Methods, devices, apparatuses, and computer-readable storage media for communication

Abstract

Example embodiments of the present disclosure relate to methods, devices, apparatuses, and media for communication. According to example embodiments of the present disclosure, a first device receives a reference signal from a second device. At least one original transmitted signal, an analog channel, and at least one analog received signal associated with the at least one original transmitted signal received via the analog channel are determined using a digital twin technology and the reference signal. Weights of a machine learning model are adjusted based on the at least one original transmitted signal, the at least one analog received signal, and at least one recovered transmitted signal recovered via the machine learning model until a difference between the recovered transmitted signal output from the machine learning model and a corresponding original transmitted signal is below a threshold difference. And a target transmitted signal received from the second device is recovered by the machine learning model with the adjusted weights. In this way, the accuracy of the signal recovered via the machine learning model can be improved, reducing the overhead of communication resources.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein relate to the field of communication technology, and more particularly to network devices, methods, apparatuses, and computer-readable storage media. Background Technology

[0002] A wireless channel is a data signal transmission channel that uses wireless signals as the transmission carrier. Channel estimation is the process of estimating the characteristics and parameters of a wireless channel by receiving signals and using machine learning models and algorithms. Through channel estimation, channel state information can be obtained to support the correct decoding and detection of signals, thereby adapting to complex communication environments. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for communication is provided. The method includes: a first device receiving a reference signal from a second device via a target channel between the first and second devices; determining, using digital twin technology and the reference signal, at least one original transmitted signal associated with the second device, an analog channel between the first and second devices, and at least one analog received signal received via the analog channel and associated with the at least one original transmitted signal; adjusting the weights of a machine learning model based on the at least one original transmitted signal, the at least one analog received signal, and at least one recovered transmitted signal recovered by a machine learning model, until the difference between the recovered transmitted signal output from the machine learning model under the weights and the corresponding original transmitted signal is less than a threshold difference; and recovering the target transmitted signal received from the second device by employing the machine learning model with the adjusted weights.

[0004] In a second aspect of this disclosure, an apparatus for communication is provided. The apparatus includes at least one processor; and at least one memory coupled to the at least one processor, the at least one memory including instructions stored therein, the at least one memory and the instructions being further configured, together with the at least one processor, to cause the apparatus to perform: a first device receiving a reference signal from a second device via a target channel between the first device and the second device; determining, using digital twin technology and the reference signal, at least one original transmitted signal associated with the second device, an analog channel between the first device and the second device, and at least one analog received signal received via the analog channel and associated with the at least one original transmitted signal; adjusting the weights of a machine learning model based on the at least one original transmitted signal, the at least one analog received signal, and at least one recovered transmitted signal recovered by a machine learning model, until the difference between the recovered transmitted signal output from the machine learning model under the weights and the corresponding original transmitted signal is less than a threshold difference; and recovering the target transmitted signal received from the second device by employing the machine learning model with the adjusted weights.

[0005] In a third aspect of this disclosure, an apparatus for communication is provided. The apparatus includes at least one processor; and at least one memory coupled to the at least one processor, the at least one memory including instructions stored therein, the at least one memory and the instructions being further configured, together with the at least one processor, to cause the apparatus to perform: a first device receiving a reference signal from a second device via a target channel between the first device and the second device; determining, using digital twin technology and the reference signal, at least one original transmitted signal associated with the second device, an analog channel between the first device and the second device, and at least one analog received signal received via the analog channel and associated with the at least one original transmitted signal; adjusting the weights of a machine learning model based on the at least one original transmitted signal, the at least one analog received signal, and at least one recovered transmitted signal recovered by a machine learning model, until the difference between the recovered transmitted signal output from the machine learning model under the weights and the corresponding original transmitted signal is less than a threshold difference; and recovering the target transmitted signal received from the second device by employing the machine learning model with the adjusted weights.

[0006] In a fourth aspect of this disclosure, an apparatus for communication is provided. The apparatus includes components for a first device to receive a reference signal from a second device via a target channel between the first and second devices; determining, using digital twin technology and the reference signal, at least one original transmitted signal associated with the second device, an analog channel between the first and second devices, and at least one analog received signal associated with the at least one original transmitted signal received via the analog channel; adjusting the weights of a machine learning model based on the at least one original transmitted signal, the at least one analog received signal, and at least one recovered transmitted signal recovered by a machine learning model, until the difference between the recovered transmitted signal output from the machine learning model under the weights and the corresponding original transmitted signal is less than a threshold difference; and recovering the target transmitted signal received from the second device by employing the machine learning model with the adjusted weights.

[0007] In a fifth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, the computer program including instructions that, when executed by a processor on a device, cause the device to perform the method described in the first aspect.

[0008] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] Exemplary embodiments of this disclosure are presented by way of example, and their advantages are explained in more detail below with reference to the accompanying drawings, wherein

[0010] Figure 1 A schematic diagram of an example communication environment using a machine learning model to recover transmitted signals is shown;

[0011] Figure 2 A schematic diagram of an environment in which the example embodiments described in this disclosure may be implemented is shown;

[0012] Figure 3 Signaling diagrams for communication according to some example embodiments of the present disclosure are shown;

[0013] Figure 4A A schematic diagram of a communication environment according to some example embodiments of the present disclosure is shown;

[0014] Figure 4B A schematic diagram of the structure of a communication environment according to some example embodiments of the present disclosure is shown;

[0015] Figure 5A A schematic diagram illustrating the recovery of a target received signal using a machine learning model according to some example embodiments of the present disclosure is shown.

[0016] Figure 5B A schematic diagram illustrating the recovery of simulated received signals using a machine learning model according to some example embodiments of the present disclosure is shown;

[0017] Figure 6 A schematic diagram of a time-frequency resource block according to some example embodiments of the present disclosure is shown;

[0018] Figure 7 A flowchart of an example communication method according to some example embodiments of the present disclosure is shown;

[0019] Figure 8 A flowchart of a method for communication according to some example embodiments of the present disclosure is shown;

[0020] Figure 9 A simplified block diagram of a device suitable for implementing example embodiments of the present disclosure is shown; and

[0021] Figure 10 A schematic diagram of a computer-readable medium according to some example embodiments of the present disclosure is shown.

[0022] In all the accompanying drawings, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0023] The principles and spirit of this disclosure will now be described with reference to several exemplary embodiments illustrated in the accompanying drawings. It should be understood that these specific exemplary embodiments are described only to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way.

[0024] As used herein, the term "comprising" and similar expressions should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0025] As used herein, the term "determine" encompasses a wide variety of actions. For example, "determine" can include calculation, computation, processing, derivation, investigation, searching (e.g., looking in a table, database, or other data structure), ascertainment, etc. Furthermore, "determine" can include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), etc. Additionally, "determine" can include parsing, selecting, choosing, building, etc.

[0026] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0027] As used herein, the term "circuit device" refers to one or more of the following: (a) a hardware circuit implementation (such as an implementation of analog and / or digital circuits only); and (b) a combination of hardware circuits and software, such as (if applicable): (i) a combination of analog and / or digital hardware circuits with software / firmware; and (ii) any part of a hardware processor with software (including digital signal processors, software, and memory that work together to enable devices such as optical communication devices or other computing devices to perform various functions); and (c) hardware circuits and / or processors, such as microprocessors or parts thereof, that require software (e.g., firmware) for operation, but may be without software when it is not required for operation.

[0028] The definition of "circuit device" applies to all uses of this term in this application (including any claim). As another example, the term "circuit device" as used herein also covers only hardware circuitry or a processor (or processors), or a portion of hardware circuitry or a processor, or an implementation thereof with accompanying software or firmware. For example, if applicable to a particular claim element, the term "circuit device" also covers baseband integrated circuits or processor integrated circuits or similar integrated circuits in an OLT or other computing device.

[0029] As used herein, the term "communication network" refers to a network that conforms to any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), and so on. Furthermore, communication between terminal devices and network devices in the communication network can be performed according to any suitable generation of communication protocol, including but not limited to, first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G), sixth-generation (6G) communication protocols and / or any other currently known or to be developed in the future. The exemplary embodiments of this disclosure can be applied to a variety of communication systems, including but not limited to terrestrial communication systems, non-terrestrial communication systems, or combinations thereof. Given the rapid development in the field of communications, there will certainly be future types of communication technologies and systems that can be used to implement this disclosure. This should not be construed as limiting the scope of this disclosure to only the aforementioned systems.

[0030] As used herein, the term "network device" refers to a node in a communication network through which terminal devices access the network and receive services. Depending on the terminology and technology applied, network devices can refer to base stations (BS) or access points (APs), such as Node B (NodeB or NB), evolved Node B (eNodeB or eNB), NR NB (also known as gNB), Remote Radio Unit (RRU), Radio Head (RH), Remote Radio Head (RRH), relay, Integrated Access and Backhaul (IAB) nodes, low-power nodes such as femtoseconds and picoseconds, etc.

[0031] As used herein, the term "terminal device" refers to any terminal device capable of wireless communication. By way of example and not limitation, a terminal device may also be referred to as a network device, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). Terminal devices may include, but are not limited to, mobile phones, cellular phones, smartphones, Voice over IP (VoIP) phones, wireless local loop phones, tablet computers, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback devices, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEEs), laptop-mounted devices (LMEs), Universal Serial Bus (USB) dongles, smart devices, wireless customer premises equipment (CPEs), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in industrial and / or automated processing chain environments), consumer electronics devices, devices operating on commercial and / or industrial wireless networks, etc. Terminal devices may correspond to the mobile terminal (MT) portion of an IAB node (e.g., a relay node). In the following description, the terms "terminal device," "network device," "terminal," "user equipment," and "UE" are used interchangeably.

[0032] As used herein, the term "circuit" refers to one or more of the following:

[0033] (a) Hardware-only implementations (such as implementations using only analog and / or digital circuits); and

[0034] (b) A combination of hardware circuitry and software, such as (if applicable):

[0035] (i) A combination of analog and / or digital hardware circuitry with software / firmware, and

[0036] (ii) Any part of the hardware processor and its software (including digital signal processors, software, and memory that work together to enable devices such as OLTs or other computing devices to perform various functions); and

[0037] (c) Hardware circuitry and / or processors, such as microprocessors or a portion thereof, that require software (e.g. firmware) for operation, but may be without software when it is not required for operation.

[0038] The definition of "circuit" applies to all uses of the term in this application (including any claim). As another example, the term "circuit" as used herein also covers a hardware circuit or processor (or processors), or a portion thereof, or an implementation thereof with accompanying software or firmware. For instance, if applicable to a particular claim element, the term "circuit" also covers a baseband integrated circuit or processor integrated circuit, or a similar integrated circuit in an OLT or other computing device.

[0039] Figure 1 A schematic diagram of an example communication environment using a machine learning model to recover transmitted signals is shown. Figure 1 As shown, in the example communication environment 100, there are receiving device 110 and transmitting device 120. Transmitting device 120 can transmit data with receiving device 110 via wireless channel 130.

[0040] Wireless channel 130 can receive the transmitted signal (B) sent via transmitting device 120 and output the target received signal (Y) to receiving device 110. Receiving device 110 includes a machine learning model 115, such as DeepRx. Machine learning model 115 can directly map the received target received signal (Y) using a deep neural network (DNN) to obtain a predicted signal, i.e., the recovered target transmitted signal (B). ’ The data information of the target transmitted signal (B) can be used as a ground truth label for evaluating the performance of machine learning model 115.

[0041] However, when the communication environment changes, there will be differences between the training data and the deployment data of the model, which will cause the model to have a generalization problem and lead to a decrease in model performance.

[0042] To improve the generalization problem of models, a common solution is to fine-tune the model using sample data pre-collected from the communication environment. However, in real-world scenarios, network devices struggle to acquire ground truth labels sent by terminal devices without any coordination. Even if network devices acquire ground truth labels with coordination, it requires a large amount of data transmission, resulting in significant transmission overhead.

[0043] Therefore, embodiments of this disclosure propose a scheme for communication. In this scheme, a first device receives a reference signal from a second device via a target channel between the first and second devices; at least one original transmitted signal associated with the second device, an analog channel between the first and second devices, and at least one analog received signal associated with the at least one original transmitted signal received via the analog channel are determined using digital twin technology and the reference signal; the weights of a machine learning model are adjusted based on the at least one original transmitted signal, the at least one analog received signal, and at least one recovered transmitted signal recovered by a machine learning model, until the difference between the recovered transmitted signal output from the machine learning model under the weights and the corresponding original transmitted signal is less than a threshold difference; and the target transmitted signal received from the second device is recovered by employing a machine learning model with adjusted weights.

[0044] In this way, channel estimation for the target channel can be achieved with less data transmission, so as to simulate the simulated channel. Then, the simulated channel can be used to fine-tune the machine learning model, which improves the accuracy of the signal recovered by the machine learning model and greatly reduces the overhead of communication resources.

[0045] The principles and exemplary embodiments of this disclosure will be further described in detail below with reference to the accompanying drawings.

[0046] Figure 2 A schematic diagram of an example communication network 100 in which exemplary embodiments described herein may be implemented is shown. Communication network 100 may be part of a communication network. Communication environment 200 includes a first device 210 and a second device 220. Communication environment 200 may include any number of first devices 210 and second devices 220. In embodiments of this disclosure, the first device 210 and the second device 220 are interchangeable; that is, methods / steps implemented at the first device 210 described in the embodiments may also be implemented at the second device 220. It should be understood that communication environment 200 is merely exemplary and is not intended to limit this disclosure in any way. In some example embodiments, the first device 210 may be a network device, and the second device 220 may be a terminal device.

[0047] In some example embodiments, the link from the network device to the terminal device may be referred to as a downlink (DL), and the link from the terminal device to the network device may be referred to as an uplink (UL). In the DL, the network device is a transmitting (TX) device (or transmitter), and the terminal device is a receiving (RX) device (or receiver). In the UL, the terminal device is a TX device (or transmitter), and the network device 110 is an RX device (or receiver).

[0048] It should be understood that Figure 1The number of devices and their connections shown are merely illustrative and not limiting. Communication network 100 may include any suitable number of devices configured to implement the exemplary embodiments of this disclosure. Although not shown, it should be understood that one or more other devices may be deployed in communication network 100.

[0049] Communication in communication network 100 can be implemented according to any appropriate communication protocol(s). Examples of communication protocols include, but are not limited to, cellular communication protocols such as first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G), and sixth generation (6G), wireless local area network communication protocols such as IEEE 802.11, and / or any other protocols currently known or to be developed in the future.

[0050] Furthermore, communication may utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple Input Multiple Output (MIMO), Orthogonal Frequency Division Multiplexing (OFDM), Spread Spectrum Orthogonal Frequency Division Multiplexing Based on Discrete Fourier Transform (DFT-s-OFDM), and / or any other technology currently known or to be developed in the future.

[0051] The principles and exemplary embodiments of this disclosure will be further described in detail below with reference to the accompanying drawings.

[0052] Figure 3 Signaling diagram 300 for communication according to some example embodiments of the present disclosure is shown. Reference will be made to this diagram for discussion purposes. Figure 2 and Figure 3 A signaling diagram 300 is described for communication. In some example embodiments, the first device 210 may be a network device, such as a gNB. The second device 220 may be a terminal device, such as a UE. It should be understood that, although Figure 3 Only a single first device 210 and a single second device 220 are shown in the diagram, but multiple first devices 210 and second devices 220 may also be involved in the signaling diagram 300.

[0053] like Figure 3 As shown, in some example embodiments, the first device 210 may maintain (302) a machine learning model to recover the received signal. The machine learning model may be, for example, DeepRx. In some example embodiments, the first device 210 may recover the target transmitted signal received from the second device 220 through DeepRx's end-to-end direct mapping capability, making the first device 210 more adaptable to channel conditions, thereby improving the reliability and efficiency of data transmission.

[0054] During data transmission between the first device 210 and the second device 220, in response to detecting a change in the channel state of the target channel, the first device 210 may enable (304) a function based on digital twin technology. In some example embodiments, digital twin technology can simulate the communication environment and transceiver functions between the first device 210 and the second device 220 at the first device 210. The specific implementation of the function based on digital twin technology will be discussed later. Figure 3 Based on the combination Figure 4A A detailed introduction will be provided.

[0055] Figure 4A A schematic diagram of a communication environment 400A according to some example embodiments of the present disclosure is shown. For example... Figure 4A As shown, in communication environment 400A, first device 210 and second device 220 transmit data through target channel 402. First device 210 may include machine learning model 404.

[0056] In some example embodiments, the first device 210 can utilize digital twin technology to simulate the communication environment between the first device 210 and the second device 220 to generate a simulated communication environment 406. Digital twin technology can replicate all modules and data from the original communication environment. For example, the simulated communication environment 406 may include the original transmitted signal (B) corresponding to the target transmitted signal (B) of the second device 220. s ), machine learning model 408 corresponding to machine learning model 404, and the recovered target transmitted signal (B) ’ The recovered transmitted signal (B) ’ s ).

[0057] like Figure 3 and Figure 4A As shown, when the channel state of the target channel 402 changes, the first device 210 may send (306) a request for a reference signal to the second device 220. In some example embodiments, the request for the reference signal may include information such as the signal type of the reference signal, the duration of transmission of the reference signal, and the number of reference signals.

[0058] In some example embodiments, the first device 210 can determine whether the channel state of the target channel 402 has changed by detecting the data distribution of the bit stream transmitted between the first device 210 and the second device 220. In other example embodiments, the first device 210 can also determine whether the channel state of the target channel 402 has changed by detecting in real time whether the reference signal received from the second device 220 has changed.

[0059] Upon receiving a request for a reference signal via the target channel 402, the second device 220 may send (308) the reference signal to the first device 210. In some example embodiments, the reference signal may be a demodulation reference signal (DM-RS) or a channel state information reference signal (CSI-RS). It should be understood that other suitable types of reference signals may also be used, and this disclosure is not limiting in this regard.

[0060] Furthermore, upon receiving a reference signal via the target channel 402, the first device 210 can perform (310) channel estimation based on the reference signal. In some example embodiments, the first device 210 can sample a small amount of data from the target channel 402 to obtain an estimated result of the channel estimation, such as multiple channel estimation samples 410. Using digital twin technology, the multiple channel estimation samples 410 can be used as an equivalent channel of the target channel 402, i.e., a simulated channel 412. The simulated channel 412 can receive the original transmitted signal (B... s ), and based on the original transmitted signal (B) s Generate analog received signal (Y) s Analog received signal (Y) s The signal (Y) corresponds to the target received signal in the original communication environment, and both can be used for model training and fine-tuning.

[0061] For example, in analog communication environment 406, there are 100 sets of original transmitted signals (B s1 To B s100 In the case of ), the first device 210 can sample 10 sets of channel estimation samples (H1 to H) of the target channel 402. 10 This serves as the analog channel 412 required in the analog communication environment 406. The analog channel 412 can be generated from 10 sets of channel estimation samples (H1 to H...). 10 Randomly select the required channel data from 100 sets of original transmitted signals (B) to base the analysis on the original transmitted signals. s1 To B s100 Generate 100 corresponding sets of analog received signals (Y) s1 To Y s100 It should be understood that the numbers or values ​​involved in the embodiments of this disclosure are merely exemplary and are not intended to limit this disclosure in any way.

[0062] In some example embodiments, the first device 210 may fine-tune the machine learning model 408 using the analog channel 412 (312). Specifically, the machine learning model 408 may fine-tune the model upon receiving the analog received signal (Y). s Then the recovered transmitted signal (B) is output. ’ sFurthermore, the first device 210 can transmit the original signal (B) by... s ) and the recovered transmission signal (B ’ s The first device 210 compares the weights of the machine learning model 408 to determine the training loss function 414. Then, the first device 210 can determine the weights 416 of the machine learning model 408 based on the training loss function 414.

[0063] After applying weights 416 to the machine learning model 408, the first device 210 can determine whether the performance of the machine learning model 408 under those weights 416 meets a preset metric. For example, the first device 210 can determine whether the difference between the recovered transmitted signal output from the machine learning model 408 and the corresponding original transmitted signal under those weights 416 is less than a threshold difference.

[0064] In some example embodiments, in response to the performance of the machine learning model 408 failing to meet a preset metric—that is, the difference between the recovered transmitted signal and the corresponding original transmitted signal exceeding a threshold difference—the first device 210 may again send (314) a request for a reference signal to the second device 220 to obtain another reference signal from the second device 220. Similar to the fine-tuning process for the machine learning model 408 described above, the first device 210 may perform another channel estimation for the target channel 402 based on the other reference signal. Then, another simulated channel is generated using the result of the other channel estimation. Subsequently, the weights 416 are readjusted based on the other simulated channel and the machine learning model 408.

[0065] In other example embodiments, in response to the performance of machine learning model 408 meeting a preset metric, namely, the difference between the recovered transmitted signal and the corresponding original transmitted signal is less than a threshold difference, the first device 210 can synchronize (316) weights 416 to machine learning model 404. Further, the first device 210 can recover the target transmitted signal (B) by inputting the target received signal (Y) into machine learning model 404 using the updated weights 415. ’ ).

[0066] In this way, the first device 210 can perform channel estimation for the target channel with less data transmission, simulate the simulated channel, and then use the simulated channel to fine-tune the machine learning model, thereby improving the accuracy of the signal recovered by the machine learning model and greatly reducing the overhead of communication resources.

[0067] The following will be in Figure 4A Based on the combination Figures 4B to 6 An example architecture of the communication environment for the first device 210 and the second device 220 is introduced.

[0068] Figure 4B A schematic diagram of the structure of a communication environment 400B according to some example embodiments of the present disclosure is shown. For example... Figure 4B As shown, the 400B communication environment can adopt a single-input single-output (SISO) orthogonal frequency division multiplexing (OFDM) topology based on 64-QAM modulation.

[0069] In some example embodiments, the first device 210 and the second device 220 may include multiple communication modules, such as a low-density parity check module (LDPC) 422, an inverse fast Fourier transform module (IFFT) or a cyclic prefix module (CP) 424, a digital-to-analog converter (DAC) 426, an analog-to-digital converter (ADC) 428, an up-conversion module 430, a down-conversion module 432, and a power amplifier (PA) 434, etc.

[0070] Figure 5A A schematic diagram illustrating a machine learning model recovering a target received signal according to some example embodiments of the present disclosure is shown. For example... Figure 5A As shown, in some example embodiments, the target received signal (Y) generated via target channel 402 can be a bitstream of size 1024×14×2. The target transmitted signal (B) recovered via machine learning model 404 ’ It can be a bitstream with a size of 1024×14×6.

[0071] Figure 5B A schematic diagram illustrating a machine learning model recovering a simulated received signal according to some example embodiments of the present disclosure is shown. For example... Figure 5B As shown, in some example embodiments, the analog received signal (Y) generated via analog channel 412 s The input data for the machine learning model 408 can be a bitstream of size 1024×14×2, and the channel estimation sample can also be a bitstream of size 1024×14×2. Therefore, the input data for the machine learning model 408 can be a bitstream of size 1024×14×4. The transmitted signal (B) recovered by the machine learning model 408... ’ s It can be a bitstream with a size of 1024×14×6.

[0072] Figure 6 A schematic diagram of a time-frequency resource block 600 according to some example embodiments of the present disclosure is shown. For example... Figure 6 As shown, in some example embodiments, the transmission between the first device 210 and the second device 220 can be implemented by a time-frequency resource block 600 with dimensions of 1024×14. During each transmission, 1024 subcarriers can be used on 14 symbols, and pilot 602 can be placed in the 3rd and 12th symbols to enhance signal processing and channel estimation capabilities.

[0073] Figure 7 A flowchart of an example communication method 700 according to some example embodiments of the present disclosure is shown. Method 700 may be implemented, for example, in a communication environment 200, such as at a first device 210.

[0074] In box 702, the first device 210 can detect channel changes in the target channel between itself and the second device 220 to determine in real time whether the communication environment has been affected by external factors.

[0075] In block 704, if a channel change occurs in the target channel, the first device 210 may send a request for a reference signal to the second device 220 to specify the transmission frequency and transmission time of the reference signal.

[0076] In block 706, the first device 210 may receive a reference signal from the second device 220. The reference signal is sent via the second device 220 on request. In some example embodiments, the reference signal may be a demodulated reference signal or a channel state information reference signal.

[0077] In block 708, the first device 210 can perform channel estimation of the target channel based on a reference signal to simulate a simulated channel equivalent to the target channel.

[0078] In block 710, the first device 210 may use digital twin technology and an analog channel to determine the original transmitted signal, the analog received signal, and the recovered transmitted signal recovered via a machine learning model. In some example embodiments, the original transmitted signal is the signal associated with the second device 220 determined by the first device 210 using digital twin technology. The analog received signal is the signal generated by the analog channel based on the original transmitted signal.

[0079] In box 712, the first device 210 can determine the weights of the machine learning model based on the original transmitted signal, the received signal, and the recovered transmitted signal.

[0080] In block 714, the first device 210 can determine whether the difference between the recovered transmitted signal and the corresponding original transmitted signal is less than a threshold difference. If the difference between the recovered transmitted signal and the corresponding original transmitted signal is greater than the threshold difference, then method 700 proceeds back to block 704, whereby the first device 210 again sends a request for a reference signal to the second device 220 to obtain an additional reference signal.

[0081] If the difference between the recovered transmitted signal and the corresponding original transmitted signal is less than a threshold difference, then method 700 proceeds to block 716, whereby the first device 210 recovers the transmitted signal received from the second device using a weighted machine learning model. The other specific implementations of each step in method 700 have been described in detail above and will not be repeated here.

[0082] Figure 8 A flowchart of a method 800 for communication according to some example embodiments of the present disclosure is shown. Method 800 may be implemented, for example, in a communication environment 200, such as at a first device 210.

[0083] In block 810, the first device 210 receives a reference signal from the second device 220 via a target channel between the first device 210 and the second device 220.

[0084] In block 820, digital twin technology and reference signals are used to determine at least one original transmitted signal associated with the second device 220, an analog channel between the first device 210 and the second device 220, and at least one analog received signal associated with the at least one original transmitted signal received via the analog channel.

[0085] In box 830, the weights of the machine learning model are adjusted based on at least one original transmitted signal, at least one analog received signal, and at least one recovered transmitted signal recovered by the machine learning model, until the difference between the recovered transmitted signal output from the machine learning model and the corresponding original transmitted signal under the weights is less than a threshold difference.

[0086] In box 840, the target transmission signal received from the second device 220 is recovered by employing a machine learning model with adjusted weights.

[0087] In some example embodiments, method 800 further includes: performing channel estimation on the target channel based on a reference signal; and determining the equivalent channel of the target channel simulated based on the estimation result of the channel estimation as the simulated channel.

[0088] In some example embodiments, method 800 further includes sending a request for a reference signal to a second device 220 in response to detecting a channel state change of the target channel.

[0089] In some example embodiments, the request includes at least one of the following: the signal type of the reference signal, the duration of sending the reference signal, and the number of reference signals.

[0090] In some example embodiments, the reference signal is a demodulation reference signal or a channel state information reference signal.

[0091] In some example embodiments, determining at least one analog received signal includes generating at least one analog received signal using at least one original transmitted signal and an analog channel.

[0092] In some example embodiments, method 800 further includes: inputting at least one original transmitted signal and at least one analog received signal into the output of a machine learning model as at least one recovered transmitted signal.

[0093] In some example embodiments, determining the weights of a machine learning model includes: determining a training loss function for the machine learning model by comparing at least one original transmitted signal with at least one recovered transmitted signal; and determining the weights based on the training loss function.

[0094] In some example embodiments, method 800 further includes: in response to a difference between the recovered transmitted signal obtained from the machine learning model under weights and the corresponding original transmitted signal being greater than a threshold difference, transmitting another reference signal obtained from the second device 220; performing another channel estimation of the target channel based on the other reference signal; generating another simulated channel using the result of the other channel estimation; and readjusting the weights based on the other simulated channel and the machine learning model.

[0095] In some example embodiments, recovering a target transmitted signal includes: receiving a target received signal associated with the target transmitted signal; and recovering the target transmitted signal by inputting the target received signal into a weighted machine learning model.

[0096] In some example embodiments, the first device 210 is a receiver and the second device 220 is a transmitter.

[0097] In some example embodiments, a communication apparatus (e.g., first device 210) may include components for performing corresponding steps of method 800. These components may be implemented in any suitable manner. For example, the components may be implemented as circuit devices or software modules.

[0098] In some example embodiments, the first device 210 may include components for performing channel estimation of the target channel based on a reference signal; and components for determining the equivalent channel of the target channel simulated based on the channel estimation results as the simulated channel.

[0099] In some example embodiments, the first device 210 may include components for sending a request for a reference signal to the second device 220 in response to detecting a channel state change of the target channel.

[0100] In some example embodiments, the request includes at least one of the following: the signal type of the reference signal, the duration of sending the reference signal, and the number of reference signals.

[0101] In some example embodiments, the reference signal is a demodulation reference signal or a channel state information reference signal.

[0102] In some example embodiments, the first device 210 may include components for generating at least one analog received signal using at least one original transmitted signal and an analog channel.

[0103] In some example embodiments, the first device 210 may include a component for taking at least one original transmitted signal and at least one analog received signal as the output of a machine learning model as at least one recovered transmitted signal.

[0104] In some example embodiments, the first device 210 may include components for determining a training loss function of a machine learning model by comparing at least one original transmitted signal with at least one recovered transmitted signal; and components for determining weights based on the training loss function.

[0105] In some example embodiments, the first device 210 may include components for sending another reference signal from the second device 220 in response to a difference between the recovered transmitted signal obtained from the machine learning model under weights and the corresponding original transmitted signal exceeding a threshold difference; components for performing another channel estimation of the target channel based on the other reference signal; components for generating another simulated channel using the result of the other channel estimation; and components for readjusting the weights based on the other simulated channel and the machine learning model.

[0106] In some example embodiments, the first device 210 may include components for receiving a target received signal associated with a target transmitted signal; and components for recovering the target transmitted signal by inputting the target received signal into a weighted machine learning model.

[0107] In some example embodiments, the first device 210 is a receiver and the second device 220 is a transmitter.

[0108] Figure 9 This is a simplified block diagram of a device 900 suitable for implementing an example embodiment of the present disclosure. Device 900 can be used to implement a first device 210 and a second device 220 in a communication environment 200. As shown, device 900 includes one or more processing units 910, one or more memories 920 coupled to the processing units 910, and a communication module 940 coupled to the processing units 910.

[0109] The communication module 940 is used for bidirectional communication. In some example embodiments, the communication module 940 may have at least one antenna to facilitate communication. In some example embodiments, the communication module 940 may have one or more communication interfaces. A communication interface may represent any interface required for communication with other network elements.

[0110] Processing unit 910 can be any type suitable for a local technology network and can include, but is not limited to, one or more of a general-purpose computer, a special-purpose computer, a microcontroller, a digital signal controller (DSP), and a controller-based multi-core controller architecture. Device 900 can have multiple processors, such as application-specific integrated circuit chips, which are time-subject to a clock synchronized with the main processor.

[0111] Memory 920 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 924, erasable programmable read-only memory (EPROM), flash memory, hard disk, optical disc (CD), digital video disc (DVD), and other magnetic and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 922 and other volatile memories that do not persist during power-off periods.

[0112] Computer program 930 includes computer-executable instructions that are executed by associated processing unit 910. Computer program 930 may be stored in ROM 924. Processing unit 910 may perform any appropriate actions and processes by loading computer program 930 into RAM 922.

[0113] The exemplary embodiments of this disclosure can be implemented by means of computer program 930, enabling device 900 to perform as described in the reference. Figures 2 to 8 Any process discussed in this disclosure. Exemplary embodiments of this disclosure may also be implemented by hardware or by a combination of software and hardware.

[0114] In some example embodiments, the computer program 930 may be tangibly contained in a computer-readable medium, which may include in device 900 (such as in memory 920) or other storage device accessible by device 900. The computer program 930 may be loaded from the computer-readable medium into RAM 922 for execution. The computer-readable medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. Figure 10 An example of a computer-readable medium 1000 in the form of a CD or DVD according to some exemplary embodiments of the present disclosure is shown. A computer program 930 is stored on the computer-readable medium 1000.

[0115] Generally, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software, which can be executed by a controller, microprocessor, or other computing device. While various aspects of exemplary embodiments of this disclosure are shown and described as block diagrams, flowcharts, or represented using some other illustration, it should be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as, as in the non-limiting examples, hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0116] This disclosure also provides at least one computer program product tangibly stored on a computer-readable storage medium. In some example embodiments, the computer-readable storage medium may be non-transitory. The computer program product includes computer-executable instructions, such as instructions included in program modules, which execute in a device on a real or virtual processor of a target to perform the above-referenced... Figure 8 The method described in 800. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided among program modules as needed. The machine-executable instructions for a program module can be executed locally or in a distributed device. In a distributed device, the program module can reside in both local and remote storage media.

[0117] Computer program code used to implement the methods of this disclosure may be written in one or more programming languages. This computer program code may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when executed by the computer or other programmable data processing apparatus, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be performed. The program code may be executed entirely on a computer, partially on a computer, as a stand-alone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0118] In the context of this disclosure, computer program code or related data may be carried on any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and so on. Examples of signals may include electrical, optical, radio, sound, or other forms of propagation signals, such as carrier waves, infrared signals, etc.

[0119] A computer-readable medium can be any tangible medium that contains or stores a program for or relating to an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. More detailed examples of computer-readable storage media include electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0120] Furthermore, although the operation of the methods of this disclosure is described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Rather, the steps depicted in the flowcharts may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps. It should also be noted that the features and functions of two or more devices according to this disclosure may be embodied in one device. Conversely, the features and functions of one device described above may be further divided and embodied by multiple devices.

[0121] While this disclosure has been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the specific embodiments disclosed. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A method for communication, comprising: The first device receives a reference signal from the second device via a target channel between the first device and the second device; Using digital twin technology and the reference signal, at least one original transmitted signal associated with the second device, an analog channel between the first device and the second device, and at least one analog received signal associated with the at least one original transmitted signal received via the analog channel are determined. The weights of the machine learning model are adjusted based on the at least one original transmitted signal, the at least one analog received signal, and at least one recovered transmitted signal recovered by the machine learning model, until the difference between the recovered transmitted signal output from the machine learning model and the corresponding original transmitted signal under the weights is less than a threshold difference. as well as The target transmitted signal received from the second device is recovered by employing the machine learning model with adjusted weights.

2. The method according to claim 1, further comprising: Channel estimation is performed on the target channel based on the reference signal; as well as The equivalent channel of the target channel, simulated based on the channel estimation results, is determined as the simulated channel.

3. The method according to claim 1 or 2, further comprising: In response to detecting a channel state change in the target channel, a request for the reference signal is sent to the second device.

4. The method of claim 3, wherein the request includes at least one of the following: The signal type of the reference signal, The duration of transmitting the reference signal, The number of reference signals.

5. The method according to claim 1, wherein the reference signal is a demodulation reference signal or a channel state information reference signal.

6. The method of claim 1, wherein determining the at least one analog received signal comprises: The at least one analog received signal is generated using the at least one original transmitted signal and the analog channel.

7. The method according to claim 1, further comprising: The output of the machine learning model after inputting the at least one original transmitted signal and the at least one analog received signal is used as the at least one recovered transmitted signal.

8. The method of claim 1, wherein determining the weights of the machine learning model comprises: The training loss function of the machine learning model is determined by comparing the at least one original transmitted signal with the at least one recovered transmitted signal; as well as The weights are determined based on the training loss function.

9. The method according to claim 1, further comprising: In response to the difference between the recovered transmitted signal obtained from the machine learning model under the said weight and the corresponding original transmitted signal being greater than a threshold difference, another reference signal is obtained from the second device; Another channel estimate is performed on the target channel based on the other reference signal; Another simulated channel is generated using the result of the other channel estimation; as well as The weights are readjusted based on the other simulated channel and the machine learning model.

10. The method of claim 1, wherein recovering the target transmitted signal comprises: Receive the target received signal associated with the target transmitted signal; as well as The target transmitted signal is recovered by inputting the target received signal into the machine learning model with the weights stated thereon.

11. The method of claim 1, wherein the first device is a receiver and the second device is a transmitter.

12. A communication device comprising at least one processor; and at least one memory coupled to said at least one processor, said at least one memory including instructions stored therein, said at least one memory and said instructions being further configured, together with said at least one processor, to cause the device to perform the method according to any one of claims 1-11.

13. An apparatus for communication, comprising components for performing the method according to any one of claims 1-11.

14. A computer-readable storage medium having a computer program stored thereon, the computer program including instructions that, when executed by a processor on a device, cause the device to perform the method according to any one of claims 1-11.

Images