

[0139] The decoding device may perform a 4096xM fully connected operation to decompress the low-dimensional vector of size M into a spatial-temporal feature data set. The decoding device may perform a reshape operation to reshape the 6W element vector into a Wx64 matrix.

[0140] The decoding device may perform one or more ResNet operations. The one or more ResNet operations may decompress spatial features and / or temporal features. In some aspects, the ResNet operation may include multiple (e.g., 3) 1-dimensional convolution operations, skip connections (e.g., between the input of the ResNet and the output of the ResNet to avoid applying a 1-dimensional convolution operation), a summation operation of a path through multiple 1-dimensional convolution operations and a path through a skip connection, etc. In some aspects, multiple 1-dimensional convolution operations may include: a Wx256 convolution operation with a kernel size of 3, whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output data set of size 256x64; a 256x512 convolution operation with a kernel size of 3, whose output is input to a BN layer, followed by a LeakyReLU activation, which produces an output data set of size 512x64; a 512xW convolution operation with a kernel size of 3, whose output has a BN data set of size Wx64. The output from the one or more ResNet operations may be a Wx64 matrix.

[0141] The decoding device may perform one or more WxW convolution operations (with a kernel size of 1 or 3). The output from one or more WxW convolution operations may be a Wx64 matrix. The encoding device may perform a convolution operation (with a kernel size of 1). In some aspects, the WxW convolution operation may perform spatial feature reconstruction, short-term (tap) feature reconstruction, etc. In some aspects, the WxW convolution operation may be a series of 1-dimensional convolution operations.

[0142] The encoding device may perform a Wx64 convolution operation (with a kernel size of 1). In some aspects, the Wx64 convolution operation may be a 1-dimensional convolution operation. The output from the 64xW convolution operation may be a 64x64 matrix.

[0143] In some aspects, the values ​​of M and / or W may be configurable to adjust the weight of features, payload size, etc.

[0144] As indicated above, Figure 8 This is provided as an example only. Other examples may differ from those described herein. Figure 8 Examples described.

[0145] As described herein, a coding device operating in a network may measure reference signals, etc., to report to a decoding device. For example, a coding device may receive a neural network-based channel state information (CSI) reference signal (CSI-RS). The coding device may measure the neural network-based CSI based at least in part on the CSI-RS. In some aspects, the neural network-based CSI may compress channel information associated with the CSI-RS in a more comprehensive form than, for example, type-II CSI or type-I CSI. For example, in type II CSI, the subband size may be fixed for all subbands, which results in limited granularity. The neural network-based CSI may facilitate greater granularity by facilitating the provision of information about the entire channel. The neural network-based CSI may also be specified to compress certain subbands with higher or lower accuracy.

[0146] In some aspects, neural network-based CSI may also facilitate multi-user (MU) multiple-input multiple-output (MU-MIMO) operations at a decoding device by facilitating provision of information about channels and interference, thereby enabling the decoding device to manage and group users, etc. Reporting CSF based on machine learning may facilitate the use of neural network-based CSI, more robust type-II CSI, etc. However, in a typical scenario, one type of CSI feedback may be scheduled and / or requested shortly after the encoding device has transmitted the same type or another type of CSI feedback. As a result, signaling overhead for transmission of redundant information may be increased, which may reduce efficiency and uplink resource availability.

[0147] According to various aspects of the techniques and equipment described herein, a coding device may be configured to save a CSF corresponding to a first reference signal for a specified time period. The coding device may use the saved CSF to facilitate the transmission of a differential CSF, which is based at least in part on a second reference signal. In some aspects, the coding device may be configured to suppress the transmission of an additional CSF for a specified time period after transmitting a neural network-based CSF. In some aspects, a neural network may be used to compress and encode channel information and interference information to provide a robust CSF so that the information sent in the initial CSF may be sufficient for a specified time period, or so that the information may be supplemented by a differential CSF rather than a full CSF transmission. As a result, the various aspects described herein can facilitate reducing uplink traffic overhead, thereby increasing uplink resource availability while providing a robust CSI to a decoding device to facilitate traffic management.

[0148] Fig. 9905 and 910 may communicate with each other. In some aspects, the first device 905 and the second device 910 may communicate with each other via a wireless communication network (e.g., Figure 1 The first device 905 may be an encoding device (eg, UE 120, encoding device 300, etc.), and the second device 910 may be a decoding device (eg, base station 110, decoding device 350, etc.).

[0149] As indicated by reference numeral 915, the second device 910 may transmit and the first device 905 may receive a CSI feedback configuration including an indication of a CSF corresponding to a first reference signal carried on a downlink channel stored within a specified time period. In some aspects, the CSF may include channel information and interference information. In some aspects, the specified time period may include a number of time slots or a number of milliseconds. In some aspects, the CSI feedback configuration may be carried in a radio resource control (RRC) message, a media access control (MAC) control element (MAC-CE), or the like.

[0150] The CSI feedback configuration may indicate a differential encoding scheme to be used to encode the differential CSF based at least in part on the CSF. In some aspects, the CSI feedback configuration may indicate a first neural network to encode the CSF and a second neural network to encode the differential CSF. In some aspects, the CSI feedback configuration may indicate a first power threshold for channel compression corresponding to the CSF and a second power threshold for channel compression corresponding to the differential CSF. The CSI feedback configuration may indicate a first number of delay taps to be used for channel compression corresponding to the CSF and a second number of delay taps to be used for channel compression corresponding to the differential CSF.

[0151] In some aspects, the CSI feedback configuration may indicate a first compression amount corresponding to the CSF and a second compression amount corresponding to the differential CSF. In some aspects, the CSI feedback configuration may indicate a first quantization type corresponding to the CSF and a second quantization type corresponding to the differential CSF. In some aspects, the CSI feedback configuration may indicate a first neural network training time corresponding to the CSF and a second neural network training time corresponding to the differential CSF.

[0152] In some aspects, the CSI feedback configuration may include an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met. In some aspects, the CSI feedback configuration may include an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including the neural network-based CSI.

[0153] As indicated by reference numeral 920, the second device 910 may transmit and the first device 905 may receive a first reference signal. In some aspects, for example, the first reference signal may include a CSI-RS. As indicated by reference numeral 925, the first device 905 may determine a CSI corresponding to the first reference signal. As indicated by reference numeral 930, the first device 905 may encode the CSI corresponding to the first reference signal to generate a CSF. In some aspects, for example, the first device 905 may generate the CSF using a first neural network.

[0154] As indicated by reference numeral 935, the first device 905 may store the CSI and / or CSF in a memory. As indicated by reference numeral 940, the first device 905 may transmit and the second device 910 may receive the CSF. As indicated by reference numeral 945, the second device 910 may transmit and the first device 905 may receive a second reference signal. In some aspects, for example, the second reference signal may include a CSI-RS. According to the CSI feedback configuration, the first device 905 may refrain from transmitting the CSF based on the second reference signal.

[0155] As indicated by reference numeral 950, in some aspects, the first device 905 may determine CSI corresponding to the second reference signal, and as indicated by reference numeral 955, may determine differential CSI. The differential CSI may be based at least in part on the CSI corresponding to the first reference signal and the CSI corresponding to the second reference signal. In some aspects, the CSI corresponding to the first reference signal may have a first CSI type, and the CSI corresponding to the second reference signal may have a second CSI type. For example, the first CSI type may include type-I CSI, type-II CSI, or type-III CSI. The second CSI type may include type-I CSI, type-II CSI, or differential neural network based CSI.

[0156] In some aspects, as shown by reference numeral 960, the first device 905 may encode the differential CSI to generate a differential CSF. The differential CSF may indicate, for example, a CSI based on a differential neural network. In some aspects, the first device 905 may encode the second CSI to generate a second CSF. The first device 905 may generate the differential CSF based at least in part on the second CSF and the stored first CSF. In some aspects, the first device 905 may generate the first CSF using the first neural network and generate the differential CSF using the second neural network.

[0157] In some aspects, the first reference signal may include a first CSI-RS associated with a first antenna port set, and the second reference signal may include a second CSI-RS associated with a second antenna port set. In some aspects, the specified time period may include a time period during which the first antenna port set and the second antenna port set are quasi-co-located.

[0158] In some aspects, the CSI feedback configuration may include an indication that the first antenna port set and the second antenna port set are not quasi-co-located. The first device 905 may determine the number of bits for the differential CSF based at least in part on the indication that the first antenna port set and the second antenna port set are not quasi-co-located. In some aspects, the first device 905 may receive an indication of the number of bits for the differential CSF, wherein the number of bits for the differential CSF is based at least in part on determining that the first antenna port set and the second antenna port set are not quasi-co-located. For example, in some aspects, the second device 910 may transmit an indication of the number of bits to the first device 905. The indication of the number of bits may be carried in downlink control information (DCI), MAC-CE, or a combination of DCI and MAC-CE.

[0159] As indicated by reference numeral 965, the first device 905 may transmit and the second device 910 may receive a differential CSF. The differential CSF may be based at least in part on the CSF and a second reference signal carried on the downlink channel, as explained above. In some aspects, as indicated by the dashed arrow associated with reference numeral 965, the first device 905 may refrain from transmitting a second CSF, a differential CSF, and the like. In some aspects, for example, the first device 905 may refrain from transmitting a second CSF and / or a differential CSF based at least in part on the CSI feedback configuration.

[0160] In some aspects, as indicated by reference numeral 970, the first device 905 may receive a third reference signal. The third reference signal may be received after a time period during which the first device 905 is to refrain from transmitting a CSF. Accordingly, as indicated by reference numeral 975, the first device 905 may determine CSI corresponding to the third reference signal. As indicated by reference numeral 980, the first device 905 may encode the CSI corresponding to the third reference signal to generate a second CSF; and, as indicated by reference numeral 985, the first device 905 may transmit the CSF. In some aspects, for example, the second CSF may include type-I CSI or type-I CSI.

[0161] As indicated above, Fig. 9 This is provided as an example only. Other examples may differ from those described herein. Fig. 9 Examples described.

[0162] Fig.10 1 is a diagram illustrating an example process 1000 performed, for example, by a first device according to the present disclosure. Example process 1000 is a diagram in which a first device (e.g., Fig. 9 An example of the first device 905, etc. shown in FIG. 9A performing operations associated with configuration for channel state feedback.

[0163] like Fig.10 As shown in , in some aspects, process 1000 may include receiving a CSI feedback configuration that includes an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period (block 1010). For example, a first device (e.g., using Fig.14 The receiving component 1402 can receive a CSI feedback configuration, which includes an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period, as described above.

[0164] like Fig.10 As further shown in FIG. 1 , in some aspects, process 1000 may include transmitting a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel (block 1020). For example, a first device (e.g., using Fig.14 The transmission component 1406) can transmit a differential CSF, which is based at least in part on the CSF and a second reference signal carried on the downlink channel, as described above.

[0165] Process 1000 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0166] In a first aspect, the CSI feedback configuration is carried in at least one of an RRC message, a MAC-CE, or a combination thereof.

[0167] In a second aspect, alone or in combination with the first aspect, the specified time period comprises a number of time slots or a number of milliseconds.

[0168] In a third aspect, alone or in combination with one or more of the first and second aspects, the CSF includes channel information and interference information.

[0169] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the CSI feedback configuration indicates a differential encoding scheme to be used to encode the differential CSF based at least in part on the CSF.

[0170] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, process 1000 includes receiving a first reference signal; determining CSI corresponding to the first reference signal; using a first neural network to encode the CSI corresponding to the first reference signal to generate the CSF; and transmitting the CSF.

[0171] In a sixth aspect, either alone or in combination with one or more of the first to fifth aspects, process 1000 includes receiving a second reference signal; determining CSI corresponding to the second reference signal; determining differential CSI based at least in part on the CSI corresponding to the first reference signal and the CSI corresponding to the second reference signal; and encoding the differential CSI using a second neural network to generate the differential CSF.

[0172] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, the CSI corresponding to the first reference signal has a first CSI type, and the CSI corresponding to the second reference signal has a second CSI type.

[0173] In an eighth aspect, either alone or in combination with one or more of the first to seventh aspects, the first CSI type comprises type-I CSI, type-II CSI, or type-III CSI, and the second CSI type comprises type-I CSI, type-II CSI, or differential neural network-based CSI.

[0174] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, the CSI feedback configuration indicates a first neural network for encoding the CSF and a second neural network for encoding the differential CSF.

[0175] In a tenth aspect, either alone or in combination with one or more of the first to ninth aspects, the CSI feedback configuration indicates a first power threshold for channel compression corresponding to the CSF and a second power threshold for channel compression corresponding to the differential CSF.

[0176] In an eleventh aspect, either alone or in combination with one or more of the first to tenth aspects, the CSI feedback configuration indicates a first number of delay taps to be used for channel compression corresponding to the CSF and a second number of delay taps to be used for channel compression corresponding to the differential CSF.

[0177] In a twelfth aspect, alone or in combination with one or more of the first to eleventh aspects, the CSI feedback configuration indicates a first compression amount corresponding to the CSF and a second compression amount corresponding to the differential CSF.

[0178] In a thirteenth aspect, alone or in combination with one or more of the first to twelfth aspects, the CSI feedback configuration indicates a first quantization type corresponding to the CSF and a second quantization type corresponding to the differential CSF.

[0179] In a fourteenth aspect, alone or in combination with one or more of the first to thirteenth aspects, the CSI feedback configuration indicates a first neural network training time corresponding to the CSF and a second neural network training time corresponding to the differential CSF.

[0180] In a fifteenth aspect, alone or in combination with one or more of the first to fourteenth aspects, the differential CSF indicates a differential type-III CSI.

[0181] In a sixteenth aspect, either alone or in combination with one or more of the first to fifteenth aspects, the CSI feedback configuration includes an indication for reporting at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

[0182] In a seventeenth aspect, either alone or in combination with one or more of the first to sixteenth aspects, the first reference signal comprises a first CSI-RS associated with a first antenna port set, and the second reference signal comprises a second CSI-RS associated with a second antenna port set.

[0183] In an eighteenth aspect, either alone or in combination with one or more of the first to seventeenth aspects, the designated time period includes a time period during which the first antenna port set and the second antenna port set are quasi co-located.

[0184] In a nineteenth aspect, alone or in combination with one or more of the first to eighteenth aspects, the CSI feedback configuration includes an indication that the first antenna port set and the second antenna port set are not quasi co-located.

[0185] In a twentieth aspect, either alone or in combination with one or more of the first to nineteenth aspects, process 1000 comprises determining a number of bits for the differential CSF based at least in part on the indication that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

[0186] In a twenty-first aspect, either alone or in combination with one or more of aspects one to twentieth, process 1000 includes receiving an indication of a number of bits to use for the differential CSF, wherein the number of bits to use for the differential CSF is based at least in part on determining that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

[0187] In aspect twenty-second, either alone or in combination with one or more of aspects one to twenty-first, the indication of the number of bits is carried in at least one of a DCI, a MAC-CE, or a combination of a DCI and a MAC-CE.

[0188] although Fig.10 An example block diagram of process 1000 is shown, but in some aspects, process 1000 may include Fig.10 Additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in the process 1000. Additionally or alternatively, two or more blocks of the process 1000 may be executed in parallel.

[0189] Fig.11 1 is a diagram illustrating an example process 1100 performed, for example, by a first device according to the present disclosure. The example process 1100 is a diagram in which a first device (e.g., Fig. 9 An example of the first device 905, etc. shown in FIG. 9A performing operations associated with configuration for channel state feedback.

[0190] like Fig.11 As shown in FIG. 1 , in some aspects, process 1100 may include receiving a CSI feedback configuration that includes an indication to refrain from transmitting a second CSF for a specified period of time after transmitting a first CSF that includes neural network-based CSI (block 1110). For example, a first device (e.g., using Fig.14 The receiving component 1402 can receive a CSI feedback configuration that includes an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI, as described above.

[0191] like Fig.11As further shown in FIG. 1 , in some aspects, process 1100 may include transmitting a first CSF (block 1120). For example, a first device (e.g., using Fig.14 The transmission component 1406) can transmit the first CSF as described above.

[0192] like Fig.11 As further shown in FIG. 14 , in some aspects, process 1100 may include refraining from transmitting a second CSF based at least in part on the CSI feedback configuration (block 11130). For example, the first device (e.g., using communication manager 1404) may refrain from transmitting a second CSF based at least in part on the CSI feedback configuration, as described above.

[0193] Process 1100 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0194] In the first aspect, the second CSF includes a Type-I CSI or a Type-II CSI.

[0195] although Fig.11 An example block diagram of process 1100 is shown, but in some aspects, process 1100 may include Fig.11 Additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in the process 1100. Additionally or alternatively, two or more blocks of the process 1100 may be executed in parallel.

[0196] Fig.12 1 is a diagram illustrating an example process 1200 performed, for example, by a second device according to the present disclosure. The example process 1200 is a diagram in which the second device (e.g., Fig. 9 An example of a second device 910, etc. shown in FIG. 9A performing operations associated with a configuration for channel state feedback.

[0197] like Fig.12 As shown in , in some aspects, process 1200 may include transmitting a CSI feedback configuration that includes an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period (block 1210). For example, a second device (e.g., using Fig.16 The transmission component 1606) can transmit a CSI feedback configuration, which includes an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period, as described above.

[0198] like Fig.12As further shown in FIG. 1 , in some aspects, process 1200 may include receiving a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel (block 1220). For example, a second device (e.g., using Fig.16 The receiving component 1602 can receive a differential CSF, which is based at least in part on the CSF and a second reference signal carried on the downlink channel, as described above.

[0199] Process 1200 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0200] In a first aspect, the CSI feedback configuration is carried in at least one of an RRC message, a MAC-CE, or a combination thereof.

[0201] In a second aspect, alone or in combination with the first aspect, the specified time period comprises a number of time slots or a number of milliseconds.

[0202] In a third aspect, alone or in combination with one or more of the first and second aspects, the CSF includes channel information and interference information.

[0203] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the CSI feedback configuration indicates a differential encoding scheme to be used to encode the differential CSF based at least in part on the CSF.

[0204] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, process 1200 includes transmitting a first reference signal and receiving the CSF.

[0205] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, process 1200 includes transmitting a second reference signal.

[0206] In a seventh aspect, either alone or in combination with one or more of the first to sixth aspects, the CSI feedback configuration includes: an instruction to a first neural network; an instruction to determine a CSI corresponding to a first reference signal; and an instruction to use the first neural network to encode the CSI corresponding to the first reference signal to generate the CSF.

[0207] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, the CSI feedback configuration includes an instruction to a second neural network; an instruction to determine CSI corresponding to a second reference signal; an instruction to determine differential CSI based at least in part on the CSI corresponding to the first reference signal and the CSI corresponding to the second reference signal; and an instruction to encode the differential CSI using the second neural network to generate the differential CSF.

[0208] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, the CSI corresponding to the first reference signal has a first CSI type, and the CSI corresponding to the second reference signal has a second CSI type.

[0209] In a tenth aspect, either alone or in combination with one or more of the first to ninth aspects, the first CSI type comprises type-I CSI, type-II CSI, or type-III CSI, and the second CSI type comprises type-I CSI, type-II CSI, or differential neural network-based CSI.

[0210] In an eleventh aspect, alone or in combination with one or more of the first to tenth aspects, the CSI feedback configuration indicates a first power threshold for channel compression corresponding to the CSF and a second power threshold for channel compression corresponding to the differential CSF.

[0211] In a twelfth aspect, either alone or in combination with one or more of the first to eleventh aspects, the CSI feedback configuration indicates a first number of delay taps to be used for channel compression corresponding to the CSF and a second number of delay taps to be used for channel compression corresponding to the differential CSF.

[0212] In a thirteenth aspect, alone or in combination with one or more of the first to twelfth aspects, the CSI feedback configuration indicates a first compression amount corresponding to the CSF and a second compression amount corresponding to the differential CSF.

[0213] In a fourteenth aspect, alone or in combination with one or more of the first to thirteenth aspects, the CSI feedback configuration indicates a first quantization type corresponding to the CSF and a second quantization type corresponding to the differential CSF.

[0214] In a fifteenth aspect, alone or in combination with one or more of the first to fourteenth aspects, the CSI feedback configuration indicates a first neural network training time corresponding to the CSF and a second neural network training time corresponding to the differential CSF.

[0215] In a sixteenth aspect, alone or in combination with one or more of the first to fifteenth aspects, the differential CSF indicates a differential type-III CSI.

[0216] In a seventeenth aspect, either alone or in combination with one or more of the first to sixteenth aspects, the CSI feedback configuration comprises an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

[0217] In an eighteenth aspect, either alone or in combination with one or more of the first to seventeenth aspects, the first reference signal comprises a first CSI-RS associated with a first antenna port set, and the second reference signal comprises a second CSI-RS associated with a second antenna port set.

[0218] In a nineteenth aspect, alone or in combination with one or more of the first to eighteenth aspects, the designated time period includes a time period during which the first antenna port set and the second antenna port set are quasi-co-located.

[0219] In a twentieth aspect, alone or in combination with one or more of the first to nineteenth aspects, the CSI feedback configuration includes an indication that the first antenna port set and the second antenna port set are not quasi co-located.

[0220] In aspect twenty-one, either alone or in combination with one or more of aspects one to twentieth, process 1200 includes determining that a first set of antenna ports and a second set of antenna ports are not quasi-co-located; determining a number of bits for the differential CSF based at least in part on determining that the first set of antenna ports and the second set of antenna ports are not quasi-co-located; and transmitting an indication of the number of bits for the differential CSF.

[0221] In aspect twenty-second, either alone or in combination with one or more of aspects one to twenty-first, the indication of the number of bits is carried in at least one of a DCI, a MAC-CE, or a combination of a DCI and a MAC-CE.

[0222] although Fig.12 An example block diagram of process 1200 is shown, but in some aspects, process 1200 may include Fig.12 Additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in the process 1200. Additionally or alternatively, two or more blocks of the process 1200 may be executed in parallel.

[0223] Fig.13 1 is a diagram illustrating an example process 1300 performed, for example, by a second device according to the present disclosure. The example process 1300 is a diagram in which the second device (e.g., Fig. 9An example of a second device 910, etc. shown in FIG. 9A , performing operations associated with configuration for a CSF.

[0224] like Fig.13 As shown in FIG. 1 , in some aspects, process 1300 may include transmitting a CSI feedback configuration that includes an indication to refrain from transmitting a second CSF for a specified period of time after transmitting a first CSF that includes neural network-based CSI (block 1310). For example, a second device (e.g., using Fig.16 The transmission component 1606) can transmit a CSI feedback configuration that includes an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI, as described above.

[0225] like Fig.13 As further shown in FIG. 16 , in some aspects, process 1300 may include receiving a first CSF (block 1320). For example, the second device (eg, using receiving component 1602) may receive the first CSF, as described above.

[0226] Process 1300 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0227] In the first aspect, the second CSF includes a Type-I CSI or a Type-II CSI.

[0228] although Fig.13 Example blocks of process 1300 are shown, but in some aspects, process 1300 may include Fig.13 Additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in the process 1300. Additionally or alternatively, two or more blocks of the process 1300 may be executed in parallel.

[0229] Fig.14 1 is a block diagram of an example apparatus 1400 for wireless communication according to the present disclosure. The apparatus 1400 may be a first device (e.g., an encoding device), or the first device may include the apparatus 1400. In some aspects, the apparatus 1400 includes a receiving component 1402, a communication manager 1404, and a transmission component 1406, which may communicate with each other (e.g., via one or more buses). As shown, the apparatus 1400 may use the receiving component 1402 and the transmission component 1406 to communicate with another apparatus 1408 (such as a decoding device, a base station, an encoding device, or another wireless communication device).

[0230] In some aspects, the apparatus 1400 may be configured to perform Figure 3-9Additionally or alternatively, the apparatus 1400 may be configured to perform one or more of the processes described herein (such as Fig.10 The process of 1000 Fig.11 In some aspects, the apparatus 1400 may include the above combined Figure 2 One or more components of UE 120 are described.

[0231] The receiving component 1402 may provide means for receiving communications (such as reference signals, control information, data communications, or combinations thereof) from the equipment 1408. The receiving component 1402 may provide the received communications to one or more other components of the equipment 1400 (such as the communications manager 1404). In some aspects, the receiving component 1402 may provide means for signal processing (such as filtering, amplifying, demodulating, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalizing, interference cancellation, or decoding, among other examples) the received communications, and may provide the processed signals to one or more other components. In some aspects, the receiving component 1402 may include a combination of the above. Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, controllers / processors, memories, or combinations thereof of the described first UE.

[0232] The transmission component 1406 may provide means for transmitting communications (such as reference signals, control information, data communications, or a combination thereof) to the equipment 1408. In some aspects, the communication manager 1404 may generate communications and may transmit the generated communications to the transmission component 1406 for transmission to the equipment 1408. In some aspects, the transmission component 1406 may provide means for performing signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and may transmit the processed signals to the equipment 1408. In some aspects, the transmission component 1406 may include a combination of the above. Figure 2 One or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof of the described first UE. In some aspects, the transmitting component 1406 can be co-located with the receiving component 1402 in a transceiver.

[0233] In some aspects, the communication manager 1404 may provide means for receiving a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; means for transmitting a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel; etc. In some aspects, the communication manager 1404 may provide means for receiving a CSI feedback configuration, the CSI feedback configuration comprising an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF comprising neural network-based CSI; means for transmitting the first CSF; means for refraining from transmitting the second CSF based at least in part on the CSI feedback configuration; etc. In some aspects, the communication manager 1404 may include means for processing and / or implementing the CSF neural network configuration received by the receiving component 1402. In some aspects, the communication manager 1404 may include the above in combination with Figure 2 A controller / processor, a memory, or a combination thereof of the described first UE.

[0234] In some aspects, the communication manager 1404 may include a set of components, such as a determining component 1410, an encoding component 1412, or a combination thereof. Alternatively, the set of components may be separate and distinct from the communication manager 1404. In some aspects, the determining component 1410 may include means for determining the CSI; means for determining the differential CSI; means for determining a number of bits for the differential CSF based at least in part on the indication that the first set of antenna ports and the second set of antenna ports are not quasi-co-located; and the like. In some aspects, the encoding component 1412 may include means for implementing one or more neural networks to encode a data set (such as, for example, the CSI or the differential CSI) to generate the CSF or the differential CSF, respectively.

[0235] In some aspects, the communication manager 1404 and / or one or more of the components of the component set may include or may be implemented in hardware (e.g., in conjunction with Fig.18 In some aspects, the communication manager 1404 and / or one or more of the components in the component set may include or may be combined with the above Figure 2 The described UE 120 is implemented within a controller / processor, memory, or a combination thereof.

[0236] In some aspects, the communication manager 1404 and / or one or more components of the component set may be implemented in code (e.g., as software or firmware stored in memory), such as in conjunction with Fig.18For example, the communication manager 1404 and / or components (or parts of components) may be implemented as instructions or codes stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the functions or operations of the communication manager 1404 and / or the components. If implemented in code, the functions of the communication manager 1404 and / or components may be implemented by combining the above Figure 2 The described UE 120 may be executed by a controller / processor, memory, scheduler, communication unit, or a combination thereof.

[0237] Fig.14 The number and arrangement of components shown in the figure are provided as examples. In practice, there may be Fig.14 Additional components, fewer components, different components, or differently arranged components than those shown in FIG. Fig.14 Two or more components shown in may be implemented in a single component, or Fig.14 The single component shown in may be implemented as multiple distributed components. Additionally or alternatively, Fig.14 The component set (e.g., one or more components) shown in Fig.14 One or more functions performed by another set of components shown in FIG.

[0238] Fig.15 1500 is a diagram illustrating an example of a hardware implementation of an apparatus 1505 employing a processing system 1510. The apparatus 1505 can be a first device (e.g., Fig.14 The equipment 1400 shown, Fig. 9 , etc.) as shown in FIG. 9A .

[0239] The processing system 1510 may be implemented with a bus architecture generally represented by bus 1515. Bus 1515 may include any number of interconnecting buses and bridges depending on the specific application and overall design constraints of the processing system 1510. Bus 1515 links together various circuits including one or more processors and / or hardware components (represented by processor 1520, illustrated components, and computer readable media / memory 1525). Bus 1515 may also link various other circuits such as timing sources, peripherals, voltage regulators, power management circuits, and the like.

[0240] The processing system 1510 may be coupled to a transceiver 1530. The transceiver 1530 is coupled to one or more antennas 1535. The transceiver 1530 provides a means for communicating with various other devices over a transmission medium. The transceiver 1530 receives signals from the one or more antennas 1535, extracts information from the received signals, and provides the extracted information to the processing system 1510 (specifically, the receiving component 1402). In addition, the transceiver 1530 receives information from the processing system 1510 (specifically, the transmitting component 1406) and generates a signal to be applied to the one or more antennas 1535 based at least in part on the received information.

[0241] The processing system 1510 includes a processor 1520 coupled to a computer-readable medium / memory 1525. The processor 1520 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory 1525. The software, when executed by the processor 1520, causes the processing system 1510 to perform various functions described herein for any particular device. The computer-readable medium / memory 1525 may also be used to store data manipulated by the processor 1520 when executing the software. The processing system further includes at least one of the illustrated components. For example, the processing system may include a determination component 1410, an encoding component 1412, and the like. Each component may be a software module running in the processor 1520, a software module resident / stored in the computer-readable medium / memory 1525, one or more hardware modules coupled to the processor 1520, or some combination thereof.

[0242] In some aspects, the processing system 1510 may be a component of the UE 120 and may include the memory 282 and / or at least one of the following: the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280. In some aspects, the apparatus 1505 for wireless communication provides: receiving a channel state information (CSI) feedback configuration, the CSI feedback configuration including an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period. In some aspects, the apparatus 1505 for wireless communication may provide: means for transmitting a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel. In some aspects, the apparatus 1505 for wireless communication provides: means for receiving a channel state information (CSI) feedback configuration, the CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first channel state feedback (CSF) including neural network-based CSI. In some aspects, the apparatus 1505 for wireless communication may provide: a device for transmitting a first CSF. In some aspects, the apparatus 1505 for wireless communication may provide: a device for suppressing the transmission of a second CSF based at least in part on the CSI feedback configuration. The aforementioned means may be one or more components in the aforementioned components of the apparatus 1400 and / or the processing system 1510 of the apparatus 1505 configured to perform the functions described by the aforementioned means. As described elsewhere herein, the processing system 1510 may include the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280. In one configuration, the aforementioned means may be the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280 configured to perform the functions and / or operations described herein.

[0243] Fig.15 are provided as examples. Other examples may differ from those in combination with Fig.15 Examples described.

[0244] Fig.16 1 is a block diagram of an example apparatus 1600 for wireless communication according to the present disclosure. The apparatus 1600 may be a second device (e.g., Fig. 9 The second device 910 shown in Figure 3 The decoding device 350 shown in Figure 110, etc.), or the second device may include equipment 1600. In some aspects, equipment 1600 includes a receiving component 1602, a communication manager 1604, and a transmission component 1606, which can communicate with each other (e.g., via one or more buses). As shown, equipment 1600 can use receiving component 1602 and transmission component 1606 to communicate with another equipment 1608 (such as a first device, UE, base station, or another wireless communication device).

[0245] In some aspects, the apparatus 1600 may be configured to perform Figure 3-9 Additionally or alternatively, the apparatus 1600 may be configured to perform one or more of the processes described herein (such as Fig.12 The process 1200 Fig.13 In some aspects, the apparatus 1600 may include the above combined Figure 2 One or more components of a base station are described.

[0246] The receiving component 1602 may provide means for receiving communications (such as reference signals, control information, data communications, or combinations thereof) from the equipment 1608. The receiving component 1602 may provide the received communications to one or more other components of the equipment 1600 (such as the communications manager 1604). In some aspects, the receiving component 1602 may provide means for performing signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, among other examples) of the received communications, and may provide the processed signals to one or more other components. In some aspects, the receiving component 1602 may include a combination of the above. Figure 2 One or more antennas, demodulators, MIMO detectors, receive processors, controllers / processors, memories, or combinations thereof of the described base stations.

[0247] The transmission component 1606 may provide means for transmitting communications (such as reference signals, control information, data communications, or a combination thereof) to the equipment 1608. In some aspects, the communication manager 1604 may generate communications and may transmit the generated communications to the transmission component 1606 for transmission to the equipment 1608. In some aspects, the transmission component 1606 may provide means for performing signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and may transmit the processed signals to the equipment 1608. In some aspects, the transmission component 1606 may include a combination of the above. Figure 2One or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof of the described base stations. In some aspects, the transmitting component 1606 can be co-located with the receiving component 1602 in a transceiver.

[0248] The communication manager 1604 may provide means for transmitting a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period. The communication manager 1604 may provide means for receiving a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel. In some aspects, the communication manager 1604 may include the above in combination with Figure 2 A controller / processor, memory, scheduler, communication unit, or a combination thereof of a described base station.

[0249] In some aspects, the communication manager 1604 may include a set of components, such as a determining component 1610. Alternatively, the set of components may be separate and distinct from the communication manager 1604. In some aspects, the determining component 1610 may provide means for determining that the first set of antenna ports and the second set of antenna ports are not quasi-co-located; means for determining a number of bits for the differential CSF based at least in part on determining that the first set of antenna ports and the second set of antenna ports are not quasi-co-located; and the like.

[0250] In some aspects, the communication manager 1604 and / or one or more of the components of the component set may include or may be implemented in hardware (e.g., in conjunction with Fig.19 In some aspects, the communication manager 1604 and / or one or more of the components in the component set may include or may be combined with the above. Figure 2 The described BS 110 is implemented within a controller / processor, a memory, or a combination thereof.

[0251] In some aspects, the communication manager 1604 and / or one or more components of the component set may be implemented in code (e.g., as software or firmware stored in memory), such as in conjunction with Fig.19 For example, the communication manager 1604 and / or components (or parts of components) may be implemented as instructions or codes stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the functions or operations of the communication manager 1604 and / or the components. If implemented in code, the functions of the communication manager 1604 and / or components may be implemented by combining the above Figure 2 The described BS 110 may be executed by a controller / processor, memory, scheduler, communication unit, or a combination thereof.

[0252] Fig.16 The number and arrangement of components shown in the figure are provided as examples. In practice, there may be Fig.16 Additional components, fewer components, different components, or differently arranged components than those shown in FIG. Fig.16 Two or more components shown in may be implemented in a single component, or Fig.16 The single component shown in may be implemented as multiple distributed components. Additionally or alternatively, Fig.16 The component set (e.g., one or more components) shown in Fig.16 One or more functions performed by another set of components shown in FIG.

[0253] Fig.17 is a diagram illustrating an example 1700 of a hardware implementation for an apparatus 1705 employing a processing system 1710. The apparatus 1705 may be a base station.

[0254] The processing system 1710 may be implemented with a bus architecture generally represented by bus 1715. Bus 1715 may include any number of interconnecting buses and bridges depending on the specific application and overall design constraints of the processing system 1710. Bus 1715 links together various circuits including one or more processors and / or hardware components (represented by processor 1720, illustrated components, and computer readable media / memory 1725). Bus 1715 may also link various other circuits such as timing sources, peripherals, voltage regulators, power management circuits, and the like.

[0255] The processing system 1710 may be coupled to a transceiver 1730. The transceiver 1730 is coupled to one or more antennas 1735. The transceiver 1730 provides a means for communicating with various other devices over a transmission medium. The transceiver 1730 receives signals from the one or more antennas 1735, extracts information from the received signals, and provides the extracted information to the processing system 1710 (specifically, the receiving component 1602). In addition, the transceiver 1730 receives information from the processing system 1710 (specifically, the transmitting component 1606) and generates a signal to be applied to the one or more antennas 1735 based at least in part on the received information.

[0256] The processing system 1710 includes a processor 1720 coupled to a computer-readable medium / memory 1725. The processor 1720 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory 1725. The software, when executed by the processor 1720, causes the processing system 1710 to perform various functions described herein for any particular device. The computer-readable medium / memory 1725 may also be used to store data manipulated by the processor 1720 when executing the software. The processing system further includes at least one of the illustrated components. For example, the processing system may include a determination component 1610. The components may be software modules running in the processor 1720, software modules residing / stored in the computer-readable medium / memory 1725, one or more hardware modules coupled to the processor 1720, or some combination thereof.

[0257] In some aspects, the processing system 1710 may be a component of the base station 110 and may include the memory 242 and / or at least one of the following: the TX MIMO processor 230, the RX processor 238, and / or the controller / processor 240. In some aspects, the apparatus 1705 for wireless communication includes: means for transmitting a channel state information (CSI) feedback configuration, the CSI feedback configuration including an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period. The apparatus 1705 for wireless communication may include means for receiving a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel. The apparatus 1705 for wireless communication may include means for transmitting a channel state information (CSI) feedback configuration, the CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first channel state feedback (CSF) including neural network-based CSI. Means for receiving the CSF; and so on. The aforementioned means may be one or more components of the aforementioned components of the apparatus 1600 and / or the processing system 1710 of the apparatus 1705 configured to perform the functions recited by the aforementioned means. As described elsewhere herein, the processing system 1710 may include the TX MIMO processor 230, the receive processor 238, and / or the controller / processor 240. In one configuration, the aforementioned means may be the TX MIMO processor 230, the receive processor 238, and / or the controller / processor 240 configured to perform the functions and / or operations recited herein.

[0258] Fig.17 are provided as examples. Other examples may differ from those in combination with Fig.17 Examples described.

[0259] Fig.18is a diagram illustrating an example of an implementation of code and circuitry for an apparatus 1805. The apparatus 1805 may be a first device (eg, an encoding device, a UE, etc.).

[0260] like Fig.18 As further shown in , the apparatus 1805 may include circuitry (circuitry 1820) for receiving a CSI feedback configuration. For example, the apparatus 1805 may include circuitry for enabling the apparatus 1805 to receive a CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. In some aspects, the apparatus 1805 may include: circuitry for enabling the apparatus to receive a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI.

[0261] like Fig.18 As further shown in FIG. 1 , the apparatus 1805 may include circuitry (circuitry 1825) for transmitting a CSF and / or a differential CSF. For example, the apparatus 1805 may include circuitry for transmitting a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel. In some aspects, the apparatus 1805 may include: circuitry for transmitting a first CSF.

[0262] like Fig.18 As further shown in FIG. 1 , the apparatus 1805 may include circuitry for refraining from transmitting a CSF (circuitry 1830). For example, the apparatus 1805 may include circuitry for refraining from transmitting a second CSF based at least in part on the CSI feedback configuration.

[0263] like Fig.18 As further shown in the apparatus 1805, the apparatus 1805 may include code (code 1850) stored in the computer-readable medium 1525 for receiving a CSI feedback configuration. For example, the apparatus 1805 may include code that, when executed by the processor 1520, may cause the processor 1520 to receive a CSI feedback configuration that includes an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. In some aspects, the apparatus 1805 may include code that, when executed by the processor 1520, may cause the processor 1520 to receive a CSI feedback configuration that includes an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI.

[0264] like Fig.18As further shown in FIG. 1 , the apparatus 1805 may include code (code 1855) for transmitting a CSF and / or a differential CSF stored in the computer-readable medium 1525. For example, the apparatus 1805 may include code that, when executed by the processor 1525, may cause the transceiver 1530 to transmit a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0265] like Fig.18 As further shown in FIG. 1 , the apparatus 1805 may include code (code 1860) for refraining from transmitting the CSF stored in the computer-readable medium 1525. For example, the apparatus 1805 may include code that, when executed by the processor 1520, may cause the processor 1520 to refrain from transmitting the second CSF based at least in part on the CSI feedback configuration.

[0266] Fig.18 are provided as examples. Other examples may differ from those in combination with Fig.18 Examples described.

[0267] Fig.19 is a diagram illustrating an example of an implementation of code and circuitry for an apparatus 1905. The apparatus 1905 may be a second device (eg, a decoding device, a base station, etc.).

[0268] like Fig.19 As further shown in , the apparatus 1905 may include circuitry (circuitry 1920) for transmitting a CSI feedback configuration. For example, the apparatus 1905 may include circuitry for enabling the apparatus 1905 to transmit a CSI feedback configuration including an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. In some aspects, the apparatus 1905 may include: circuitry for enabling the apparatus 1905 to transmit a CSI feedback configuration including an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI.

[0269] like Fig.19 As further shown in FIG. 1 , the apparatus 1905 may include circuitry (circuitry 1925) for receiving a CSF and / or a differential CSF. For example, the apparatus 1905 may include circuitry for enabling the apparatus 1905 to receive a CSF and / or a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0270] like Fig.19As further shown in the apparatus 1905, the apparatus 1905 may include code (code 1930) stored in the computer-readable medium 1725 for transmitting a CSI feedback configuration. For example, the apparatus 1905 may include code that, when executed by the processor 1720, may cause the transceiver 1730 to transmit a CSI feedback configuration that includes an indication to save a CSF corresponding to a first reference signal carried on a downlink channel for a specified time period. In some aspects, the apparatus 1905 may include code that, when executed by the processor 1720, may cause the transceiver 1730 to transmit a CSI feedback configuration that includes an indication to refrain from transmitting a second CSF for a specified time period after transmitting a first CSF including neural network-based CSI.

[0271] like Fig.19 As further shown in FIG. 1 , the apparatus 1905 may include code (code 1955) for receiving a CSF and / or a differential CSF stored in the computer-readable medium 1725. For example, the apparatus 1905 may include code that, when executed by the processor 1520, may cause the transceiver 1530 to receive a CSF and / or a differential CSF based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0272] Fig.19 are provided as examples. Other examples may differ from those in combination with Fig.19 Examples described.

[0273] Fig. 20 2 is a diagram illustrating an example process 2000 performed, for example, by a first device according to the present disclosure. The example process 2000 is a diagram in which the first device (eg, encoding device, UE 120, Fig.14 An example of equipment 1400, etc.) performing operations associated with using a data network to encode a data set.

[0274] like Fig. 20 As shown in , in some aspects, process 2000 may include encoding a data set using one or more extraction operations and compression operations associated with a neural network to produce a compressed data set, the one or more extraction operations and compression operations being based at least in part on a feature set of the data set (block 2010). For example, a first device (e.g., using Fig.14 The encoding component 1412 shown in can encode the data set using one or more extraction operations and compression operations associated with the neural network to produce a compressed data set, and the one or more extraction operations and compression operations are based at least in part on a feature set of the data set, as described above.

[0275] like Fig. 20As further shown in FIG. 20, in some aspects, process 2000 may include transmitting the compressed data set to a second device (block 2020). For example, a first device (e.g., using Fig.14 The transmission component 1406 shown in ) can transmit the compressed data set to the second device, as described above.

[0276] Process 2000 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0277] In a first aspect, the data set is based at least in part on sampling of one or more reference signals.

[0278] In a second aspect, alone or in combination with the first aspect, transmitting the compressed data set to the second device includes transmitting channel state information feedback to the second device.

[0279] In a third aspect, either alone or in combination with one or more of the first and second aspects, process 2000 includes identifying the feature set of the data set, wherein the one or more extraction operations and compression operations include: a first type of operation performed in a dimension associated with a feature in the feature set of the data set and a second type of operation performed in remaining dimensions associated with other features in the feature set of the data set, the second type of operation being different from the first type of operation.

[0280] In a fourth aspect, alone or in combination with one or more of the first to third aspects, the first type of operation comprises a one-dimensional fully connected layer operation, and the second type of operation comprises a convolution operation.

[0281] In a fifth aspect, either alone or in combination with one or more of the first to fourth aspects, the one or more extraction operations and compression operations include multiple operations including one or more of convolution operations, fully connected layer operations, or residual neural network operations.

[0282] In the sixth aspect, alone or in combination with one or more of the first to fifth aspects, the one or more extraction operations and compression operations include: a first extraction operation and a first compression operation performed on a first feature in the feature set of the data set, and a second extraction operation and a second compression operation performed on a second feature in the feature set of the data set.

[0283] In a seventh aspect, alone or in combination with one or more of the first to sixth aspects, process 2000 includes: performing one or more additional operations on the intermediate data set output after performing the one or more extraction operations and compression operations.

[0284] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, the one or more additional operations include one or more of the following: a quantization operation, a flattening operation, or a fully connected operation.

[0285] In a ninth aspect, alone or in combination with one or more of the first to eighth aspects, the feature set of the data set comprises one or more of spatial features or tap-domain features.

[0286] In the tenth aspect, alone or in combination with one or more of the first to ninth aspects, the one or more extraction operations and compression operations include one or more of the following: spatial feature extraction using a one-dimensional convolution operation, temporal feature extraction using a one-dimensional convolution operation, a residual neural network operation for refining the extracted spatial features, a residual neural network operation for refining the extracted temporal features, a point-by-point convolution operation for compressing the extracted spatial features, a point-by-point convolution operation for compressing the extracted temporal features, a flattening operation for flattening the extracted spatial features, a flattening operation for flattening the extracted temporal features, or a compression operation for compressing one or more of the extracted temporal features or the extracted spatial features into a low-dimensional vector for transmission.

[0287] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, the one or more extraction operations and compression operations include: a first feature extraction operation associated with one or more features associated with the second device, a first compression operation for compressing one or more features associated with the second device, a second feature extraction operation associated with one or more features associated with the first device, and a second compression operation for compressing one or more features associated with the first device.

[0288] although Fig. 20 An example block diagram of process 2000 is shown, but in some aspects, process 2000 may include Fig. 20 Additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in the process 2000. Additionally or alternatively, two or more blocks of the process 2000 may be executed in parallel.

[0289] Fig.21 2 is a diagram illustrating an example process 2100 performed, for example, by a second device according to the present disclosure. The example process 2100 is a diagram in which the second device (eg, a decoding device, a base station 110, Fig.16 An example of equipment 1600, etc.) performing operations associated with using a neural network to decode a data set.

[0290] like Fig.21As shown in , in some aspects, process 2100 may include receiving a compressed data set from a first device (block 2110). For example, a second device (e.g., using Fig.16 The receiving component 1602 shown in can receive a compressed data set from a first device, as described above.

[0291] like Fig.21 As further shown in FIG. 21 , in some aspects, process 2100 may include decoding the compressed data set using one or more decompression operations and reconstruction operations associated with the neural network to produce a reconstructed data set, the one or more decompression operations and reconstruction operations being based at least in part on the feature set of the compressed data set (block 2120). For example, a second device (e.g., using Fig.16 The communication component 1604 shown in can decode the compressed data set using one or more decompression operations and reconstruction operations associated with the neural network to produce a reconstructed data set, and the one or more decompression operations and reconstruction operations are based at least in part on the feature set of the compressed data set, as described above.

[0292] Process 2100 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0293] In a first aspect, decoding the compressed data set using the one or more decompression operations and reconstruction operations includes performing the one or more decompression operations and reconstruction operations based at least in part on an assumption that the first device generates the compressed data set using a set of operations that are symmetric to the one or more decompression operations and reconstruction operations, or performing the one or more decompression operations and reconstruction operations based at least in part on an assumption that the first device generates the compressed data set using a set of operations that are asymmetric to the one or more decompression operations and reconstruction operations.

[0294] In a second aspect, alone or in combination with the first aspect, the compressed data set is based at least in part on sampling of one or more reference signals by the first device.

[0295] In a third aspect, alone or in combination with one or more of the first and second aspects, receiving the compressed data set includes receiving channel state information feedback from the first device.

[0296] In a fourth aspect, either alone or in combination with one or more of the first to third aspects, the one or more decompression operations and reconstruction operations include: a first type of operation performed in a dimension associated with a feature in the feature set of the compressed data set, and a second type of operation performed in the remaining dimensions associated with other features of the feature set of the compressed data set, the second type of operation being different from the first type of operation.

[0297] In a fifth aspect, either alone or in combination with one or more of the first to fourth aspects, the first type of operation comprises a one-dimensional fully connected layer operation, and wherein the second type of operation comprises a convolution operation.

[0298] In a sixth aspect, either alone or in combination with one or more of the first to fifth aspects, the one or more decompression operations and reconstruction operations include multiple operations including one or more of convolution operations, fully connected layer operations, or residual neural network operations.

[0299] In the seventh aspect, alone or in combination with one or more of the first to sixth aspects, the one or more decompression operations and reconstruction operations include: a first operation performed on a first feature of the feature set of the compressed data set, and a second operation performed on a second feature of the feature set of the compressed data set.

[0300] In an eighth aspect, either alone or in combination with one or more of the first to seventh aspects, process 2100 includes performing a reshaping operation on the compressed data set.

[0301] In a ninth aspect, either alone or in combination with one or more of the first to eighth aspects, the feature set of the compressed data set comprises one or more of spatial features or tap-domain features.

[0302] In a tenth aspect, alone or in combination with one or more of the first to ninth aspects, the one or more decompression operations and reconstruction operations include one or more of the following: a feature decompression operation, a temporal feature reconstruction operation, or a spatial feature reconstruction operation.

[0303] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, the one or more decompression operations and reconstruction operations include: a first feature reconstruction operation performed on one or more features associated with the first device, and a second feature reconstruction operation performed on one or more features associated with the second device.

[0304] although Fig.21 An example block diagram of process 2100 is shown, but in some aspects, process 2100 may include Fig.21Additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in the process 2100. Additionally or alternatively, two or more blocks of the process 2100 may be executed in parallel.

[0305] The following provides an overview of some aspects of the disclosure:

[0306] Aspect 1: A wireless communication method performed by a first device, comprising: receiving a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication of maintaining a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; and transmitting a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0307] Aspect 2: The method of aspect 1, wherein the CSI feedback configuration is carried in at least one of the following: a radio resource control message, a medium access control (MAC) control element (MAC-CE), or a combination thereof.

[0308] Aspect 3: The method according to any one of Aspects 1 or 2, wherein the specified time period comprises a number of time slots or a number of milliseconds.

[0309] Aspect 4: The method according to any one of aspects 1 to 3, wherein the CSF includes channel information and interference information.

[0310] Aspect 5: The method of any one of aspects 1-4, wherein the CSI feedback configuration indicates a differential encoding scheme to be used to encode the differential CSF based at least in part on the CSF.

[0311] Aspect 6: The method of any one of Aspects 1-5, further comprising: receiving a first reference signal; determining CSI corresponding to the first reference signal; and using a first neural network to encode the CSI corresponding to the first reference signal to generate the CSF; and transmitting the CSF.

[0312] Aspect 7: The method of Aspect 6 further includes: receiving a second reference signal; determining CSI corresponding to the second reference signal; determining differential CSI based at least in part on the CSI corresponding to the first reference signal and the CSI corresponding to the second reference signal; and using a second neural network to encode the differential CSI to generate the differential CSF.

[0313] Aspect 8: The method of aspect 7, wherein the CSI corresponding to the first reference signal has a first CSI type; and wherein the CSI corresponding to the second reference signal has a second CSI type.

[0314] Aspect 9: The method of aspect 8, wherein the first CSI type comprises type-I CSI, type-II CSI, or type-III CSI, and wherein the second CSI type comprises type-I CSI, type-II CSI, or differential neural network based CSI.

[0315] Aspect 10: The method according to any one of aspects 1-9, wherein the CSI feedback configuration indicates a first neural network for encoding the CSF and a second neural network for encoding the differential CSF.

[0316] Aspect 11: The method according to any one of aspects 1-10, wherein the CSI feedback configuration indicates a first power threshold for channel compression corresponding to the CSF and a second power threshold for channel compression corresponding to the differential CSF.

[0317] Aspect 12: The method of aspect 11, wherein the CSI feedback configuration indicates a first number of delay taps to be used for channel compression corresponding to the CSF and a second number of delay taps to be used for channel compression corresponding to the differential CSF.

[0318] Aspect 13: The method according to any one of aspects 1-12, wherein the CSI feedback configuration indicates a first compression amount corresponding to the CSF and a second compression amount corresponding to the differential CSF.

[0319] Aspect 14: The method according to any one of aspects 1-13, wherein the CSI feedback configuration indicates a first quantization type corresponding to the CSF and a second quantization type corresponding to the differential CSF.

[0320] Aspect 15: The method according to any one of Aspects 1-14, wherein the CSI feedback configuration indicates a first neural network training time corresponding to the CSF and a second neural network training time corresponding to the differential CSF.

[0321] Aspect 16: The method according to any one of aspects 1-15, wherein the differential CSF indicates a differential type-III CSI.

[0322] Aspect 17: The method of any of Aspects 1-16, wherein the CSI feedback configuration includes an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

[0323] Aspect 18: The method of any one of aspects 1-17, wherein the first reference signal comprises a first CSI reference signal (CSI-RS) associated with a first set of antenna ports, and wherein the second reference signal comprises a second CSI-RS associated with a second set of antenna ports.

[0324] Aspect 19: The method of aspect 18, wherein the designated time period includes a time period during which the first antenna port set and the second antenna port set are quasi co-located.

[0325] Aspect 20: The method according to any one of Aspects 18 or 19, wherein the CSI feedback configuration comprises an indication that the first antenna port set and the second antenna port set are not quasi co-located.

[0326] Aspect 21: The method of aspect 20, further comprising: determining a number of bits for the differential CSF based at least in part on the indication that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

[0327] Aspect 22: The method of any of Aspects 18-21, further comprising: receiving an indication of a number of bits used for the differential CSF, wherein the number of bits used for the differential CSF is based at least in part on determining that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

[0328] Aspect 23: A method as in Aspect 22, wherein the indication of the number of bits is carried in at least one of: downlink control information (DCI), a media access control (MAC) control element (MAC-CE), or a combination of DCI and MAC-CE.

[0329] Aspect 24: A wireless communication method performed by a first device, comprising: receiving a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to suppress transmission of a second CSF within a specified time period after transmitting a first channel state feedback (CSF) comprising neural network-based CSI; transmitting the first CSF; and suppressing transmission of the second CSF based at least in part on the CSI feedback configuration.

[0330] Aspect 25: The method of Aspect 24, wherein the second CSF comprises a Type-I CSI or a Type-II CSI.

[0331] Aspect 26: A method for performing wireless communications by a second device, comprising: transmitting a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication of maintaining a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; and receiving a differential CSF, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

[0332] Aspect 27: The method of Aspect 26, wherein the CSI feedback configuration is carried in at least one of: a radio resource control message, a medium access control (MAC) control element (MAC-CE), or a combination thereof.

[0333] Aspect 28: The method of any one of Aspects 26 or 27, wherein the specified time period comprises a number of time slots or a number of milliseconds.

[0334] Aspect 29: The method according to any one of aspects 26-28, wherein the CSF comprises channel information and interference information.

[0335] Aspect 30: The method of any one of aspects 26-29, wherein the CSI feedback configuration indicates a differential encoding scheme to be used to encode the differential CSF based at least in part on the CSF.

[0336] Aspect 31: The method of any one of Aspects 26-30, further comprising: transmitting a first reference signal; and receiving the CSF.

[0337] Aspect 32: The method of any one of Aspects 26-31, further comprising: transmitting a second reference signal.

[0338] Aspect 33: A method as in any of Aspects 26-32, wherein the CSI feedback configuration includes: an instruction to the first neural network; an instruction to determine the CSI corresponding to the first reference signal; and an instruction to use the first neural network to encode the CSI corresponding to the first reference signal to generate the CSF.

[0339] Aspect 34: A method as in Aspect 33, wherein the CSI feedback configuration includes: an instruction to a second neural network; an instruction to determine CSI corresponding to a second reference signal; an instruction to determine differential CSI based at least in part on the CSI corresponding to the first reference signal and the CSI corresponding to the second reference signal; and an instruction to use the second neural network to encode the differential CSI to generate the differential CSF.

[0340] Aspect 35: The method of aspect 34, wherein the CSI corresponding to the first reference signal has a first CSI type, and wherein the CSI corresponding to the second reference signal has a second CSI type.

[0341] Aspect 36: The method of aspect 35, wherein the first CSI type comprises type-I CSI, type-II CSI, or type-III CSI, and wherein the second CSI type comprises type-I CSI, type-II CSI, or differential neural network based CSI.

[0342] Aspect 37: The method of any one of Aspects 26-36, wherein the CSI feedback configuration indicates a first power threshold for channel compression corresponding to the CSF and a second power threshold for channel compression corresponding to the differential CSF.

[0343] Aspect 38: The method of aspect 37, wherein the CSI feedback configuration indicates a first number of delay taps to be used for channel compression corresponding to the CSF and a second number of delay taps to be used for channel compression corresponding to the differential CSF.

[0344] Aspect 39: The method of any one of Aspects 26-38, wherein the CSI feedback configuration indicates a first compression amount corresponding to the CSF and a second compression amount corresponding to the differential CSF.

[0345] Aspect 40: The method of any one of aspects 26-39, wherein the CSI feedback configuration indicates a first quantization type corresponding to the CSF and a second quantization type corresponding to the differential CSF.

[0346] Aspect 41: The method of any one of Aspects 26-40, wherein the CSI feedback configuration indicates a first neural network training time corresponding to the CSF and a second neural network training time corresponding to the differential CSF.

[0347] Aspect 42: The method of any one of Aspects 26-41, wherein the differential CSF indicates a differential type-III CSI.

[0348] Aspect 43: The method of any of Aspects 26-42, wherein the CSI feedback configuration comprises an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

[0349] Aspect 44: The method of any of Aspects 26-43, wherein the first reference signal comprises a first CSI reference signal (CSI-RS) associated with a first set of antenna ports, and wherein the second reference signal comprises a second CSI-RS associated with a second set of antenna ports.

[0350] Aspect 45: The method of aspect 44, wherein the designated time period includes a time period during which the first set of antenna ports and the second set of antenna ports are quasi co-located.

[0351] Aspect 46: The method of any one of Aspects 44 or 45, wherein the CSI feedback configuration comprises an indication that the first antenna port set and the second antenna port set are not quasi co-located.

[0352] Aspect 47: A method as in any of Aspects 44-46, further comprising: determining that the first antenna port set and the second antenna port set are not quasi-co-located; determining the number of bits used for the differential CSF based at least in part on determining that the first antenna port set and the second antenna port set are not quasi-co-located; and transmitting an indication of the number of bits used for the differential CSF.

[0353] Aspect 48: A method as in Aspect 47, wherein the indication of the number of bits is carried in at least one of: downlink control information (DCI), medium access control (MAC) control element (MAC-CE), or a combination of DCI and MAC-CE.

[0354] Aspect 49: A method for performing wireless communications by a second device, comprising: transmitting a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to suppress transmitting a second CSF within a specified time period after transmitting a first channel state feedback (CSF) comprising neural network-based CSI; and receiving the first CSF.

[0355] Aspect 50: The method of Aspect 49, wherein the second CSF comprises a Type-I CSI or a Type-II CSI.

[0356] Aspect 51: An apparatus for wireless communication at a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method as in one or more of Aspects 1-23.

[0357] Aspect 52: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors configured to perform the method of one or more aspects of aspects 1-23.

[0358] Aspect 53: An apparatus for wireless communication, comprising at least one means for performing the method of one or more aspects of aspects 1-23.

[0359] Aspect 54: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method of one or more aspects of aspects 1-23.

[0360] Aspect 55: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform a method as in one or more aspects of aspects 1-23.

[0361] Aspect 56: An apparatus for wireless communication at a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method as in one or more aspects of Aspects 24-25.

[0362] Aspect 57: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors configured to perform the method of one or more aspects of aspects 24-25.

[0363] Aspect 58: An apparatus for wireless communication, comprising at least one means for performing the method of one or more aspects of aspects 24-25.

[0364] Aspect 59: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method of one or more aspects of aspects 24-25.

[0365] Aspect 60: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform the method of one or more aspects of aspects 24-25.

[0366] Aspect 61: An apparatus for wireless communication at a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method as in one or more of Aspects 26-48.

[0367] Aspect 62: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors configured to perform the method of one or more aspects of aspects 26-48.

[0368] Aspect 63: An apparatus for wireless communication, comprising at least one means for performing the method of one or more aspects of aspects 26-48.

[0369] Aspect 64: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method of one or more aspects of aspects 26-48.

[0370] Aspect 65: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform a method as in one or more of aspects 26-48.

[0371] Aspect 66: An apparatus for wireless communication at a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform a method as in one or more of Aspects 49-50.

[0372] Aspect 67: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors configured to perform the method of one or more aspects of aspects 49-50.

[0373] Aspect 68: An apparatus for wireless communication, comprising at least one means for performing the method of one or more aspects of aspects 49-50.

[0374] Aspect 69: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method of one or more aspects of aspects 49-50.

[0375] Aspect 70: A non-transitory computer-readable medium storing an instruction set for wireless communication, the instruction set comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform a method as in one or more of aspects 49-50.

[0376] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired by practice of the various aspects.

[0377] As used herein, the term "component" is intended to be broadly interpreted as a combination of hardware, firmware, and / or hardware and software. As used herein, a processor is implemented with a combination of hardware, firmware, and / or hardware and software. It will be apparent that the systems and / or methods described herein can be implemented in different forms of hardware, firmware, and / or a combination of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit various aspects. Thus, the operation and behavior of these systems and / or methods are described herein without reference to specific software codes—it is understood that software and hardware can be designed to implement these systems and / or methods based at least in part on the description herein.

[0378] As used herein, satisfying a threshold may refer to a value being greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc., depending on the context.

[0379] Although specific feature combinations are described in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various aspects. In fact, many of these features can be combined in a manner not specifically described in the claims and / or undisclosed in the specification. Although each dependent claim listed below can be directly subordinate to only one claim, the disclosure of various aspects includes that each dependent claim is combined with each other claim in this group of claims. As used herein, the phrase quoting "at least one of" a column of items refers to any combination of these items, including single members. As an example, "at least one of a, b or c" is intended to cover: a, b, c, ab, ac, bc and abc, and any combination with multiple identical elements (for example, aa, aaa, aab, aac, abb, acc, bb, bbb, bbc, cc and ccc, or any other sorting of a, b and c).

[0380] Elements, actions or instructions used herein should not be interpreted as key or necessary unless explicitly described as such. Moreover, as used herein, the articles "one" and "a" are intended to include one or more projects, and can be used interchangeably with "one or more". In addition, as used herein, the article "the" is intended to include one or more projects quoted in conjunction with the article "the", and can be used interchangeably with "one or more". In addition, as used herein, the terms "set (set)" and "group" are intended to include one or more projects (for example, related items, non-related items, or a combination of related items and non-related items), and can be used interchangeably with "one or more". In the occasion of intending to have only one project, the phrase "only one" or similar language is used. Moreover, as used herein, the terms "having", "containing", "including" etc. are intended to be open terms. In addition, the phrase "based on" is intended to mean "based at least in part on", unless otherwise explicitly stated. Furthermore, as used herein, the term "or" when used in a sequence is intended to be inclusive and may be used interchangeably with "and / or" unless explicitly stated otherwise (e.g., when used in conjunction with "either of" or "only one of").

Claims

1. A method for performing wireless communication by a first device, comprising: receiving a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; as well as A differential CSF is transmitted, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

2. The method of claim 1, wherein: The CSI feedback configuration is carried in at least one of the following: Radio Resource Control messages, Media Access Control MAC Control Element MAC-CE, or Its combination.

3. The method of claim 1, wherein: The specified time period includes a number of time slots or a number of milliseconds.

4. The method of claim 1, wherein: The CSF includes channel information and interference information.

5. The method of claim 1, wherein: The CSI feedback configuration indicates a differential encoding scheme to be used to encode the differential CSF based at least in part on the CSF.

6. The method of claim 1, further comprising: receiving the first reference signal; determining CSI corresponding to the first reference signal; as well as encoding CSI corresponding to the first reference signal using a first neural network to generate the CSF; as well as The CSF is transmitted.

7. The method of claim 6, further comprising: receiving the second reference signal; determining CSI corresponding to the second reference signal; determining differential CSI based at least in part on CSI corresponding to the first reference signal and CSI corresponding to the second reference signal; as well as The differential CSI is encoded using a second neural network to generate the differential CSF.

8. The method of claim 7, wherein: The CSI corresponding to the first reference signal has a first CSI type, and The CSI corresponding to the second reference signal has a second CSI type.

9. The method of claim 8, wherein: The first CSI type includes type-I CSI, type-II CSI or type-III CSI, and The second CSI type includes type-I CSI, type-II CSI or CSI based on differential neural network.

10. The method of claim 1, wherein: The CSI feedback configuration indicates a first neural network for encoding the CSF and a second neural network for encoding the differential CSF.

11. The method of claim 1, wherein: The CSI feedback configuration indicates a first power threshold for channel compression corresponding to the CSF and a second power threshold for channel compression corresponding to the differential CSF.

12. The method of claim 11, wherein: The CSI feedback configuration indicates a first number of delay taps to be used for channel compression corresponding to the CSF and a second number of delay taps to be used for channel compression corresponding to the differential CSF.

13. The method of claim 1, wherein: The CSI feedback configuration indicates a first compression amount corresponding to the CSF and a second compression amount corresponding to the differential CSF.

14. The method of claim 1, wherein: The CSI feedback configuration indicates a first quantization type corresponding to the CSF and a second quantization type corresponding to the differential CSF.

15. The method of claim 1, wherein: The CSI feedback configuration indicates a first neural network training time corresponding to the CSF and a second neural network training time corresponding to the differential CSF.

16. The method of claim 1, wherein: The differential CSF indicates a differential type-III CSI.

17. The method of claim 1, wherein: The CSI feedback configuration includes an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

18. The method of claim 1, wherein: The first reference signal comprises a first CSI reference signal CSI-RS associated with a first antenna port set, and The second reference signal includes a second CSI-RS associated with a second antenna port set.

19. The method of claim 18, wherein: The designated time period includes a time period during which the first set of antenna ports and the second set of antenna ports are quasi co-located.

20. The method of claim 18, wherein: The CSI feedback configuration includes an indication that the first set of antenna ports and the second set of antenna ports are not quasi co-located.

21. The method of claim 20, further comprising determining a number of bits for the differential CSF based at least in part on the indication that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

22. The method of claim 18, further comprising receiving an indication of a number of bits used for the differential CSF, wherein: The number of bits used for the differential CSF is based at least in part on a determination that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

23. The method of claim 22, wherein: The indication of the number of bits is carried in at least one of: Downlink Control Information DCI, Media Access Control MAC Control Element MAC-CE, or A combination of DCI and MAC-CE.

24. The method of claim 1, wherein: The CSF includes a neural network-based CSI, and wherein the CSI feedback configuration further indicates to suppress transmission of a second CSF corresponding to the second reference signal for a specified period of time after transmitting the CSF, and The method further comprises: transmitting the CSF; and Transmitting the second CSF is refrained from based at least in part on the CSI feedback configuration.

25. The method of claim 24, wherein: The second CSF includes a Type-I CSI or a Type-II CSI, and wherein the CSF and the second CSF are of the same type or of different types.

26. A method for performing wireless communication by a device, comprising: transmitting a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; as well as A differential CSF is received, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

27. The method of claim 26, wherein: The differential CSF indicates a differential type-III CSI.

28. The method of claim 26, wherein: The CSI feedback configuration includes an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

29. The method of claim 26, wherein: The CSF includes a neural network-based CSI, and wherein the CSI feedback configuration further indicates to suppress transmission of a second CSF corresponding to the second reference signal for a specified period of time after transmitting the CSF, and The method also includes receiving the CSF.

30. The method of claim 29, wherein: The second CSF includes a Type-I CSI or a Type-II CSI, and wherein the CSF and the second CSF are of the same type or of different types.

31. An apparatus for wireless communication, comprising: Memory; as well as one or more processors coupled to the memory, the one or more processors being configured to cause the apparatus to: receiving a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; as well as A differential CSF is transmitted, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

32. The apparatus of claim 31, wherein: The CSI feedback configuration is carried in at least one of the following: Radio Resource Control messages, Media Access Control MAC Control Element MAC-CE, or Its combination.

33. The apparatus of claim 31, wherein: The specified time period includes a number of time slots or a number of milliseconds.

34. The apparatus of claim 31, wherein: The CSF includes channel information and interference information.

35. The apparatus of claim 31, wherein: The CSI feedback configuration indicates a differential encoding scheme to be used to encode the differential CSF based at least in part on the CSF.

36. The apparatus of claim 31, wherein: The one or more processors are further configured to cause the apparatus to: receiving the first reference signal; determining CSI corresponding to the first reference signal; as well as encoding CSI corresponding to the first reference signal using a first neural network to generate the CSF; as well as The CSF is transmitted.

37. The apparatus of claim 36, wherein: The one or more processors are further configured to cause the apparatus to: receiving the second reference signal; determining CSI corresponding to the second reference signal; determining differential CSI based at least in part on CSI corresponding to the first reference signal and CSI corresponding to the second reference signal; as well as The differential CSI is encoded using a second neural network to generate the differential CSF.

38. The apparatus of claim 37, wherein: The CSI corresponding to the first reference signal has a first CSI type, and The CSI corresponding to the second reference signal has a second CSI type.

39. The apparatus of claim 38, wherein: The first CSI type includes type-I CSI, type-II CSI or type-III CSI, and The second CSI type includes type-I CSI, type-II CSI or CSI based on differential neural network.

40. The apparatus of claim 31, wherein: The CSI feedback configuration indicates a first neural network for encoding the CSF and a second neural network for encoding the differential CSF.

41. The apparatus of claim 31, wherein: The CSI feedback configuration indicates a first power threshold for channel compression corresponding to the CSF and a second power threshold for channel compression corresponding to the differential CSF.

42. The apparatus of claim 41, wherein: The CSI feedback configuration indicates a first number of delay taps to be used for channel compression corresponding to the CSF and a second number of delay taps to be used for channel compression corresponding to the differential CSF.

43. The apparatus of claim 31, wherein: The CSI feedback configuration indicates a first compression amount corresponding to the CSF and a second compression amount corresponding to the differential CSF.

44. The apparatus of claim 31, wherein: The CSI feedback configuration indicates a first quantization type corresponding to the CSF and a second quantization type corresponding to the differential CSF.

45. The apparatus of claim 31, wherein: The CSI feedback configuration indicates a first neural network training time corresponding to the CSF and a second neural network training time corresponding to the differential CSF.

46. ​​The apparatus of claim 31, wherein: The differential CSF indicates a differential type-III CSI.

47. The apparatus of claim 31, wherein: The CSI feedback configuration includes an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

48. The apparatus of claim 31, wherein: The first reference signal comprises a first CSI reference signal CSI-RS associated with a first antenna port set, and The second reference signal includes a second CSI-RS associated with a second antenna port set.

49. The apparatus of claim 48, wherein: The designated time period includes a time period during which the first set of antenna ports and the second set of antenna ports are quasi co-located.

50. The apparatus of claim 48, wherein: The CSI feedback configuration includes an indication that the first set of antenna ports and the second set of antenna ports are not quasi co-located.

51. The apparatus of claim 50, wherein: The one or more processors are further configured to cause the apparatus to: A number of bits for the differential CSF is determined based at least in part on the indication that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

52. The apparatus of claim 48, wherein: The one or more processors are further configured to cause the apparatus to: An indication of a number of bits for the differential CSF is received, wherein the number of bits for the differential CSF is based at least in part on determining that the first set of antenna ports and the second set of antenna ports are not quasi-co-located.

53. The apparatus of claim 52, wherein: The indication of the number of bits is carried in at least one of: Downlink Control Information DCI, Media Access Control MAC Control Element MAC-CE, or A combination of DCI and MAC-CE.

54. The apparatus of claim 31, wherein: The CSF includes a neural network-based CSI, and wherein the CSI feedback configuration further indicates to suppress transmission of a second CSF corresponding to the second reference signal for a specified period of time after transmitting the CSF, and The one or more processors are further configured to cause the apparatus to: transmitting the CSF; and Transmitting the second CSF is refrained from based at least in part on the CSI feedback configuration.

55. The apparatus of claim 54, wherein: The second CSF includes a Type-I CSI or a Type-II CSI, and wherein the CSF and the second CSF are of the same type or of different types.

56. An apparatus for wireless communication, comprising: Memory; one or more processors coupled to the memory, wherein the one or more processors are configured to cause the apparatus to: transmitting a channel state information (CSI) feedback configuration, the CSI feedback configuration comprising an indication to save a channel state feedback (CSF) corresponding to a first reference signal carried on a downlink channel for a specified time period; as well as A differential CSF is received, the differential CSF being based at least in part on the CSF and a second reference signal carried on the downlink channel.

57. The apparatus of claim 56, wherein: The differential CSF indicates a differential type-III CSI.

58. The apparatus of claim 56, wherein: The CSI feedback configuration includes an indication to report at least one neural network-based CSI based at least in part on determining that a differential neural network-based reporting threshold is met.

59. The apparatus of claim 56, wherein: The CSF includes a neural network-based CSI, and wherein the CSI feedback configuration further indicates to suppress transmission of a second CSF corresponding to the second reference signal for a specified period of time after transmitting the CSF, and The one or more processors are further configured to cause the apparatus to receive the CSF.

60. The apparatus of claim 59, wherein: The second CSF includes a Type-I CSI or a Type-II CSI, and wherein the CSF and the second CSF are of the same type or of different types.

Images