Geometric deep learning for grid reduction

Abstract

Certain aspects of this disclosure provide techniques for wireless communication by an apparatus. Some techniques include: receiving a signal corresponding to a MIMO channel matrix; generating a first gram matrix from a basis of a first lattice corresponding to a first signal in the received signal; providing the first gram matrix to a neural lattice reduction model, the neural lattice reduction model including an equivariant neural network configured to generate a current extended Gaussian shift; generating a currently partially modified basis using the neural lattice reduction model based on the current extended Gaussian shift and the basis; performing one or more additional iterations of the neural lattice reduction model; and demapping the MIMO channel matrix based on combining the currently partially modified basis and each of the additional partially modified bases generated by each additional iteration in one or more additional iterations of the neural lattice reduction model.

Description

[0001] Cross-references to related applications

[0002] This application claims priority and benefit to U.S. Patent Application No. 18 / 410,660, filed January 11, 2024, and U.S. Patent Application No. 18 / 410,677, filed January 11, 2024, the entire contents of which are incorporated herein by reference. Background Technology Technical Field

[0004] Various aspects of this disclosure relate to wireless communication, and more specifically to techniques for lattice reduction using neural lattice reduction.

[0005] Related technical descriptions

[0006] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, broadcasting, or other similar services. These wireless communication systems can employ multiple access technologies that enable communication with multiple users by sharing available wireless communication system resources.

[0007] Despite significant technological advancements in wireless communication systems over the years, challenges remain. For example, complex and dynamic environments can still attenuate or block signals between wireless transmitters and receivers. Accordingly, there is a continuous expectation for improving the technical performance of wireless communication systems, including, for example: improving communication speed and data carrying capacity; improving the efficiency of shared communication media; reducing the power used by transmitters and receivers during communication; improving the reliability of wireless communication; avoiding redundant transmission and / or reception and related processing; improving the coverage area of ​​wireless communication; increasing the number and types of devices that can access the wireless communication system; increasing the ability of different types of devices to communicate with each other; and increasing the number and types of available wireless communication media. Therefore, there is a need for further improvements to wireless communication systems to overcome the aforementioned technical challenges and other obstacles. Summary of the Invention

[0008] Lattice reduction is useful for solving the nearest vector problem (CVP) and the shortest vector problem (SVP) on lattices, which, as examples, appear in multiple-input multiple-output (MIMO) demapping processes and standard public-key methods for post-quantum cryptography processes, respectively. Solutions to CVP and SVP are possible when the basis (B) is orthogonal or approximately orthogonal. However, not all lattices allow orthogonal bases, making the problem of finding the most orthogonal basis of a lattice (i.e., the lattice reduction problem) NP-hard and therefore infeasible to solve directly. Thus, challenges arise in the computation of lattice reduction. For example, there are challenges in developing power-efficient and computationally efficient MIMO detectors that separate spatially multiplexed data streams to fully utilize the potential of MIMO systems. Furthermore, a drawback of MIMO is the increased complexity of detectors due to the non-orthogonality of MIMO channels. Computational complexity increases exponentially with the number of antennas.

[0009] Accordingly, certain aspects of this paper provide techniques for reducing, for example, multiple lattices corresponding to MIMO channel matrices in a computationally efficient manner. Specifically, some methods described herein provide neural lattice reduction procedures that implement a recursive process for iteratively reducing lattices, providing a computationally efficient MIMO demapping process in MIMO use cases, enabling the full potential of MIMO-Orthogonal Frequency Division Multiplexing (OFDM) to be utilized. That is, in some respects, the neural lattice reduction procedure has been shown to have less runtime compared to specific implementations of the Lenstra–Lenstra–Lovász (LLL) algorithm. Such techniques can similarly provide lattice reduction with reduced computational complexity for other use cases, such as post-quantum cryptography.

[0010] One aspect provides a method for wireless communication by an apparatus. The method includes: receiving a signal corresponding to a multiple-input multiple-output (MIMO) channel matrix; generating a first gram matrix from a basis of a first lattice corresponding to a first signal in the received signal; providing the first gram matrix to a neural lattice reduction model, the neural lattice reduction model including an equivariant neural network configured to generate a current extended Gaussian shift; generating a currently partially modified basis using the neural lattice reduction model based on the current extended Gaussian shift and the basis; performing one or more additional iterations of the neural lattice reduction model, wherein each iteration includes: generating a subsequent gram matrix from the currently partially modified basis, providing the subsequent gram matrix to the equivariant neural network to generate a subsequent extended Gaussian shift, and generating an additional partially modified basis based on the subsequent extended Gaussian shift and the currently partially modified basis; and demapping the MIMO channel matrix by combining the currently partially modified basis with each of these additional partially modified bases generated by each additional iteration of the one or more additional iterations of the neural lattice reduction model.

[0011] Other aspects provide: one or more means, which are operable, configured, or otherwise adapted to perform any portion of any method described herein (e.g., such that performance can be implemented by only one means or in a distributed manner across multiple means); one or more non-transitory computer-readable media, which include instructions that, when executed by one or more processors of the one or more means, cause the one or more means to perform any portion of any method described herein (e.g., such that instructions can be included in only one computer-readable medium or in a distributed manner across multiple computer-readable media, such that instructions can be executed by only one processor or by multiple processors in a distributed manner, such that the one or more means...). Each device in the apparatus may include one or more processors, and / or enable execution to be performed by only one device or in a distributed manner across multiple devices; one or more computer program products embodied on one or more computer-readable storage media including code for performing any part of any method described herein (e.g., enabling the code to be stored in only one computer-readable medium or in a distributed manner across computer-readable media); and / or one or more devices including one or more components for performing any part of any method described herein (e.g., enabling execution to be performed by only one device or by multiple devices in a distributed manner). By way of example, an apparatus may include a processing system, a device having a processing system, or a processing system cooperating via one or more networks. An apparatus may include: one or more memories; and one or more processors configured to enable the apparatus to perform any part of any method described herein. In some examples, one or more processors may be pre-configured to perform the various functions or operations described herein without being configured by software.

[0012] For illustrative purposes, the following description and figures illustrate certain features. Attached Figure Description

[0013] The accompanying drawings depict certain features of the various aspects described herein and should not be considered as limiting the scope of this disclosure.

[0014] Figure 1 An example wireless communication network is depicted.

[0015] Figure 2 An example decomposed base station architecture is described.

[0016] Figure 3 Various aspects of the example base station and example user equipment (UE) are described.

[0017] Figure 4A , Figure 4B , Figure 4C and Figure 4D Various example aspects of data structures used in wireless communication networks are described.

[0018] Figure 5 This is a diagram illustrating an example of a MIMO model.

[0019] Figure 6 This is a diagram illustrating an example of a demodulator.

[0020] Figure 7 An illustrative block diagram of the neural grid reduction process is schematically depicted.

[0021] Figure 8 An exemplary example of equivariant message passing is depicted.

[0022] Figure 9 A method for demapping neural lattice reduction and MIMO channel matrices is described.

[0023] Figure 10 A method for neural grid reduction is described.

[0024] Figure 11 Various aspects of the example communication device are described.

[0025] Figure 12 Various aspects of the example communication device are described. Detailed Implementation

[0026] Various aspects of this disclosure provide apparatus, methods, processing systems, and computer-readable media for performing lattice reduction using neural lattice reduction.

[0027] As discussed, the lattice reduction problem is NP-hard, and therefore a direct solution is not feasible. Consequently, technical challenges arise in the computation of lattice reduction. For example, there are challenges in developing power-efficient and computationally efficient MIMO detectors that separate spatially multiplexed data streams and fully utilize the potential of MIMO systems. Furthermore, a drawback of MIMO is the increased complexity of the detector due to the non-orthogonality of MIMO channels. Computational complexity increases exponentially with the number of antennas.

[0028] Accordingly, certain aspects of this paper provide a technical solution to the technical problem by offering techniques for reducing, for example, multiple lattices corresponding to MIMO channel matrices in a computationally efficient process. In some aspects, the methods described herein provide a neural lattice reduction process that implements a recursive process for iteratively reducing lattices, providing a computationally efficient MIMO demapping process in MIMO use cases, enabling the full potential of MIMO-Orthogonal Frequency Division Multiplexing (OFDM) to be utilized. That is, in some aspects, the neural lattice reduction process has been shown to have less runtime compared to specific implementations of the Lenstra–Lenstra–Lovász (LLL) algorithm.

[0029] Linear MIMO detectors use zero-forcing (ZF) or minimum mean square error (MMSE) techniques to demap the received signal to points in the signal constellation. However, these linear MIMO detectors do not account for inter-stream interference, where one stream interferes with other streams, and therefore are generally unable to demap the received signal when the signals carried on different carriers are highly correlated. In other words, low-complexity linear MIMO detectors such as zero-forcing (ZF) or minimum mean square error (MMSE) cannot account for inter-stream interference and suffer performance degradation, especially for associated MIMO channels, and are therefore not considered a viable solution.

[0030] Some aspects of this disclosure improve existing linear MIMO detectors with minimal adaptation and provide a lightweight alternative (near-ML performance) to full maximum likelihood (ML) solutions (desmotherers based on tree-based sequential search, such as ML and spherical decoding).

[0031] Traditional lattice reduction (LR) algorithms (such as LLL) are based on simplified matrix assumptions (such as uniform distribution of lattice coefficients), but some aspects of the technique discussed in this paper can utilize the structure of channels observed in the real world and can be fine-tuned, resulting in better performance compared to LLL.

[0032] Furthermore, conventional LR heuristics cannot be easily batched for parallel execution and therefore cannot fully utilize neural accelerator chips (e.g., Neural Processing SDKs (NSPs)). In some respects, neural LR methods can fully utilize deep learning hardware and can parallelize LR across multiple lattices (across frequency and temporal distributions). The technical effect of certain aspects of the neural lattice reduction process and apparatus described in this paper can be the ability to provide significantly less runtime compared to other specific implementations of LLL.

[0033] An introduction to wireless communication networks

[0034] The techniques and methods described herein can be used in a variety of wireless communication networks. Although aspects herein may be described using terms commonly associated with 3G, 4G, 5G, 6G, and / or other generations of wireless technologies, aspects of this disclosure are equally applicable to other communication systems and standards not explicitly mentioned herein.

[0035] Figure 1 An example of a wireless communication network 100 in which the aspects described herein can be implemented is depicted.

[0036] Generally, wireless communication network 100 includes various network entities (optionally, network elements or network nodes). Network entities are typically communication devices and / or communication functions performed by communication devices (e.g., user equipment (UE), base station (BS), components of a BS, servers, etc.). Because such communication devices are part of wireless communication network 100 and facilitate wireless communication, they may be referred to as wireless communication devices. For example, various functions of the network and various devices associated with and interacting with the network may be considered network entities. Furthermore, wireless communication network 100 includes terrestrial aspects, such as terrestrial network entities (e.g., BS 102), and non-terrestrial aspects, such as satellite 140 and carrier 145, which may include onboard network entities (e.g., one or more BSs) capable of communicating with other network elements (e.g., terrestrial BSs) and UEs.

[0037] In the depicted example, wireless communication network 100 includes BS 102, UE 104 and one or more core networks (such as Evolved Packet Core (EPC) 160 and 5G Core (5GC) network 190) that interoperate to provide communication services over various communication links, including wired and wireless links.

[0038] Figure 1 Various example UE 104s are described, which may more generally include: cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players, cameras, game consoles, tablet computers, smart devices, wearable devices, vehicles, electricity meters, air pumps, large or small kitchen appliances, healthcare devices, implants, sensors / actuators, displays, Internet of Things (IoT) devices, always-on (AON) devices, edge processing devices, or other similar devices. UE 104 may also be more generally referred to as mobile devices, wireless devices, stations, mobile stations, subscriber stations, mobile subscriber stations, mobile units, subscriber units, wireless units, remote units, remote devices, access terminals, mobile terminals, wireless terminals, remote terminals, mobile phones, and others.

[0039] BS 102 communicates wirelessly with UE 104 via communication link 120 (e.g., sending or receiving signals to or from UE 104). Communication link 120 between BS 102 and UE 104 may include uplink (UL) transmission (also referred to as reverse link) from UE 104 to BS 102 and / or downlink (DL) transmission (also referred to as forward link) transmission from BS 102 to UE 104. In various aspects, communication link 120 may utilize multiple-input multiple-output (MIMO) antenna technologies, including spatial multiplexing, beamforming, and / or transmit diversity.

[0040] BS 102 may typically include: Node B, Enhanced Node B (eNB), Next Generation Enhanced Node B (ng-eNB), Next Generation Node B (gNB or gNodeB), access point, transceiver base station, radio base station, radio transceiver, transceiver functionality, transmit / receive point, and / or others. Each of BS 102 provides communication coverage for a corresponding coverage area 110, which may sometimes be referred to as a cell, and in some cases may overlap (e.g., a small cell 102' may have a coverage area 110' that overlaps with the coverage area 110 of a macro cell). For example, BS may provide communication coverage for macro cells (covering a relatively large geographic area), pico cells (covering a relatively small geographic area, such as a stadium), femtocells (covering a relatively small geographic area (e.g., a home)), and / or other types of cells.

[0041] Although BS 102 is described as a single communication device in various aspects, it can be implemented in a variety of configurations. For example, to give a few examples, one or more components of the base station can be decomposed, including a central unit (CU), one or more distributed units (DU), one or more radio units (RU), a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. In another example, various aspects of the base station can be virtualized. More generally, a base station (e.g., BS 102) can include components located at a single physical location or components located at various physical locations. In examples where the base station includes components located at various physical locations, the various components can each perform functions, such that the various components collectively achieve functionality similar to a base station located at a single physical location. In some aspects, a base station including components located at various physical locations can be referred to as a decomposed radio access network architecture (such as an open RAN (O-RAN) or virtualized RAN (VRAN) architecture). Figure 2 An example decomposed base station architecture is depicted and described.

[0042] Different BSs 102 within the wireless communication network 100 can also be configured to support different radio access technologies (such as 3G, 4G, and / or 5G). For example, a BS 102 configured for 4G LTE (collectively referred to as Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can interface with EPC 160 via a first backhaul link 132 (e.g., S1 interface). A BS 102 configured for 5G (e.g., 5G NR or Next Generation RAN (NG-RAN)) can interface with 5GC 190 via a second backhaul link 184. BSs 102 can communicate directly or indirectly (e.g., via EPC 160 or 5GC 190) on a third backhaul link 134 (e.g., X2 interface), which can be wired or wireless.

[0043] Wireless communication network 100 can subdivide the electromagnetic spectrum into various categories, bands, channels, or other characteristics. In some aspects, subdivision is provided based on wavelength and frequency, where frequency may also be referred to as carrier, subcarrier, channel, tone, or subband. For example, 3GPP currently defines frequency range 1 (FR1) as including 410MHz-7125MHz, which is often (interchangeably) referred to as “sub-6GHz”. Similarly, 3GPP currently defines frequency range 2 (FR2) as including 24,250MHz to 52,600MHz, which is sometimes (interchangeably) referred to as “millimeter wave” (“mmW” or “mmWave”). Base stations configured to communicate using mmWave / near mmWave radio bands (e.g., mmWave base stations such as BS 180) can utilize beamforming (e.g., 182) with UEs (e.g., 104) to improve path loss and range.

[0044] The communication link 120 between BS 102 and, for example, UE 104 can be via one or more carriers, which may have different bandwidths (e.g., 5MHz, 10MHz, 15MHz, 20MHz, 100MHz, 400MHz and / or other MHz) and may be aggregated in various ways. The carriers may or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated to DL compared to UL).

[0045] Compared to lower-frequency communication, communication using higher frequency bands may have higher path loss and shorter range. Accordingly, some base stations (e.g., Figure 1The beamforming 182 of the BS 180 (180) with the UE 104 can be used to improve path loss and range. For example, the BS 180 and UE 104 may each include multiple antennas, such as antenna elements, antenna panels, and / or antenna arrays, to facilitate beamforming. In some cases, the BS 180 may transmit beamformed signals to the UE 104 in one or more transmit directions 182''. The UE 104 may receive beamformed signals from the BS 180 in one or more receive directions 182''. The UE 104 may also transmit beamformed signals to the BS 180 in one or more transmit directions 182''. The BS 180 may also receive beamformed signals from the UE 104 in one or more receive directions 182''. The BS 180 and UE 104 may then perform beamforming training to determine the optimal receive and transmit directions for each of the BS 180 and UE 104. It is worth noting that the transmit and receive directions of the BS 180 may or may not be the same. Similarly, the transmission and reception directions of UE 104 may or may not be the same.

[0046] The wireless communication network 100 further includes a Wi-Fi AP 150 that communicates with a Wi-Fi station (STA) 152 via a communication link 154 in, for example, unlicensed spectrum in 2.4 GHz and / or 5 GHz.

[0047] Some UEs 104 may use device-to-device (D2D) communication link 158 to communicate with each other. The D2D communication link 158 may use one or more sidelink channels, such as physical sidelink broadcast channel (PSBCH), physical sidelink discovery channel (PSDCH), physical sidelink shared channel (PSSCH), physical sidelink control channel (PSCCH), and / or physical sidelink feedback channel (PSFCH).

[0048] EPC 160 may include various functional components, including: Mobility Management Entity (MME) 162, other MMEs 164, Serving Gateway 166, Multimedia Broadcast Multicast Service (MBMS) Gateway 168, Broadcast Multicast Service Center (BM-SC) 170, and / or Packet Data Network (PDN) Gateway 172, as in the illustrated example. MME 162 may communicate with Home Subscriber Server (HSS) 174. MME 162 is the control node that handles signaling between UE 104 and EPC 160. Generally, MME 162 provides bearer and connectivity management.

[0049] Generally, user Internet Protocol (IP) packets are transmitted through Serving Gateway 166, which is itself connected to PDN Gateway 172. PDN Gateway 172 provides UE IP address allocation and other functions. PDN Gateway 172 and BM-SC 170 are connected to IP services 176, which may include, for example, the Internet, intranets, IP Multimedia Subsystem (IMS), packet-switched (PS) streaming services, and / or other IP services.

[0050] The BM-SC 170 provides functions for MBMS user service dispatch and delivery. The BM-SC 170 can serve as an entry point for content provider MBMS transmissions, authorize and initiate MBMS bearer services within a Public Land Mobile Network (PLMN), and / or schedule MBMS transmissions. The MBMS Gateway 168 can distribute MBMS services to BS 102 within a Broadcast-Specific Service Single Frequency Network (MBSFN) area, and / or be responsible for session management (start / stop) and collecting eMBMS-related billing information.

[0051] 5GC 190 may include various functional components, including: Access and Mobility Management Function (AMF) 192, other AMFs 193, Session Management Function (SMF) 194, and User Plane Function (UPF) 195. AMF 192 may communicate with Unified Data Management (UDM) 196.

[0052] AMF 192 is the control node that handles signaling between UE 104 and 5GC 190. AMF 192 provides services such as Quality of Service (QoS) flow and session management.

[0053] Internet Protocol (IP) packets are transmitted via UPF 195, which connects to IP service 197 and provides UE IP address allocation and other functions for 5GC 190. IP service 197 may include, for example, the Internet, intranet, IMS, PS streaming service, and / or other IP services.

[0054] In various aspects, to give a few examples, network entities or network nodes can be implemented as aggregated base stations, decomposed base stations, components of base stations, integrated access and backhaul (IAB) nodes, relay nodes, and sidelink nodes.

[0055] Figure 2An example decomposed base station 200 architecture is depicted. The decomposed base station 200 architecture may include one or more central units (CUs) 210, which may communicate directly with the core network 220 via a backhaul link, or indirectly with the core network 220 through one or more decomposed base station units, such as a near real-time (near-RT) RAN Intelligent Controller (RIC) 225 via an E2 link, or a non-real-time (non-RT) RIC 215 associated with a Service Management and Orchestration (SMO) framework 205, or both. CUs 210 may communicate with one or more distributed units (DUs) 230 via corresponding midhaul links (such as F1 interfaces). DUs 230 may communicate with one or more radio units (RUs) 240 via corresponding fronthaul links. RUs 240 may communicate with a corresponding UE 104 via one or more radio frequency (RF) access links. In some specific implementations, UE 104 may be served simultaneously by multiple RUs 240.

[0056] Each unit in a cell (e.g., CU 210, DU 230, RU 240, and near-RT RIC 225, non-RT RIC 215, and SMO frame 205) may include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via a wired or wireless transmission medium. Each of the cells, or an associated processor or controller that provides instructions to the cell's communication interface, may be configured to communicate with one or more other cells via the transmission medium. For example, these cells may include a wired interface configured to receive signals or transmit signals to one or more other cells via a wired transmission medium. Additionally or alternatively, a cell may include a wireless interface that may include a receiver, transmitter, or transceiver (such as a radio frequency (RF) transceiver) configured to receive signals on a wireless transmission medium or transmit signals to one or more other cells, or both.

[0057] In some aspects, CU 210 can host one or more higher-level control functions. Such control functions may include Radio Resource Control (RRC), Packet Data Convergence Protocol (PDCP), Serving Data Adaptation Protocol (SDAP), etc. Each control function can be implemented using an interface configured to signal to other control functions hosted by CU 210. CU 210 can be configured to handle user plane functions (e.g., Central Unit-User Plane (CU-UP)), control plane functions (e.g., Central Unit-Control Plane (CU-CP)), or combinations thereof. In some implementations, CU 210 can be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, CU-UP units can communicate bidirectionally with CU-CP units via an interface such as an E1 interface. CU 210 can be implemented to communicate with DU 230 for network control and signaling, as needed.

[0058] DU 230 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RU 240s. In some aspects, DU 230 may at least partially host one or more of the Radio Link Control (RLC) layer, Medium Access Control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) according to functional splits (such as those defined by the 3rd Generation Partnership Project (3GPP). In some aspects, DU 230 may further host one or more low PHY layers. Each layer (or module) may be implemented using an interface configured to communicate signals with other layers (and modules) hosted by DU 230 or with control functions hosted by CU 210.

[0059] Lower-layer functionality can be implemented by one or more RU 240s. In some deployments, an RU240 controlled by a DU 230 may correspond to a logical node that hosts RF processing functions or low-PHY layer functions (such as performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, Physical Random Access Channel (PRACH) extraction and filtering, or both, based at least in part on functional decomposition (such as lower-layer functional decomposition). In such architectures, the RU 240 may be implemented to handle over-the-air (OTA) communications with one or more UE 104s. In some specific implementations, the real-time and non-real-time aspects of control plane and user plane communications with the RU 240 may be controlled by the corresponding DU 230. In some scenarios, this configuration enables the implementation of the DU 230 and CU 210 in cloud-based RAN architectures such as vRAN architectures.

[0060] SMO framework 205 can be configured to support RAN deployment and provisioning of both non-virtualized and virtualized network elements. For non-virtualized network elements, SMO framework 205 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via operation and maintenance interfaces such as the O1 interface. For virtualized network elements, SMO framework 205 can be configured to interact with a cloud computing platform such as Open Cloud (O-Cloud) 290 to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface such as the O2 interface. Such virtualized network elements may include, but are not limited to, CU 210, DU 230, RU 240, and near-RT RIC 225. In some implementations, SMO framework 205 can communicate with the hardware aspects of the 4G RAN (such as Open eNB (O-eNB) 211) via the O1 interface. Additionally, in some implementations, SMO framework 205 can communicate directly with one or more RU 240s via the O1 interface. SMO framework 205 may also include a non-RT RIC 215 configured to support the functionality of SMO framework 205.

[0061] The non-RT RIC 215 can be configured to include logical functions that enable non-real-time control and optimization of RAN elements and resources, including artificial intelligence / machine learning (AI / ML) workflows for model training and updates, or policy-based guidance for applications / features in the near-RT RIC 225. The non-RT RIC 215 can be coupled to or communicate with the near-RT RIC 225, such as via an A1 interface. The near-RT RIC 225 can be configured to include logical functions that enable near real-time control and optimization of RAN elements and resources via an interface, such as via an E2 interface, through data collection and actions, connecting one or more CU 210s, one or more DU 230s, or both, and O-eNBs to the near-RT RIC 225.

[0062] In some implementations, to generate AI / ML models to be deployed in the near-RT RIC 225, the non-RT RIC 215 may receive parameters or external enrichment information from an external server. This information can be utilized by the near-RT RIC 225 and may be received from non-network data sources or network functions at the SMO framework 205 or the non-RT RIC 215. In some examples, the non-RT RIC 215 or the near-RT RIC 225 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 215 may monitor long-term trends and patterns in performance and employ AI / ML models to perform corrective actions via the SMO framework 205 (such as reconfiguration via O1) or by creating RAN management policies (such as A1 policies).

[0063] Figure 3 Various aspects of examples BS 102 and UE 104 are described.

[0064] Generally, BS 102 includes various processors (e.g., 320, 330, 338, and 340), antennas 334a-334t (collectively referred to as 334), transceivers 332a-332t (collectively referred to as 332) including modulators and demodulators, and other aspects that enable the wireless transmission of data (e.g., data source 312) and the wireless reception of data (e.g., data sink 339). For example, BS 102 can transmit and receive data between BS 102 and UE 104. BS 102 includes a controller / processor 340 that can be configured to implement the various wireless communication-related functions described herein.

[0065] Generally, UE 104 includes various processors (e.g., 358, 364, 366, and 380), antennas 352a-352r (collectively referred to as 352), transceivers 354a-354r (collectively referred to as 354) including modulators and demodulators, and other aspects that enable the wireless transmission of data (e.g., retrieved from data source 362) and the wireless reception of data (e.g., provided to data sink 360). UE 104 includes a controller / processor 380 that can be configured to implement the various wireless communication-related functions described herein.

[0066] Regarding example downlink transmission, BS 102 includes a transmission processor 320 that can receive data from data source 312 and control information from controller / processor 340. This control information may be for a Physical Broadcast Channel (PBCH), Physical Control Format Indicator Channel (PCFICH), Physical Hybrid Automatic Repeat Request (HARQ) Indicator Channel (PHICH), Physical Downlink Control Channel (PDCCH), Group Common PDCCH (GC PDCCH), and / or others. In some examples, this data may be for a Physical Downlink Shared Channel (PDSCH).

[0067] The transmitter processor 320 can process data and control information (e.g., encoding and symbol mapping) to obtain data symbols and control symbols, respectively. The transmitter processor 320 can also generate reference symbols (such as those for the primary synchronization signal (PSS), secondary synchronization signal (SSS), PBCH demodulation reference signal (DMRS), and channel state information reference signal (CSI-RS)).

[0068] The transmit (TX) multiple-input multiple-output (MIMO) processor 330 can perform spatial processing (e.g., pre-decoding) on ​​data symbols, control symbols, and / or reference symbols where applicable, and can provide the output symbol stream to the modulators (MODs) in transceivers 332a to 332t. Each modulator in transceivers 332a to 332t can process the corresponding output symbol stream to obtain an output sample stream. Each modulator can further process (e.g., convert to analog, amplify, filter, and up-convert) the output sample stream to obtain a downlink signal. The downlink signal from the modulators in transceivers 332a to 332t can be transmitted via antennas 334a to 334t, respectively.

[0069] To receive downlink transmissions, UE 104 includes antennas 352a to 352r that receive downlink signals from BS 102 and provide the received signals to demodulators (DEMODs) in transceivers 354a to 354r, respectively. Each demodulator in transceivers 354a to 354r can adjust (e.g., filter, amplify, down-convert, and digitize) the corresponding received signal to obtain an input sample. Each demodulator can further process the input sample to obtain the received symbols.

[0070] The RX MIMO detector 356 acquires received symbols from all demodulators in transceivers 354a to 354r, performs MIMO detection on the received symbols where applicable, and provides the detected symbols. The receive processor 358 processes the detected symbols (e.g., demodulation, deinterleaving, and decoding), provides the decoded data of UE 104 to data sink 360, and provides the decoded control information to controller / processor 380.

[0071] Regarding the example uplink transmission, UE 104 further includes a transmission processor 364 that receives and processes data from data source 362 (e.g., for PUSCH) and control information from controller / processor 380 (e.g., for Physical Uplink Control Channel (PUCCH)). Transmission processor 364 can also generate reference symbols for reference signals (e.g., for Sounding Reference Signal (SRS)). Symbols from transmission processor 364 may be pre-decoded by TX MIMO processor 366, where applicable, further processed by modulators in transceivers 354a to 354r (e.g., for SC-FDM), and transmitted to BS 102.

[0072] At BS 102, uplink signals from UE 104 can be received by antennas 334a to 334t, processed by demodulators in transceivers 332a to 332t, detected where applicable by RX MIMO detector 336, and further processed by receiver processor 338 to obtain decoded data and control information transmitted by UE 104. Receiver processor 338 can provide the decoded data to data sink 339 and the decoded control information to controller / processor 340.

[0073] Memory 342 and memory 382 can store data and program code for BS 102 and UE 104, respectively.

[0074] Scheduler 344 can schedule UE to send data on the downlink and / or uplink.

[0075] In various respects, BS 102 can be described as transmitting and receiving various types of data associated with the methods described herein. In these contexts, “transmitting” can refer to various mechanisms that output data, such as from data source 312, scheduler 344, memory 342, transmit processor 320, controller / processor 340, TX MIMO processor 330, transceivers 332a to 332t, antennas 334a to 334t, and / or other aspects described herein. Similarly, “receiving” can refer to various mechanisms that acquire data, such as from antennas 334a to 334t, transceivers 332a to 332t, RX MIMO detector 336, controller / processor 340, receive processor 338, scheduler 344, memory 342, and / or other aspects described herein.

[0076] In various respects, UE 104 can also be described as transmitting and receiving various types of data associated with the methods described herein. In these contexts, “transmitting” can refer to various mechanisms that output data, such as from data source 362, memory 382, ​​transmit processor 364, controller / processor 380, TX MIMO processor 366, transceivers 354a to 354t, antennas 352a to 352t, and / or other aspects described herein. Similarly, “receiving” can refer to various mechanisms that acquire data, such as from antennas 352a to 352t, transceivers 354a to 354t, RX MIMO detector 356, controller / processor 380, receive processor 358, memory 382, ​​and / or other aspects described herein.

[0077] In some respects, the processor can be configured to perform various operations (such as those associated with the methods described herein) and to send (output) data to or receive data from another interface configured to send or receive data, respectively.

[0078] Figure 4A , Figure 4B , Figure 4C and Figure 4D Describes the use of wireless communication networks (such as Figure 1 All aspects of the data structure of the wireless communication network 100.

[0079] Specifically, Figure 4A Figure 400 is an example of the first subframe within a 5G (e.g., 5G NR) frame structure. Figure 4B Figure 430 illustrates an example of a DL channel within a 5G subframe. Figure 4C Figure 450 illustrates an example of the second subframe within a 5G frame structure, and Figure 4DFigure 480 illustrates an example of a UL channel within a 5G subframe.

[0080] Wireless communication systems can utilize Orthogonal Frequency Division Multiplexing (OFDM) with a cyclic prefix (CP) on both the uplink and downlink. Such systems can also support half-duplex operation using Time Division Duplex (TDD). OFDM and Single-Carrier Frequency Division Multiplexing (SC-FDM) will (e.g., as...) Figure 4B and Figure 4D The system bandwidth (as depicted in the text) is divided into multiple orthogonal subcarriers. Each subcarrier can be modulated with data. Modulation symbols can be transmitted in the frequency domain using OFDM and / or in the time domain using SC-FDM.

[0081] Wireless communication frame structures can be frequency division duplex (FDD), where for a specific set of subcarriers, subframes within that set are dedicated to either deep (DL) or ultra-low (UL). Wireless communication frame structures can also be time division duplex (TDD), where for a specific set of subcarriers, subframes within that set are dedicated to both DL and UL.

[0082] exist Figure 4A and Figure 4C In this example, the wireless communication frame structure is TDD, where D stands for DL, U for UL, and X is flexibly used between DL and UL. The UE can configure the time slot format using the received Time Slot Format Indicator (SFI) (dynamically via DL Control Information (DCI) or semi-statically / statically via Radio Resource Control (RRC) signaling). In the depicted example, a 10ms frame is divided into 10 equal-sized 1ms subframes. Each subframe may include one or more time slots. In some examples, each time slot may include 7 or 14 symbols, depending on the time slot format. Subframes may also include micro-slots, which typically have fewer symbols than the entire time slot. Other wireless communication technologies may have different frame structures and / or different channels.

[0083] In some respects, the number of time slots within a subframe is based on the time slot configuration and parameter set. For example, for time slot configuration 0, different parameter sets (μ) 0 to 5 allow for 1, 2, 4, 8, 16, and 32 time slots per subframe, respectively. For time slot configuration 1, different parameter sets 0 to 2 allow for 2, 4, and 8 time slots per subframe, respectively. Therefore, for time slot configuration 0 and parameter set μ, there are 14 symbols per time slot and 2µ time slots per subframe. The subcarrier spacing and symbol length / duration are functions of the parameter set. The subcarrier spacing can be equal to... kHz, where μ is the parameter set from 0 to 5. Therefore, the parameter set... It has a subcarrier spacing of 15 kHz and a parameter set It has a subcarrier spacing of 480 kHz. The symbol length / duration is negatively correlated with the subcarrier spacing. Figure 4A , Figure 4B , Figure 4C and Figure 4D It provides slot configuration 0 with 14 symbols per slot and parameter set with 4 slots per subframe. Example: The time slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs.

[0084] like Figure 4A , Figure 4B , Figure 4C and Figure 4D As depicted, the resource grid can be used to represent the frame structure. Each time slot includes a resource block (RB) (also known as a physical RB (PRB)) extending for, for example, 12 consecutive subcarriers. The resource grid is divided into multiple resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0085] like Figure 4A As illustrated, some REs in the RE carry information for the UE (e.g., Figure 1 and Figure 3 The reference (pilot) signal (RS) for the UE (104) may include a demodulation RS (DMRS) and / or a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and / or a phase tracking RS (PT-RS).

[0086] Figure 4B Examples of various DL channels within a subframe of a frame are illustrated. The Physical Downlink Control Channel (PDCCH) carries the DCI within one or more Control Channel Elements (CCEs), each CCE comprising, for example, nine RE groups (REGs), each REG comprising, for example, four consecutive REs in an OFDM symbol.

[0087] The Primary Synchronization Signal (PSS) can be located within symbol 2 of a specific subframe of the frame. The PSS is generated by the UE (e.g., Figure 1 and Figure 3 104) is used to determine subframe / symbol timing and physical layer identifier.

[0088] The secondary synchronization signal (SSS) can be located within symbol 4 of a specific subframe of a frame. The SSS is used by the UE to determine the physical layer cell identification group number and radio frame timing.

[0089] Based on the Physical Layer Identifier and Physical Layer Cell Identifier Group Number, the UE can determine the Physical Cell Identifier (PCI). Based on the PCI, the UE can determine the location of the aforementioned DMRS. The Physical Broadcast Channel (PBCH), carrying the Master Information Block (MIB), can be logically grouped with the PSS and SSS to form a Synchronization Signal (SS) / PBCH block. The MIB provides the number of RBs and the System Frame Number (SFN) in the system bandwidth. The Physical Downlink Shared Channel (PDSCH) carries user data, broadcast system information (such as System Information Block (SIB)) not transmitted via the PBCH, and / or paging messages.

[0090] like Figure 4C As illustrated, some REs in the REs carry DMRS for channel estimation at the base station (indicated as R for a particular configuration, but other DMRS configurations are possible). The UE can transmit DMRS for PUCCH and DMRS for PUSCH. PUSCH DMRS can be transmitted, for example, in the first or second symbol before the PUSCH. PUCCH DMRS can be transmitted in different configurations depending on whether a short or long PUCCH is being transmitted and depending on the specific PUCCH format used. UE104 can transmit a Sounding Reference Signal (SRS). SRS can be transmitted, for example, in the last symbol of a subframe. SRS can have a comb structure, and the UE can transmit SRS on one of the comb teeth. SRS can be used by the base station for channel quality estimation to enable frequency-dependent scheduling of the UL.

[0091] Figure 4D Examples of various UL channels within a subframe of a frame are illustrated. The PUCCH can be located as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), pre-decoding matrix indicators (PMI), rank indicators (RI), and HARQ ACK / NACK feedback. The PUSCH carries data and may additionally be used to carry buffer status reports (BSR), power clearance reports (PHR), and / or UCI.

[0092] MIMO demapping using lattice reduction (LR)

[0093] Figure 5 This is an example illustration of the MIMO model 500. The lattice is a grid in any dimension. More formally, an n-dimensional lattice is a lattice with the highest rank. The discrete subgroup of .

[0094] if It is the receiving space ( ) in the grid ( Then there exists a group isomorphism. This isomorphism determines the basis of the lattice (i.e., linearly independent vectors). The set of (a set of) such that .base( ) by invertible matrix In short, the columns of this invertible matrix are basis vectors. Any two basis vectors... By (right) multiplying by an integer invertible matrix (i.e., for a certain , ,in Q It is related to the basis transformation matrix. It belongs to... The matrix is ​​considered to be monomorphic.

[0095] As noted above, lattices present two fundamental computational problems. SVP is reduced to CVP, and it is known that SVP is NP-hard under randomized reduction.

[0096] Not all bases are created identically. An ideal base is an orthogonal base, i.e., such that... H T H It is diagonal. However, not all lattices allow orthogonal bases, and quantities whose bases are not orthogonal are determined by... The orthogonality defect is Measurement.

[0097] Given the basis of the lattice This can be achieved by minimizing the orthogonality defect. To find the basis of the specification However, the problem described above is NP-hard, and therefore a direct solution is not feasible.

[0098] Some aspects discussed in this paper provide neural lattice reduction processes using deep learning. For example, some aspects involve... Training format for the target: The model. Lattice reduction exhibits two types of symmetry: left orthogonality invariance: for all , ; and right monomorphism, etc.: for all , Some aspects discussed in this paper address how to design using neural lattice reduction models. To meet the challenges of the two aforementioned properties.

[0099] Multiple-input multiple-output (MIMO) wireless systems employ multiple antennas on both the transmitting and receiving sides, and provide improved spectral efficiency compared to single-antenna systems.

[0100] In the context of MIMO signal processing, for example, Figure 5 As depicted, multiple transmitting antennas transmit signals to multiple receiving antennas. x i .Signal, The transmission is modeled as a noisy linear process (i.e.: ), and was decoded as The set of possible transmitted (noise-free) signals in the receiving space. The lattice is defined in the middle. MIMO decoding is an instance of the nearest vector problem (CVP).

[0101] MIMO technology can be used to achieve high data rates by transmitting signals from multiple antennas for reception by multiple antennas. MIMO wireless systems employ multiple antennas on both the transmitting and receiving sides and offer improved spectral efficiency compared to single-antenna systems. MIMO-OFDM achieves high data rates (data throughput) by transmitting multiple data streams in parallel within the same frequency band (a process known as spatial multiplexing).

[0102] At the receiver, various demappers can be used to decode the received signal and provide it to the error correction block for further processing. Since calculating the probability estimate of the transmitted bits to be used as input to the error correction block is typically a computationally complex task, the neural lattice reduction process described in this paper adds minimal complexity compared to existing linear schemes while enhancing detection performance.

[0103] Aspects related to the demolition of the grid specification

[0104] Figure 6 This is a diagram illustrating examples of a demodulator 600 according to the various aspects described herein. In some aspects, the demodulator 600 may be a wireless communication device (such as UE 104, base station (BS 102 / 180)) and / or Figures 1 to 3 The demodulator 600 is part of a component of a decomposed base station. For example, the demodulator 600 may be part of a transceiver 354 / 332, an RX MIMO detector 356 / 336, and / or a receive processor 358 / 338. The demodulator 600 includes a receive component 605 and an LR component 610. One or more of the components 605 to 610 of the demodulator 600 may be part of a transceiver 354 / 332, an RX MIMO detector 356 / 336, and / or a receive processor 358. Each of the components 605 to 610 of the demodulator 600 may correspond to one or more hardware components specifically configured to perform the stated process / algorithm, implemented by one or more processors configured to execute the stated process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof.

[0105] The receiving component 605 is configured to receive signals from, for example, another wireless communication device (e.g., UE 104, base station (BS 102 / 180) and / or Figures 1 to 3 The receiving component 605 receives communication (as part of a decomposed base station). For example, a network entity may transmit communication to UE 104 in a communication channel (corresponding to a frequency range), or vice versa, which is received by the receiving component 605, such as using multiple antennas. Communication may take the form of one or more beamformed transmissions scheduled for one or more REs of a wireless communication device. In some aspects, communication in the form of one or more beamformed transmissions may correspond to one or more modulated signals. The receiving component 605 outputs a vector. This vector is a representation of the received signaling, which includes one or more beamforming transmissions, such as signaling received over a communication channel (e.g., over one or more REs scheduled for a wireless communication device) via each of multiple antennas. In some respects, the LR component 610 is deploying geometric machine learning to approximate lattice reduction, as in... Figure 7 A more detailed description is provided below.

[0106] Aspects related to neural grid reduction methods

[0107] Figure 7 This is an example of a lattice reduction component 700 that includes neural lattice reduction processes (such as references). Figure 6 A block diagram of an example of the LR component 610 discussed is provided. This document describes the neural lattice reduction process with reference to a specific implementation of the MIMO demapping process. In some aspects, devices such as UE 104 or network entities receive signals corresponding to the MIMO channel matrix.

[0108] The input 710 of model 720 is a grid corresponding to the first signal in the received signal. base The output 730 of model 720 can be one of the following: a first output and / or a second output. The first output is the basis transformation matrix. In this case, the approximate isovariant mapping is about It is isotropic and has discrete values. The second output is... In this case, the approximate mapping is about It is invariant and has continuous values. In either case, the natural candidate for the objective used in the model is the orthogonality defect. The orthogonality defect regarding H′ It is differentiable. Since the orthogonality defect has a multiplicative form (e.g., the orthogonality defect involves products, determinants, etc.), consider the logarithmic objective: It can be convenient.

[0109] Model 720 includes a Gram matrix component 722, an equivariant neural network 724, an extended Gaussian shift component 726, and a recursive component 728.

[0110] Gram matrix component 722 is derived from the base of the first cell corresponding to the first signal in the received signal. H Generate the first gram matrix ( G=H T H ).

[0111] By using the Gram matrix As input, orthogonality invariance is achieved. The latter, relative to the right monomodulus, acts according to... A transformation is performed. To simplify the notation, the equivariant neural network 724 can be represented as... It can receive or As input, the first Gram matrix can be provided to the equivariant neural network 724. The equivariant neural network 724 can be configured to generate the current extended Gaussian shift.

[0112] Additionally, due to the overall The isovariability is too difficult to determine. Model 720 can consider only significant subgroups, i.e., by... The group of hyperoctahedrons is given by a symbolic permutation matrix. This significant subgroup is an isometric group of both hyperoctahedra and hypercubes, and can be viewed as a discrete simulation of an orthogonal group.

[0113] Model 720 can be recursively applied to equivariant neural networks 724 In order to gradually understand the grid Perform regulation. Isovariant properties. It is compatible with this recursion.

[0114] At each iteration, The output is a matrix in the following form (referred to as an extended Gaussian shift):

[0115] The extended Gaussian shift is 1 on the diagonal and 0 at every position except for single rows and columns. Each Can be written The product of extended Gaussian shifts.

[0116] To obtain the matrix referred to as the extended Gaussian shift (located at the extended Gaussian shift component 726), the following steps are performed. Given a matrix generated by an equivariant neural network 724 (e.g., having a graph neural network architecture). via Gumbel-Softmax to The absolute value of the log-likelihood is sampled for index (i, j). Then, for each value... m i,jDiscretization is performed via random rounding, for example, by rounding each value up or down with a probability proportional to the rounding error. Next, while retaining... M The i row and number j Simultaneously, the sampling is transformed into an extended Gaussian shift by masking the diagonal and all other entries. In some respects, the retained values ​​are discretized via random rounding, which can be an unbiased and differentiable discretization technique.

[0117] Furthermore, the model that outputs M from G can be designed to satisfy... A message-passing graph neural network architecture. For example, the graph under consideration has index pairs ( i,j ) as vertices and the following adjacency matrix ,in This represents the Kronecker delta function. In some respects, It is possible to assume only Different values, for example, Figure 8 The description. The description of from arrive Fifteen (15) possible messages.

[0118] Return to reference Figure 7 In some respects, the equivariant neural network 724 is suitable for... The message is propagated in the next iteration as follows: .here, It is a multilayer perceptron (MLP).

[0119] Model 720 is based on the current extended Gaussian shift from the equivariant neural network 724. T i ) and base ( H To generate the base that has been partially changed ( ) H '= HT i In some respects, model 720 is further configured to perform one or more additional iterations. In some respects, each iteration includes a base that has been changed from the current part ( ). H ') Generate subsequent Gram matrices ( G '), and this subsequent Gram matrix ( G=H T H ) is provided to the equivariant neural network to generate subsequent extended Gaussian shift ( T i+n ), and based on this subsequent extended Gaussian shift ( T i+n ) and the base that the current part changes ( H ') to generate a base with altered additional parts (H ′= HT i ′).

[0120] In some respects, the process of combining the currently partially modified basis with each of the additional partially modified basis components forms the basis of the first reduced lattice using the reduced basis components (e.g., output 730). In the MIMO demapping use case, this process can continue to demapping the MIMO channel matrix based on combining the currently partially modified basis with each of the additional partially modified basis components generated in each of the additional additional iterations of one or more additional iterations of the neural lattice reduced model.

[0121] In some respects, Model 720 is parallelizable. That is, in some respects, the neural method described with respect to Model 720 is suitable for batch processing of multiple lattices simultaneously on modern hardware. The parallelizability of Model 720 provides technical benefits superior to conventional lattice reduction heuristics. For example, each spatially separated signal received by each of a plurality of individual antennas produces a separate lattice. In some respects, each lattice within a lattice can be reduced in parallel by executing Model 720 in parallel. Furthermore, in some respects, Model 720 can fully utilize deep learning hardware and can parallelize lattice reduction across multiple lattices (across frequency and time distributions).

[0122] Example Operation

[0123] Figure 9 It shows a device (such as) Figure 1 and Figure 3 Method 900 for wireless communication of UE 104.

[0124] Method 900 begins at block 905 with receiving a signal corresponding to the MIMO channel matrix.

[0125] Then, method 900 proceeds to block 910, where a first gram matrix is ​​generated from the basis of the first gram corresponding to the first signal in the received signal.

[0126] Then, method 900 proceeds to box 915, where a first gram matrix is ​​provided to a neural lattice reduction model, which includes an equivariant neural network configured to generate the current extended Gaussian shift.

[0127] Then, method 900 proceeds to box 920, where the basis of the current partial change is generated using a neural lattice reduction model based on the current extended Gaussian shift and basis.

[0128] Then, method 900 proceeds to box 925, where one or more additional iterations of the neural lattice reduction model are performed, wherein each iteration includes: generating a subsequent gram matrix from the currently partially changed basis, feeding the subsequent gram matrix to the equivariant neural network to generate a subsequent extended Gaussian shift, and generating an additional partially changed basis based on the subsequent extended Gaussian shift and the currently partially changed basis.

[0129] Then, method 900 proceeds to block 930, where the MIMO channel matrix is ​​demapped based on combining the basis of the currently partially changed basis and the basis of each additional partially changed basis generated by each additional iteration in one or more additional iterations of the neural lattice reduction model.

[0130] In some respects, the basis of the first reduction of the first lattice is formed by combining the basis of the current partial change and the basis of the additional partial change of each of the additional partial changes.

[0131] In some respects, method 900 also includes generating a second gram matrix from the basis of a second lattice corresponding to a second signal in the received signal.

[0132] In some respects, method 900 also includes using a neural lattice reduction model to generate one or more second-part altered bases for the second lattice.

[0133] In some respects, method 900 also includes generating a second reduction basis of the second lattice based on one or more second-part modified bases, wherein one or more processors generate the bases of the first reduction and the second reduction through parallel processing of the neural lattice reduction model.

[0134] In some respects, the device includes multiple antennas, wherein a first signal of the received signals is received by a first antenna of the multiple antennas, and a second signal of the received signals is received by a second antenna of the multiple antennas.

[0135] In some respects, parallel processing of neural lattice reduction models is achieved through batch processing by graphics processing units.

[0136] In some respects, method 900 also includes demapping the MIMO channel matrix based on the basis of the first and second reductions.

[0137] In some respects, the basis of the first reduction is more orthogonal and shorter than the basis of the first lattice corresponding to the MIMO channel matrix.

[0138] In some respects, the device includes multiple antennas configured to receive signals, wherein the received signals are distributed across time and frequency.

[0139] In some respects, method 900 or any aspect thereof may be made by means of a device (such as...) Figure 11 The communication device 1100 performs the method 900, which includes various components capable of operating, being configured, or adapted to perform the method. The communication device 1100 is described in further detail below.

[0140] It should be noted that Figure 9 This is merely one example of a method, and other methods that include fewer, additional, or alternative operations may also be consistent with this disclosure.

[0141] Figure 10 It shows a device (such as) Figure 1 and Figure 3 Method 1000 for wireless communication of UE 104.

[0142] Method 1000 begins at box 1005 by providing the first gram matrix to the neural lattice reduction model.

[0143] Then, method 1000 proceeds to box 1010, where a neural lattice reduction model is used to generate one or more partially modified bases.

[0144] Then, method 1000 proceeds to box 1015, where the basis of the first reduction is generated based on one or more partially modified bases.

[0145] In some respects, the neural lattice reduction model includes an equivariant neural network configured to generate the current extended Gaussian shift.

[0146] In some respects, method 1000 further includes generating a first gram matrix from the basis of a first lattice corresponding to a first signal among a plurality of received signals, wherein one or more partially modified bases generated by the neural lattice reduction model are based at least on the current extended Gaussian shift and basis.

[0147] In some respects, method 1000 further includes performing multiple additional iterations of the neural lattice reduction model, wherein each iteration includes: generating a subsequent Gram matrix from one of the partially modified bases of one or more partially modified bases, providing the subsequent Gram matrix to the neural lattice reduction model to generate a subsequent extended Gaussian shift, and generating additional partially modified bases based on the subsequent extended Gaussian shift and the one or more partially modified bases.

[0148] In some respects, method 1000 also includes providing a second gram matrix from the basis of the second lattice.

[0149] In some respects, method 1000 also includes using a neural lattice reduction model to generate one or more second-part altered bases for the second lattice.

[0150] In some respects, method 1000 also includes generating a basis for the second reduction of the second lattice based on one or more second-part modified bases, wherein one or more processors generate the basis for the first reduction and the basis for the second reduction through parallel processing of the neural lattice reduction model.

[0151] In some respects, parallel processing of neural lattice reduction models is achieved through batch processing by graphics processing units.

[0152] In some respects, method 1000 further includes generating a first gram matrix from the basis of a first lattice corresponding to a first signal among a plurality of received signals.

[0153] In some respects, multiple received signals correspond to a MIMO channel matrix.

[0154] In some respects, the device includes multiple antennas, wherein a first signal of the multiple received signals is received by a first antenna of the multiple antennas, and a second signal of the multiple received signals is received by a second antenna of the multiple antennas.

[0155] In some respects, method 1000 also includes a basis for a first specification that combines one or more partially modified bases to form a first lattice.

[0156] In some respects, method 1000 or any aspect thereof may be made by means of a device (such as...) Figure 12 The communication device 1200 performs the operation, and the device includes various components that are operable, configured, or adapted to perform the method 1000. The communication device 1200 is described in further detail below.

[0157] It should be noted that Figure 10 This is merely one example of a method, and other methods that include fewer, additional, or alternative operations may also be consistent with this disclosure.

[0158] Example communication device

[0159] Figure 11 Various aspects of the example communication device 1100 are depicted. In some aspects, the communication device 1100 is a wireless communication device, such as a UE 104, a base station (BS 102 / 180), and / or Figures 1 to 3 Components of a decomposed base station.

[0160] Communication device 1100 includes a processing system 1105 coupled to a transceiver 1175 (e.g., a transmitter and / or receiver). Transceiver 1175 is configured to transmit and receive signals for communication device 1100 via antenna 1180, such as various signals as described herein. Processing system 1105 may be configured to perform processing functions of communication device 1100, including processing signals received by and / or to be transmitted by communication device 1100.

[0161] Processing system 1105 includes one or more processors 1110. In various aspects, the one or more processors 1110 may represent one or more of a receive processor 358, a transmit processor 364, a TX MIMO processor 366, and / or a controller / processor 380, as per [reference to...]. Figure 3 As described. One or more processors 1110 are coupled to a computer-readable medium / memory 1140 via a bus 1170. In some aspects, the computer-readable medium / memory 1140 is configured to store instructions (e.g., computer-executable code) that, when executed by one or more processors 1110, enable one or more processors 1110 to execute and cause the one or more processors to perform actions related to... Figure 9 The described method 900 or any aspect thereof, including regarding Figure 9 Any operation described. Note that references to processors performing the functions of communication device 1100 may include one or more processors, such as performing the functions of communication device 1100 in a distributed manner.

[0162] In the depicted example, computer-readable medium / memory 1140 stores code 1145 for receiving, code 1150 for generating, code 1155 for providing, code 1160 for executing, and code 1165 for demapping. Processing of codes 1145 to 1165 enables communication device 1100 to execute and perform actions related to... Figure 9 The method described 900 or any aspect thereof.

[0163] One or more processors 1110 include circuitry configured to implement (e.g., execute) code stored in computer-readable medium / memory 1140, including circuitry 1115 for receiving, circuitry 1120 for generating, circuitry 1125 for providing, circuitry 1130 for executing, and circuitry 1135 for demapping. Processing using circuitry 1115 to 1135 enables communication device 1100 to execute and perform actions related to... Figure 9 The method described 900 or any aspect thereof.

[0164] More generally, components used for conveying, sending, transmitting, or outputting for transmission may include Figure 3 The UE104 illustrated includes a transceiver 354, an antenna 352, a transmit processor 364, a TX MIMO processor 366, an AI processor 370, and / or a controller / processor 380. Figure 11 The transceiver 1175 and / or antenna 1180 of the communication device 1100 in the middle Figure 11 One or more processors 1110 of the communication device 1100. Components for transmitting, receiving, or acquiring may include... Figure 3 The UE 104 illustrated includes a transceiver 354, an antenna 352, a receiver processor 358, an AI processor 370, and / or a controller / processor 380. Figure 11 The transceiver 1175 and / or antenna 1180 of the communication device 1100 in the middle Figure 11 One or more processors 1110 of the communication device 1100 in the middle.

[0165] Figure 12 Various aspects of the example communication device 1200 are depicted. In some aspects, the communication device 1200 is a wireless communication device, such as a UE 104, a base station (BS 102 / 180), and / or Figures 1 to 3 Components of a decomposed base station.

[0166] Communication device 1200 includes a processing system 1205 coupled to a transceiver 1265 (e.g., a transmitter and / or receiver). Transceiver 1265 is configured to transmit and receive signals for communication device 1200 via antenna 1270, such as various signals as described herein. Processing system 1205 may be configured to perform processing functions of communication device 1200, including processing signals received by and / or to be transmitted by communication device 1200.

[0167] Processing system 1205 includes one or more processors 1210. In various aspects, the one or more processors 1210 may represent one or more of a receive processor 358, a transmit processor 364, a TX MIMO processor 366, and / or a controller / processor 380, as per [reference to...]. Figure 3 As described. One or more processors 1210 are coupled to a computer-readable medium / memory 1235 via a bus 1260. In some aspects, the computer-readable medium / memory 1235 is configured to store instructions (e.g., computer-executable code) that, when executed by one or more processors 1210, enable one or more processors 1210 to execute and cause the one or more processors to perform actions regarding... Figure 10 The described method 1000 or any aspect thereof, including regarding Figure 10Any operation described. Note that references to processors performing the functions of communication device 1200 may include one or more processors, such as performing the functions of communication device 1200 in a distributed manner.

[0168] In the depicted example, computer-readable medium / memory 1235 stores code 1240 for provisioning, code 1245 for generation, code 1250 for execution, and code 1255 for combination. Processing of codes 1240 to 1255 enables communication device 1200 to execute and perform actions related to... Figure 10 The method 1000 described or any aspect thereof.

[0169] One or more processors 1210 include circuitry configured to implement (e.g., execute) code stored in a computer-readable medium / memory 1235, including circuitry 1215 for providing, circuitry 1220 for generating, circuitry 1225 for executing, and circuitry 1230 for combining. Processing using circuitry 1215 to 1230 enables communication device 1200 to execute and perform actions related to... Figure 10 The method 1000 described or any aspect thereof.

[0170] More generally, components used for conveying, sending, transmitting, or outputting for transmission may include Figure 3 The UE104 illustrated includes a transceiver 354, an antenna 352, a transmit processor 364, a TX MIMO processor 366, an AI processor 370, and / or a controller / processor 380. Figure 12 The transceiver 1265 and / or antenna 1270 of the communication device 1200 Figure 12 One or more processors 1210 of the communication device 1200. Components for transmitting, receiving, or acquiring may include... Figure 3 The UE 104 illustrated includes a transceiver 354, an antenna 352, a receiver processor 358, an AI processor 370, and / or a controller / processor 380. Figure 12 The transceiver 1265 and / or antenna 1270 of the communication device 1200 Figure 12 One or more processors 1210 of the communication device 1200.

[0171] Example Terms

[0172] Specific implementation examples are described in the following numbered clauses: Clause 1: A method for wireless communication by means of an apparatus, the method comprising: receiving a signal corresponding to a MIMO channel matrix; generating a first gram matrix from a basis of a first lattice corresponding to a first signal in the received signal; providing the first gram matrix to a neural lattice reduction model, the neural lattice reduction model including an equivariant neural network configured to generate a current extended Gaussian shift; generating a currently partially modified basis using the neural lattice reduction model based on the current extended Gaussian shift and the basis; performing one or more additional iterations of the neural lattice reduction model, wherein each iteration comprises: generating a subsequent gram matrix from the currently partially modified basis, providing the subsequent gram matrix to the equivariant neural network to generate a subsequent extended Gaussian shift, and generating an additional partially modified basis based on the subsequent extended Gaussian shift and the currently partially modified basis; and demapping the MIMO channel matrix by combining the currently partially modified basis and each of the additional partially modified bases generated by each additional iteration of the one or more additional iterations of the neural lattice reduction model.

[0173] Clause 2: The method according to Clause 1, wherein the basis of the first specification of the first lattice is formed by combining the basis of the current part change and the basis of the additional part change.

[0174] Clause 3: The method according to Clause 2 further comprises: generating a second gram matrix from a second basis of a second lattice corresponding to a second signal in the received signal; generating a basis of one or more second-part alterations of the second lattice using the neural lattice reduction model; and generating a basis of a second reduction of the second lattice based on the one or more second-part alterations, wherein the basis of the first reduction and the basis of the second reduction are generated by parallel processing of the neural lattice reduction model.

[0175] Clause 4: The method according to Clause 3, wherein the device comprises a plurality of antennas, wherein the first signal of the received signals is received by a first antenna of the plurality of antennas, and the second signal of the received signals is received by a second antenna of the plurality of antennas.

[0176] Clause 5: The method described in Clause 3, wherein the parallel processing of the neural lattice reduction model is achieved through batch processing by a graphics processing unit.

[0177] Clause 6: The method according to Clause 3 further includes demapping the MIMO channel matrix based on the basis of the first protocol and the basis of the second protocol.

[0178] Clause 7: The method according to Clause 2, wherein the basis of the first reduction is more orthogonal and shorter than the basis of the first lattice corresponding to the MIMO channel matrix.

[0179] Clause 8: The method according to any one of Clauses 1 to 7, wherein the received signal is distributed across time and frequency.

[0180] Clause 9: A method for wireless communication by a device, the method comprising: providing a first gram matrix to a neural lattice reduction model; generating one or more partially modified bases using the neural lattice reduction model; and generating a base for the first reduction based on the one or more partially modified bases.

[0181] Item 10: The method according to Item 9, wherein the neural lattice reduction model includes an equivariant neural network configured to generate the current extended Gaussian shift.

[0182] Clause 11: The method according to Clause 10 further includes generating the first gram matrix from the basis of a first lattice corresponding to a first signal among a plurality of received signals, wherein the basis of the one or more partially modified by the neural lattice reduction model is based at least on the current extended Gaussian shift and the basis.

[0183] Clause 12: The method according to any one of Clauses 9 to 11, the method further comprising performing multiple additional iterations of the neural lattice reduction model, wherein each iteration comprises: generating a subsequent Gram matrix from one of the one or more partially modified bases, providing the subsequent Gram matrix to the neural lattice reduction model to generate a subsequent extended Gaussian shift, and generating additional partially modified bases based on the subsequent extended Gaussian shift and the one or more partially modified bases.

[0184] Clause 13: The method according to any one of Clauses 9 to 12, the method further comprising: providing a second gram matrix from a basis of a second lattice; generating a basis of one or more second-part alterations of the second lattice using the neural lattice reduction model; and generating a basis of a second reduction of the second lattice based on the one or more second-part alterations of the basis, wherein the one or more processors generate the basis of the first reduction and the basis of the second reduction through parallel processing of the neural lattice reduction model.

[0185] Clause 14: The method according to Clause 13, wherein the parallel processing of the neural lattice reduction model is achieved through batch processing by a graphics processing unit.

[0186] Clause 15: The method according to any one of Clauses 9 to 14, the method further comprising: generating the first gram matrix from a basis of a first cell corresponding to a first signal among a plurality of received signals.

[0187] Clause 16: The method according to Clause 15, wherein the plurality of received signals correspond to a MIMO channel matrix.

[0188] Clause 17: The method according to Clause 16, wherein the first signal of the plurality of received signals is received by a first antenna of the plurality of antennas, and the second signal of the plurality of received signals is received by a second antenna of the plurality of antennas.

[0189] Clause 18: The method according to any one of Clauses 9 to 17, the method further comprising: combining the bases of the one or more partially modified portions to form the base of the first specification of the first lattice.

[0190] Clause 19: One or more apparatuses comprising: one or more memories including executable instructions; and one or more processors configured to execute the executable instructions and cause the one or more apparatuses to perform the method according to any one of Clauses 1 to 18.

[0191] Clause 20: One or more devices, the one or more devices comprising: one or more memories; and one or more processors, the one or more processors being coupled to the one or more memories and configured to cause the one or more devices to perform the method according to any one of Clauses 1 to 18.

[0192] Clause 21: One or more means comprising: one or more memories; and one or more processors coupled to the first plurality of memories and configured to perform the method according to any one of Clauses 1 to 18.

[0193] Clause 22: One or more apparatuses, said one or more apparatuses comprising components for performing the method according to any one of Clauses 1 to 18.

[0194] Clause 23: One or more non-transitory computer-readable media, the one or more non-transitory computer-readable media comprising executable instructions that, when executed by one or more processors of one or more devices, cause the one or more devices to perform the method according to any one of Clauses 1 to 18.

[0195] Clause 24: One or more computer program products embodied on one or more computer-readable storage media, the one or more computer-readable storage media including code for performing the method according to any one of Clauses 1 to 18.

[0196] Clause 25: A user equipment (UE) comprising: a processing system including processor circuitry and memory circuitry storing code and coupled to the processor circuitry, the processing system being configured to cause the UE to perform a method according to any one of Clauses 1 to 18.

[0197] Clause 26: A network entity comprising: a processing system including processor circuitry and memory circuitry storing code and coupled to the processor circuitry, the processing system being configured to cause the network entity to perform a method according to any one of Clauses 1 to 18.

[0198] Additional Notes

[0199] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. The examples discussed herein do not limit the scope, applicability, or aspects set forth in the claims. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. For example, the function and arrangement of the elements discussed may be changed without departing from the scope of this disclosure. Various processes or components may be omitted, substituted, or added as appropriate in the various examples. For example, the described methods may be performed in a different order than described, and various actions may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined in some other examples. For example, any number of aspects set forth herein may be used to implement an apparatus or practice. Additionally, the scope of this disclosure is intended to cover such apparatuses or methods practiced using other structures, functionalities, or structures and functionalities that complement or replace the various aspects of this disclosure set forth herein. It should be understood that any aspect of the disclosure herein may be embodied by one or more elements of the claims.

[0200] The various exemplary logic blocks, modules, and circuits described in this disclosure can be implemented or executed using a general-purpose processor, digital signal processor (DSP), ASIC, field-programmable gate array (FPGA) or other programmable logic device (PLD), discrete gate or transistor logic device, discrete hardware component, or any combination thereof designed to perform the functions described herein. While the general-purpose processor may be a microprocessor, in alternative embodiments, the processor may be any commercially available processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors working in conjunction with a DSP core, a system-on-a-chip (SoC), or any other such configuration.

[0201] As used in this article, the phrase “at least one of” in a list of items refers to any combination of those items, including a single member. For example, “at least one of a, b, or c” is intended to cover a, b, c, ab, ac, bc, and abc, as well as any combination with multiple identical elements (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbb, bbc, cc, and ccc, or any other ordering of a, b, and c).

[0202] As used herein, the term "determine" encompasses a wide variety of actions. For example, "determine" can include calculation, operation, processing, deduction, investigation, lookup (e.g., searching in a table, database, or other data structure), assertion, etc. Additionally, "determine" can include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), etc. Furthermore, "determine" can include parsing, selecting, picking, building, etc.

[0203] As used herein, unless otherwise stated, “coupled to” and “coupled with” generally encompass both direct and indirect coupling (e.g., including intermediate aspects of coupling). For example, stating that a processor is coupled to memory allows for direct coupling or coupling via an intermediate aspect such as a bus.

[0204] The methods disclosed herein include one or more actions for implementing the methods. These method actions may be interchanged without departing from the scope of the claims. In other words, unless a specified order of actions is given, the order and / or use of a particular action may be modified without departing from the scope of the claims. Furthermore, the various operations of the methods described above can be performed by any suitable component capable of performing the corresponding function. This component may include various hardware and / or software components and / or modules, including but not limited to circuits, application-specific integrated circuits (ASICs), or processors.

[0205] The following claims are not intended to be limited to the aspects shown herein, but should be given the full scope consistent with the language of the claims. References to elements in the singular form are not intended to mean “only one” (unless specifically stated otherwise), but rather “one or more.” For example, unless specifically stated otherwise, references to elements (e.g., “processor,” “controller,” “memory,” etc.) should be understood to mean one or more elements (e.g., “one or more processors,” “one or more controllers,” “one or more memories,” etc.). The terms “set” and “group” are intended to include one or more elements and are used interchangeably with “one or more.” In the case of references to one or more elements performing a function (e.g., steps of a method), one element may perform all the functions, or more than one element may perform these functions collectively. When more than one element performs these functions collectively, each function does not need to be performed by every single element (e.g., different functions may be performed by different elements), and / or each function does not need to be performed by only one element overall (e.g., different elements may perform different sub-functions of a function). Similarly, when referring to one or more elements configured to cause another element (e.g., a device) to perform a function, one element may be configured to cause the other element to perform all functions, or more than one element may be collectively configured to cause the other element to perform those functions. Unless otherwise specifically stated, the term "some" refers to one or more. All structural and functional equivalents of the various aspects described throughout this disclosure that are currently or hereafter known to those skilled in the art are intended to be covered by the claims. Furthermore, nothing disclosed herein is intended to be offered to the public, whether or not such disclosure is explicitly recited in the claims.

Claims

1. An apparatus configured for wireless communication, the apparatus comprising: One or more memory units; and One or more processors, said one or more processors being coupled to said one or more memories and configured to cause the device to: Receive signals corresponding to a multiple-input multiple-output (MIMO) channel matrix; Generate the first gram matrix from the basis of the first cell corresponding to the first signal in the received signal; The first gram matrix is ​​provided to the neural lattice reduction model, which includes an equivariant neural network configured to generate the current extended Gaussian shift; The neural lattice reduction model is used to generate the currently partially changed basis based on the current extended Gaussian shift and the basis; Perform one or more additional iterations of the neural lattice reduction model, wherein each iteration includes: Generate subsequent Gram matrices from the basis that has been partially changed. The subsequent Gram matrix is ​​provided to the equivariant neural network to generate a subsequent extended Gaussian shift, and The basis for additional partial changes is generated based on the subsequent extended Gaussian shift and the basis of the current partial change; as well as The MIMO channel matrix is ​​demapped by combining the basis of the currently partially changed basis and each of the additional partially changed basis generated by each additional iteration in one or more additional iterations of the neural lattice reduction model.

2. The apparatus of claim 1, wherein each of the additionally modified bases of the currently modified base and the additionally modified base is combined to form the base of the first specification of the first lattice.

3. The apparatus of claim 2, wherein the one or more processors are configured to further cause the apparatus to: Generate a second gram matrix from the second basis of the second lattice corresponding to the second signal in the received signal; The neural lattice reduction model is used to generate one or more second-part modified bases for the second lattice; and The basis of the second reduction of the second lattice is generated based on the basis of the one or more second-part changes, wherein the one or more processors generate the basis of the first reduction and the basis of the second reduction through parallel processing of the neural lattice reduction model.

4. The apparatus of claim 3, further comprising a plurality of antennas, wherein the first signal of the received signals is received by a first antenna of the plurality of antennas, and the second signal of the received signals is received by a second antenna of the plurality of antennas.

5. The apparatus of claim 3, wherein the parallel processing of the neural lattice reduction model is achieved through batch processing by a graphics processing unit.

6. The apparatus of claim 3, wherein the one or more processors are configured to further cause the apparatus to demap the MIMO channel matrix based on the basis of the first protocol and the basis of the second protocol.

7. The apparatus of claim 2, wherein the basis of the first reduction is more orthogonal and shorter than the basis of the first lattice corresponding to the MIMO channel matrix.

8. The apparatus of claim 1, further comprising a plurality of antennas configured to receive the signal, wherein the received signal is distributed across time and frequency.

9. A method for wireless communication by a device, the method comprising: Receive signals corresponding to a multiple-input multiple-output (MIMO) channel matrix; Generate the first gram matrix from the basis of the first cell corresponding to the first signal in the received signal; The first gram matrix is ​​provided to the neural lattice reduction model, which includes an equivariant neural network configured to generate the current extended Gaussian shift; The neural lattice reduction model is used to generate the currently partially changed basis based on the current extended Gaussian shift and the basis; Perform one or more additional iterations of the neural lattice reduction model, wherein each iteration includes: generating a subsequent Gram matrix from the currently partially changed basis, providing the subsequent Gram matrix to the equivariant neural network to generate a subsequent extended Gaussian shift, and generating an additional partially changed basis based on the subsequent extended Gaussian shift and the currently partially changed basis; as well as The MIMO channel matrix is ​​demapped by combining the basis of the currently partially changed basis and each of the additional partially changed basis generated by each additional iteration in one or more additional iterations of the neural lattice reduction model.

10. The method of claim 9, wherein each of the additionally modified bases of the currently partially modified base and the additionally modified base is combined to form the base of the first specification of the first lattice.

11. The method according to claim 10, further comprising: Generate a second gram matrix from the second basis of the second lattice corresponding to the second signal in the received signal; The neural lattice reduction model is used to generate one or more second-part altered bases for the second lattice; as well as The basis of the second reduction of the second lattice is generated based on the basis of the one or more second-part changes, wherein the basis of the first reduction and the basis of the second reduction are generated through parallel processing of the neural lattice reduction model.

12. The method of claim 11, wherein the first signal of the received signals is received by a first antenna of a plurality of antennas, and the second signal of the received signals is received by a second antenna of the plurality of antennas.

13. The method of claim 11, wherein the parallel processing of the neural lattice reduction model is achieved through batch processing by a graphics processing unit.

14. The method of claim 11, further comprising demapping the MIMO channel matrix based on the basis of the first protocol and the basis of the second protocol.

15. The method of claim 10, wherein the basis of the first reduction is more orthogonal and shorter than the basis of the first lattice corresponding to the MIMO channel matrix.

16. The method of claim 9, wherein the received signal is distributed across time and frequency.

17. A non-transitory computer-readable medium comprising processor-executable instructions that, when executed by one or more processors of a device, cause the device to perform a method, the method comprising: Receive signals corresponding to a multiple-input multiple-output (MIMO) channel matrix; Generate the first gram matrix from the basis of the first cell corresponding to the first signal in the received signal; The first gram matrix is ​​provided to the neural lattice reduction model, which includes an equivariant neural network configured to generate the current extended Gaussian shift; The neural lattice reduction model is used to generate the currently partially changed basis based on the current extended Gaussian shift and the basis; Perform one or more additional iterations of the neural lattice reduction model, wherein each iteration includes: generating a subsequent Gram matrix from the currently partially changed basis, providing the subsequent Gram matrix to the equivariant neural network to generate a subsequent extended Gaussian shift, and generating an additional partially changed basis based on the subsequent extended Gaussian shift and the currently partially changed basis; as well as The MIMO channel matrix is ​​demapped by combining the basis of the currently partially changed basis and each of the additional partially changed basis generated by each additional iteration in one or more additional iterations of the neural lattice reduction model.

18. The non-transitory computer-readable medium of claim 17, wherein the basis of the first specification of the first lattice is formed by combining the basis of the currently partially changed basis and the basis of the additionally partially changed basis.

19. The non-transitory computer-readable medium of claim 18, wherein the method further comprises: Generate a second gram matrix from the second basis of the second lattice corresponding to the second signal in the received signal; The neural lattice reduction model is used to generate one or more second-part altered bases for the second lattice; as well as The basis of the second reduction of the second lattice is generated based on the basis of the one or more second-part changes, wherein the basis of the first reduction and the basis of the second reduction are generated through parallel processing of the neural lattice reduction model.

20. The non-transitory computer-readable medium of claim 19, wherein the first signal of the received signals is received by a first antenna of a plurality of antennas, and the second signal of the received signals is received by a second antenna of the plurality of antennas.

Images