Communication method and related apparatus

Abstract

The present application relates to the technical field of wireless communications. Disclosed are a communication method and a related apparatus. The method is applied to a first communication apparatus. The method comprises: sending first information to a second communication apparatus, the first information being used for indicating a first pseudo-random sequence, the first pseudo-random sequence being used for training a channel estimation model, the channel estimation model being used for predicting a channel between the first communication apparatus and the second communication apparatus, and the channel being predicted on the basis of the first pseudo-random sequence and a second pseudo-random sequence; and sending the second pseudo-random sequence to the second communication apparatus. The present application is used for keeping the model performance of channel estimation models during training.

Description

A communication method and related apparatus

[0001] This application claims priority to Chinese Patent Application No. 202411985424.8, filed on December 28, 2024, entitled "A Communication Method and Related Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of wireless communication technology, and in particular to a communication method and related apparatus. Background Technology

[0003] Wireless channels are complex and variable. Signals are affected by various factors during transmission, such as multipath effects, fading, noise, and interference. These factors can lead to channel distortion, which in turn affects the receiver's ability to correctly demodulate the signal. Channel estimation allows us to obtain the transmission characteristics of the channel, enabling us to minimize its influence at the receiver and thus recover the transmitted signal from the received signal.

[0004] Traditional channel estimation methods typically use a channel estimation model to fit the channel. The input to this channel estimation model can include a sequence of demodulation reference signals (DMRS) (also known as DMRS sequences). However, due to the diversity of DMRS, the training and inference of the channel estimation model will be affected. It is difficult to traverse all DMRS sequences during the training process, which will result in poor performance or difficulty in convergence of the final trained channel estimation model.

[0005] Therefore, how to maintain the model performance during channel estimation model training is a technical problem that urgently needs to be solved by those in this field. Summary of the Invention

[0006] This application provides a communication method and related apparatus that can maintain the model performance during channel estimation model training.

[0007] The present application is described below from different aspects. It should be understood that the different implementation methods and beneficial effects described below can be referenced from each other.

[0008] In a first aspect, embodiments of this application provide a communication device, which may be a first communication device or a chip within a first communication device. The communication device is used to implement the method described in the second aspect or any implementation thereof below. The communication device includes modules for implementing the method in the second aspect or any implementation thereof.

[0009] In the first aspect, the communication device described above may include a transceiver module and a processing module. Further details regarding the transceiver module and processing module can be found in the device embodiments shown below. The beneficial effects of the first aspect can be referenced in the relevant description of the second aspect, and will not be repeated here.

[0010] Secondly, embodiments of this application provide a communication method applied to a first communication device. The first communication device may be an access network device (such as a base station), a communication module or component of the access network device, or a logic module or chip capable of implementing all or part of the functions of the access network device. The method includes: sending first information to a second communication device, the first information indicating a first pseudo-random sequence, the first pseudo-random sequence being used to train a channel estimation model, the channel estimation model being used to predict the channel between the first and second communication devices, the channel being predicted based on the first and second pseudo-random sequences; and sending a second pseudo-random sequence to the second communication device.

[0011] The second pseudo-random sequence is the inference sequence of the channel estimation model, that is, the pseudo-random sequence transmitted by the first communication device and the second communication device during the actual communication process.

[0012] In the above scheme, the first communication device not only needs to send the first information to the second communication device, but also needs to send the second pseudo-random sequence to the second communication device. This means that the second communication device can know not only that the inference sequence of the channel estimation model is the second pseudo-random sequence, but also that the training sequence of the channel estimation model is the first pseudo-random sequence. The channel is predicted based on the first and second pseudo-random sequences. In other words, the training and inference sequences of the channel estimation model participate in the model inference process together. Thus, even if there are differences between the first and second pseudo-random sequences, the channel between the first and second communication devices can still be accurately predicted through the channel estimation model. In other words, the embodiments of this application do not require that the training and inference sequences of the channel estimation model be the same; that is, even when the training and inference sequences are different, the model performance during channel estimation model training can still be maintained.

[0013] In this application, the pseudo-random sequence involved in the embodiments can be a sequence used for mapping a reference signal. In one possible implementation, the first pseudo-random sequence and the second pseudo-random sequence can be sequences used for mapping a demodulation reference signal (DMRS), which can also be understood as the first and second pseudo-random sequences being carried in the DMRS. Optionally, the first and second pseudo-random sequences can be DMRS sequences, which will not be limited here. The DMRS is mainly used for channel estimation to demodulate the corresponding physical channel.

[0014] In one possible implementation, the first information includes one or more of the following: an identifier of the first pseudo-random sequence, or parameters used to generate the first pseudo-random sequence.

[0015] In the above implementation, the identifier of the first pseudo-random sequence is used to uniquely represent the first pseudo-random sequence. Compared with the first pseudo-random sequence, the identifier of the first pseudo-random sequence or the parameters used to generate the first pseudo-random sequence occupy a smaller amount of data, which can effectively reduce the transmission overhead between the first communication device and the second communication device and improve communication performance.

[0016] In one possible implementation, there is a mapping relationship between the identifier of the first pseudo-random sequence and the first pseudo-random sequence, and the mapping relationship is predefined.

[0017] In one possible implementation, the first information includes indication information and / or time-frequency location information, the time-frequency location information being used to determine the second pseudo-random sequence, and the indication information being used to indicate that the second pseudo-random sequence is the same as the first pseudo-random sequence.

[0018] In the above implementation, the first communication device sending first information to the second communication device can be understood as the first communication device using the first information to indicate the relationship between the currently transmitted pseudo-random sequence and the training sequence of the channel estimation model (i.e., the first pseudo-random sequence), meaning that the currently transmitted pseudo-random sequence (i.e., the second pseudo-random sequence) is the same as the first pseudo-random sequence. The indication information can be sent simultaneously with the time-frequency location information or separately; this will not be limited here.

[0019] In one possible implementation, the first information is carried in the downlink control information.

[0020] In one possible implementation, the method further includes: sending second information to a second communication device, the second information being used to indicate a channel estimation model.

[0021] In the above implementation, the first communication device interacts with the second communication device, enabling the second communication device to deploy a channel estimation model based on the second information. Here, the channel estimation model can be a channel estimation model that has already been trained. That is, the model training process is executed by the network side, rather than by the second communication device (e.g., the terminal side). Generally speaking, the network side has stronger computing power than the terminal side, and the model training process takes less time. This can effectively improve the efficiency of model training, enabling the second communication device to deploy the channel estimation model that has already been trained more quickly.

[0022] In one possible implementation, the method further includes: transmitting a first observation sequence and a first pseudo-random sequence to a server of the first communication device, wherein the first observation sequence is obtained by transmitting the first pseudo-random sequence through a channel between the first communication device and the second communication device, and the first pseudo-random sequence and the first observation sequence are used to train a channel estimation model; and obtaining second information from the server of the first communication device.

[0023] In the above implementation, the first communication device needs to interact with the server of the first communication device to realize the model training process of the channel estimation model. In other words, the model training process of the channel estimation model is not executed by the first communication device, but by the server of the first communication device. This can effectively reduce the computational pressure of the first communication device and improve the operating performance of the first communication device.

[0024] Thirdly, embodiments of this application provide a communication device, which may be a second communication device or a chip within a second communication device. This communication device is used to implement a method as described in the fourth aspect or any implementation thereof. The communication device includes modules for implementing the method in the fourth aspect or any implementation thereof.

[0025] In the third aspect, the aforementioned communication device may include a transceiver module and a processing module. For a detailed description of the transceiver module and the processing module, please refer to the device embodiments shown below. The beneficial effects of the third aspect can be found in the relevant description of the fourth aspect, and will not be repeated here.

[0026] Fourthly, embodiments of this application provide a communication method applied to a second communication device. The second communication device may be a terminal, a communication module or component of the terminal, or a logic module or chip capable of implementing all or part of the terminal's functions. The method includes: receiving first information from a first communication device, the first information indicating a first demodulation reference signal pseudo-random sequence, the first pseudo-random sequence being used to train a channel estimation model; and acquiring a second pseudo-random sequence, the channel estimation model being used to predict the channel between the first and second communication devices, the channel being predicted based on the first and second pseudo-random sequences.

[0027] In the above scheme, the second communication device can not only receive the first information from the first communication device, but also acquire the second pseudo-random sequence. This means that the second communication device can know not only that the inference sequence of the channel estimation model is the second pseudo-random sequence, but also that the training sequence of the channel estimation model is the first pseudo-random sequence. The channel is predicted based on the first and second pseudo-random sequences. In other words, the training and inference sequences of the channel estimation model participate in the model inference process together. Thus, even if there are differences between the first and second pseudo-random sequences, the channel between the first and second communication devices can still be accurately predicted through the channel estimation model. In other words, the embodiments of this application do not require that the training and inference sequences of the channel estimation model be the same; that is, even when the training and inference sequences are different, the model performance during channel estimation model training can still be maintained.

[0028] In one possible implementation, the second pseudo-random sequence is the inference sequence of the channel estimation model.

[0029] In one possible implementation, the first pseudo-random sequence and the second pseudo-random sequence are sequences used to map the demodulation reference signal DMRS.

[0030] In one possible implementation, the method further includes: receiving a second observation sequence, the second observation sequence being obtained after the second pseudo-random sequence is transmitted through a channel between the first communication device and the second communication device; the channel is predicted based on the first pseudo-random sequence and the second pseudo-random sequence, including: the channel is predicted based on the first pseudo-random sequence, the second pseudo-random sequence and the second observation sequence.

[0031] In the above implementation, during model inference, the input to the channel estimation model includes not only the second pseudo-random sequence and the second observation sequence, but also the first pseudo-random sequence. This means that the training sequence of the channel estimation model also participates in the model inference process. Through the first pseudo-random sequence, the second pseudo-random sequence, and the second observation sequence, the features already learned by the channel estimation model (i.e., the observation sequence of the first pseudo-random sequence) can be constructed as much as possible. Thus, even if there are differences between the first and second pseudo-random sequences, the channel between the first and second communication devices can still be accurately predicted through the channel estimation model. In other words, this embodiment does not require the training sequence and the inference sequence to be the same; that is, even when the training sequence and the inference sequence are different, the model performance during channel estimation model training can still be maintained.

[0032] In one possible implementation, the first information includes one or more of the following: an identifier of the first pseudo-random sequence, or parameters used to generate the first pseudo-random sequence.

[0033] In one possible implementation, there is a mapping relationship between the identifier of the first pseudo-random sequence and the first pseudo-random sequence, and the mapping relationship is predefined.

[0034] In one possible implementation, the first information includes indication information and / or time-frequency location information, the time-frequency location information being used to determine the second pseudo-random sequence, and the indication information being used to indicate that the second pseudo-random sequence is the same as the first pseudo-random sequence.

[0035] In one possible implementation, the first information is carried in the downlink control information.

[0036] In one possible implementation, the method further includes receiving second information, which is used to indicate the channel estimation model.

[0037] In the above implementation, the second communication device can deploy a channel estimation model based on the second information. The channel estimation model can be a channel estimation model that has already been trained. That is, the model training process is executed by the network side, rather than by the second communication device (e.g., the terminal side). This not only reduces the computational pressure on the second communication device, but also improves the deployment efficiency of the channel estimation model.

[0038] In one possible implementation, the method further includes: transmitting a first pseudo-random sequence, a second pseudo-random sequence, and a second observation sequence to a server of the second communication device, wherein the second observation sequence is obtained after the second pseudo-random sequence is transmitted through a channel between the first and second communication devices; and acquiring characteristics of the channel from the server of the second communication device.

[0039] In the above implementation, the second communication device needs to interact with the server of the second communication device to realize the model inference process of the channel estimation model. In other words, the channel estimation model is not deployed on the second communication device, but may be deployed on another device (i.e. the server of the second communication device) independent of the second communication device to reduce the operating burden of the second communication device. In addition, the subsequent model inference process will also be executed by the server of the first communication device, which can effectively reduce the computational pressure of the first communication device and improve the operating performance of the first communication device.

[0040] Fifthly, embodiments of this application provide a communication device including a processor and a transceiver. The transceiver is used to send and receive information, and the processor is used to enable the communication device to implement the method as described in the second aspect or any of the implementations in the second aspect.

[0041] In a sixth aspect, embodiments of this application provide a communication device, which includes a processor and a transceiver. The transceiver is used to send and receive information, and the processor is used to enable the communication device to implement the method as described in the fourth aspect or any of the implementations in the fourth aspect.

[0042] In a seventh aspect, this application provides a communication device that includes at least a processor. The processor executes computer-executable instructions to cause the communication device to implement the method as described in the second aspect or any implementation thereof.

[0043] In conjunction with the seventh aspect, in one possible implementation, the communication device may further include interface circuitry. This interface circuitry is used to receive computer execution instructions and transmit them to the processor.

[0044] Eighthly, this application provides a communication device that includes at least a processor. The processor is configured to execute computer execution instructions to cause the communication device to implement the method as described in the fourth aspect or any of the implementations of the fourth aspect.

[0045] In conjunction with aspect eight, in one possible implementation, the communication device may further include interface circuitry. This interface circuitry is used to receive computer execution instructions and transmit them to the processor.

[0046] Ninthly, this application provides a computer-readable storage medium storing a computer program that, when executed, causes a communication device including a processor to implement the method as described in the second aspect or any of the second aspects, or to implement the method as described in the fourth aspect or any of the fourth aspects.

[0047] In a tenth aspect, embodiments of this application provide a computer program product including instructions that, when executed on a computer, cause the computer to implement a method as described in the second aspect or any of the second aspects, or to implement a method as described in the fourth aspect or any of the fourth aspects.

[0048] Eleventhly, embodiments of this application provide a communication system, which includes at least a first communication device and a second communication device. The first communication device is used to implement the method as described in the second aspect or any of the implementations of the second aspect, and the second communication device is used to implement the method as described in the fourth aspect or any of the implementations of the fourth aspect.

[0049] In a twelfth aspect, embodiments of this application provide a communication system that includes at least the communication device described in the fifth aspect and the communication device described in the sixth aspect.

[0050] The technical effects achieved in the above aspects can be referred to each other or to the beneficial effects in the method embodiments shown below, which will not be repeated here. Attached Figure Description

[0051] Figure 1a is a simplified schematic diagram of a communication system provided in an embodiment of this application;

[0052] Figure 1b is a simplified schematic diagram of another communication system provided in an embodiment of this application;

[0053] Figure 2 is a schematic diagram of a possible application framework in the communication system provided in an embodiment of this application;

[0054] Figure 3 is a schematic diagram of another possible application framework in the communication system provided in the embodiments of this application;

[0055] Figure 4 is a flowchart of a communication method provided in an embodiment of this application;

[0056] Figure 5a is a schematic diagram of a basic pattern of DMRS time and frequency resources provided in an embodiment of this application;

[0057] Figure 5b is a schematic diagram of another basic pattern of DMRS time-frequency resources provided in an embodiment of this application;

[0058] Figure 6 is a flowchart of another communication method provided in an embodiment of this application.

[0059] Figure 7 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0060] Figure 8 is a schematic diagram of the structure of another communication device provided in an embodiment of this application. Detailed Implementation

[0061] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0062] In the description of this application, terms such as "first" and "second" are used only to distinguish different objects, not to describe a specific order. Furthermore, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Additionally, "at least one" refers to one or more, and "multiple" refers to two or more. "One or more of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, and c can be single or multiple.

[0063] The terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0064] In this application, the words "exemplary" or "for example" are used to indicate that something is an example, illustration, or illustration. Any embodiment or design described as "exemplary," "for example," or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of the words "exemplary," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0065] It is understood that in this application, "when," "if," and "if" all refer to the device performing a corresponding action under certain objective circumstances, and are not time-limited, nor do they require the device to perform a judgment action when it is implemented, nor do they imply any other limitations. The device performing a corresponding action under certain objective circumstances includes: satisfying the objective circumstances, i.e., being able to perform the corresponding action; or satisfying both the objective circumstances and other circumstances, in order to perform the corresponding action.

[0066] In this application, "simultaneous" can be understood as "parallel", or at the same point in time, or within a period of time, or within the same cycle. The specific meaning can be understood in conjunction with the context.

[0067] In this application, the use of singular designations for elements is intended to represent "one or more" rather than "one and only one," unless otherwise specified.

[0068] It is understood that in the various embodiments of this application, phrases such as "B corresponding to A," "A corresponds to B," or similar expressions indicate that B is associated with A, and B can be determined based on A. This includes determining information B solely based on A, as well as determining B based on A and other information. Furthermore, the use of A to determine information B can also include indirect determination, such as B being determined based on C, and C being determined based on A.

[0069] In this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which can include direct transmission via the air interface or indirect transmission by other units or modules via the air interface. "Receive information from YY" can be understood as the source of the information being YY, which can include direct reception from YY via the air interface or indirect reception from YY by other units or modules via the air interface. "Send" can also be understood as the "output" of a chip interface, and "receive" can also be understood as the "input" of a chip interface. In other words, sending and receiving can occur between devices, for example, through buses, traces, or interfaces between components, modules, chips, software modules, or hardware modules within a device.

[0070] The technical solutions provided in this application can be applied to various communication systems, such as: 5th generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area network (WLAN) systems, satellite communication systems, future communication systems such as 6th generation (6G) mobile communication systems, or integrated systems of multiple systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0071] In a communication system, one network element can send signals to or receive signals from another network element. These signals can include information, signaling, or data. The term "network element" can also be replaced by an entity, network entity, device, communication equipment, communication module, node, communication node, communication apparatus, etc. This disclosure uses a communication apparatus as an example. For instance, a communication system can include at least one terminal device and at least one network device. The network device can send downlink signals to the terminal device, and / or the terminal device can send uplink signals to the network device. It is understood that the network device in this disclosure can be replaced by a first communication apparatus, and the terminal device can be replaced by a second communication apparatus, both performing the corresponding communication methods described in this disclosure.

[0072] It should be understood that in this application, terminal devices and / or network devices may perform some or all of the steps in the various embodiments. These steps or operations are merely examples, and other operations or variations thereof may also be performed in the embodiments of this application. Furthermore, the steps may be performed in different orders as presented in the various embodiments, and it is not necessarily necessary to perform all the operations in the embodiments of this application.

[0073] In the embodiments of this application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user apparatus.

[0074] Terminal devices can be devices that provide voice / data, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving vehicles, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0075] As an example and not a limitation, in this application embodiment, wearable devices can also be called wearable smart devices. This is a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices; they achieve powerful functions through software support, data interaction, and cloud interaction. Broadly defined, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functionality without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific application function and require use with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0076] In this embodiment, the device for implementing the functions of the terminal device can be the terminal device itself, or it can be any device capable of supporting the terminal device in implementing those functions, such as a chip system. This device can be installed in or used in conjunction with the terminal device. In this embodiment, the chip system can be composed of chips or may include chips and other discrete components. This embodiment only uses the terminal device as an example to illustrate the device for implementing the functions of the terminal device, and does not constitute a limitation on the solution of this embodiment.

[0077] The network device in this application embodiment can be a device for communicating with a terminal device. This network device can also be called an access network device or a wireless access network device, such as a base station. In this application embodiment, the network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. A base station can broadly encompass, or be replaced by, various names including: NodeB, evolved NodeB (eNB), next-generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, auxiliary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station can be a macro base station, micro base station, relay node, donor node, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, equipment performing base station functions in D2D, V2X, and M2M communications, network-side equipment in 6G networks, and equipment performing base station functions in future communication systems. A base station can support networks using the same or different access technologies. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). The embodiments of this application do not limit the specific technologies or equipment forms used in the network equipment.

[0078] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0079] In some deployments, the network devices mentioned in the embodiments of this application may be devices including CU, DU, or CU and DU, or devices with control plane CU nodes (central unit-control plane (CU-CP)) and user plane CU nodes (central unit-user plane (CU-UP)) and DU nodes. For example, the network devices may include gNB-CU-CP, gNB-CU-UP, and gNB-DU.

[0080] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CU-CPs, CU-UPs, or RUs. CUs and DUs can be configured separately or included in the same network element, such as a BBU. RUs can be included in radio frequency equipment or radio frequency units, such as RRUs, AAUs, or RRHs.

[0081] RAN nodes can support one or more types of fronthaul interfaces, each corresponding to a DU and RU with different functions. If the fronthaul interface between the DU and RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and RU is another type of interface, relative to CPRI, some downlink and / or uplink baseband functions, such as, for downlink, precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix addition, are moved from the DU to the RU; for uplink, digital beamforming (BF), or one or more of fast Fourier transform (FFT) / cyclic prefix removal, are moved from the DU to the RU. In one possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the segmentation between DU and RU differs, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0082] Taking eCPRI Cat A as an example, for downlink transmission, layer mapping is used as the dividing line. The DU is configured to implement one or more functions preceding layer mapping (i.e., coding, rate matching, scrambling, modulation, and layer mapping itself). Other functions following layer mapping (e.g., resource element (RE) mapping, digital beamforming, or inverse fast Fourier transform / adding a cyclic prefix) are implemented in the RU. For uplink transmission, de-RE mapping is used as the dividing line. The DU is configured to implement one or more functions preceding de-mapping (i.e., decoding, rate matching de-matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and de-RE mapping itself). Other functions following de-mapping (e.g., digital beamforming or fast Fourier transform (FFT) / de-CP) are implemented in the RU. It is understood that descriptions of the functions of the DU and RU corresponding to various types of eCPRI can be found in the eCPRI protocol and will not be elaborated upon here.

[0083] In one possible design, the processing unit in the BBU used to implement baseband functions is called the baseband high (BBH) unit, and the processing unit in the RRU / AAU / RRH used to implement baseband functions is called the baseband low (BBL) unit.

[0084] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0085] In this embodiment, the apparatus for implementing the functions of a network device can be a network device itself; it can also be an apparatus capable of supporting the network device in implementing those functions, such as a chip system, hardware circuit, software module, or a hardware circuit plus a software module. This apparatus can be installed in the network device or used in conjunction with the network device. In this embodiment, the example of a network device being used to implement the functions of a network device is provided only and does not constitute a limitation on the solutions described in this embodiment.

[0086] Network devices and / or terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located. Furthermore, terminal devices and network devices can be hardware devices, or software functions running on dedicated hardware or general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities that include dedicated or general-purpose hardware devices and software functions. This application does not limit the specific form of the terminal devices and network devices.

[0087] The system architecture used in the embodiments of this application is described below. It should be noted that the system architecture and application scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, as the system architecture or application scenarios evolve, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0088] For example, please refer to Figure 1a, which is a simplified schematic diagram of a communication system provided in an embodiment of this application. As shown in Figure 1a, the communication system A includes a wireless access network, which can be a next-generation (e.g., 6G or higher) wireless access network or a traditional (e.g., 5G, 4G, 3G or 2G) wireless access network.

[0089] The communication system A may include at least one network device, such as network device 110 shown in FIG1a; the communication system A may also include at least one terminal device, such as terminal device 120 and terminal device 130 shown in FIG1a. Network device 110 and terminal devices (such as terminal devices 120 and 130) can communicate via a wireless link. The communication devices in the communication system A, for example, network device 110 and terminal device 120, can communicate with each other through multi-antenna technology.

[0090] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, leading to increasingly diverse requirements. For example, networks need to support ultra-high speeds, ultra-low latency, and / or massive connectivity. This characteristic makes network planning, network configuration, and / or resource scheduling increasingly complex. Furthermore, as network functions become more powerful, such as supporting higher spectrum levels, supporting higher-order multiple-input multiple-output (MIMO) technologies, supporting beamforming, and / or supporting beam management, network energy efficiency has become a hot research topic. These new requirements, new scenarios, and new characteristics bring unprecedented challenges to network planning, operation, and efficient operation. To meet these challenges, artificial intelligence (AI) technology can be introduced into wireless communication networks to achieve network intelligence.

[0091] Artificial intelligence (AI) enables machines to possess human-like intelligence, such as allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve AI, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. These models represent the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result.

[0092] In the process of training a machine learning model, a loss function can be defined. The loss function describes the difference between the model's output value and the desired target value. The loss function can be expressed in various forms, and there are no restrictions on its specific form. The model training process can be viewed as follows: by adjusting some or all of the model's parameters, the value of the loss function is made to be less than a threshold or to meet the target requirement.

[0093] A model can also be called an AI model, a rule, or other names. An AI model can be considered a specific method for implementing AI functions. An AI model represents the mapping relationship or function between the model's input and output. AI functions can include one or more of the following: data collection, model training (or model learning), model information dissemination, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model validation, or inference result publication, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0094] To support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0095] Optionally, the AI ​​node can be deployed in one or more of the following locations within the communication system: access network devices, terminal devices, or core network devices, etc. Alternatively, the AI ​​node can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements, etc.

[0096] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0097] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0098] AI nodes can also be called AI network elements, AI devices, AI entities, AI modules, or AI units, etc.

[0099] The AI ​​network element here can be directly connected to network devices, or connected to terminal devices, or simultaneously connected to both network device 110 and terminal devices. Alternatively, the AI ​​network element can also be connected to network devices through a third-party network element. This application embodiment does not limit the connection relationship between the AI ​​network element and other network elements. The third-party network element can be a core network element such as an authentication management function (AMF) network element or a user plane function (UPF) network element, an operation administration and maintenance (OAM) management network element, a cloud server, or other network elements, without limitation. For example, this independent network element can be deployed on one or more of the following: the network device side, the terminal device side, or the core network side. Optionally, it can be deployed on a cloud server.

[0100] For ease of understanding, the following explanation uses the direct connection between the AI ​​network element and the network device as an example. For instance, please refer to Figure 1b, which is a simplified schematic diagram of another communication system provided in an embodiment of this application. As shown in Figure 1b, compared to the communication system A shown in Figure 1a, the communication system B shown in Figure 1b further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building training datasets or training AI models.

[0101] In one possible implementation, network device 110 can send data related to the training of the AI ​​model to AI network element 140, which then constructs a training dataset and trains the AI ​​model. For example, if the AI ​​model is a channel estimation model (i.e., used to predict the channel between two communication devices), the training dataset can be a pseudo-random sequence used to train the channel estimation model, and the data related to the training of the AI ​​model can include parameters used to generate the pseudo-random sequence.

[0102] AI network element 140 can send the results of AI model-related operations to network device 110, and forward them to terminal devices via network device 110. For example, the results of AI model-related operations may include at least one of the following: a trained AI model, model evaluation results, or test results. Exemplarily, a portion of the trained AI model may be deployed on network device 110, and another portion on the terminal device. Alternatively, the trained AI model may be deployed on network device 110. Or, the trained AI model may be deployed on the terminal device.

[0103] In one possible implementation, the AI ​​network element 140 can also be configured as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device shown in FIG1b.

[0104] It should be noted that Figures 1a and 1b are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 1a and 1b. In practical applications, the communication system may include multiple network devices and multiple terminal devices simultaneously. A network device may serve one or more terminal devices simultaneously. A terminal device may also access one or more network devices simultaneously. The embodiments of this application do not limit the number of terminal devices and network devices included in the communication system.

[0105] Further, please refer to Figure 2, which is a schematic diagram of a possible application framework in the communication system provided in the embodiments of this application. As shown in Figure 2, network elements in the communication system are connected through interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network device 230, access network node 220 (RAN node), terminal device 210, or one or more OAM devices, are equipped with one or more AI modules (only one is shown in Figure 2 for clarity). Access network node 220 can be a single RAN node or can include multiple RAN nodes, for example, including CU and DU. CU and / or DU can also be equipped with one or more AI modules. Optionally, CU can also be split into CU-CP and CU-UP. CU-CP and / or CU-UP are equipped with one or more AI models.

[0106] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the neural network biases.

[0107] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0108] Optionally, the network device can be a network device equipped with one or more AI modules. The network device can be one or more of the core network device 230, access network node (RAN node) 220, or OAM as shown in Figure 2. Here, the AI ​​module can be a RAN intelligent controller (RIC), such as a near-real-time RIC (near-RT RIC) or a non-real-time RIC (non-RT RIC). For example, the near-real-time RIC is located in the RAN node (e.g., in the CU, DU), while the non-real-time RIC is located in the OAM, cloud server, core network device, or other network device. The RIC can obtain a subset from multiple terminal devices from the RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU), reassemble it into a training dataset, and train based on the training dataset. Exemplarily, the near-real-time RIC and the non-real-time RIC can also be set up separately as a network element; the network device can be either a near-real-time RIC or a non-real-time RIC.

[0109] For example, please refer to Figure 3, which is a schematic diagram of another possible application framework in the communication system provided in the embodiments of this application. As shown in Figure 3, the communication system includes a Resource Interchange (RIC). For example, the RIC can be the AI ​​module shown in Figure 2, used to implement AI-related functions. The RIC includes near real-time RIC and non-real-time RIC. Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to latency, and the latency of this data can be on the order of seconds. The near real-time RIC mainly processes near real-time information, such as data that is relatively sensitive to latency, and the latency of this data can be on the order of tens of milliseconds.

[0110] Near real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. The near real-time RIC can obtain network-side and / or terminal-side information from access network nodes 320 (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminal devices 310. This information can be used as training data or inference data. Optionally, the near real-time RIC can deliver inference results to RAN nodes and / or terminal devices 310. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the near real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0111] Non-real-time RICs are also used for model training and inference. For example, they can be used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminal devices 310. This information can be used as training data or inference data, and the inference results can be delivered to the RAN nodes and / or terminal devices 310. Optionally, inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0112] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Optionally, near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CU, DU), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0113] To facilitate understanding of the technical solutions provided in the embodiments of this application, the relevant terminology of the communication system involved in the embodiments of this application will first be introduced:

[0114] 1. AI Model

[0115] AI models are function models that map inputs of a certain dimension to outputs of a certain dimension, and their parameters are obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be viewed as an AI model. a and b correspond to the parameters of the model and can be obtained through machine learning training. Since the AI ​​model disclosed herein is used to predict the channel between two communication devices, it can be called a channel estimation model.

[0116] 2. Neural Network (NN)

[0117] Neural networks, or artificial neural networks, are mathematical models that mimic the behavioral characteristics of animal neural networks to perform distributed parallel information processing. They are a specific implementation of AI or machine learning. Taking neural networks as an example of AI models, the AI ​​models disclosed herein can be deep neural networks (DNNs). Depending on the network's construction method, DNNs can include feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs), etc.

[0118] 3. Training data and inference data

[0119] In the field of machine learning, ground truth usually refers to data that is considered accurate or real.

[0120] In the field of communications, training data can include simulation data collected through simulation platforms, experimental data collected from experimental scenarios, or measured data collected in actual communication networks. Because the geographical environment and channel conditions at the source of the data vary—for example, indoor / outdoor conditions, movement speed, frequency bands, or antenna configurations—the collected data can be categorized during acquisition. For instance, data with the same channel propagation environment and antenna configuration can be grouped together.

[0121] Model training essentially involves learning certain features from training data. In training AI models (such as neural network models), the goal is to make the model's output as close as possible to the desired predicted value. This is achieved by comparing the network's current prediction with the target value and updating the weight vector of each layer based on the difference. (Of course, there's usually an initialization process before the first update, where parameters are pre-configured for each layer.) For example, if the network's prediction is too high, the weight vector is adjusted to predict a lower value. This adjustment continues until the AI ​​model can predict the target value or a value very close to it. Therefore, it's necessary to predefine "how to compare the difference between the predicted and target values," which is the loss function or objective function. These are important equations used to measure the difference between the predicted and target values. Taking the loss function as an example, a higher output value (loss) indicates a greater difference. Therefore, training the AI ​​model becomes a process of minimizing this loss, making the loss function value less than a threshold, or making the loss function value meet the target requirements. For example, if the AI ​​model is a neural network, adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers of the neural network, the width, the weights of the neurons, or the parameters in the activation function of the neurons.

[0122] Inference data can be used as input to a trained AI model for inference. During the model's inference process, the inference data is input into the AI ​​model, and the corresponding output, which is the inference result, is obtained.

[0123] It is understood that, since the AI ​​model involved in this application embodiment is a channel estimation model, the input of the channel estimation model can be a pseudo-random sequence. Therefore, in this application embodiment, the training data of the channel estimation model can be called the training sequence, and its inference data can be called the inference sequence.

[0124] To facilitate understanding of the technical methods provided in the embodiments of this application, the relevant technologies of the embodiments of this application will be briefly introduced as follows:

[0125] Existing channel estimation methods (e.g., an AI-based method) use a channel estimation model to fit the channel. During inference, if the inference sequence is the same as a training sequence—that is, the inference sequence is a DMRS sequence used by the channel estimation model during training—then the predicted channel value output by the model has a high similarity to the ground truth channel value. However, due to the diversity of DMRS, attempting to traverse all DMRS sequences during training makes it difficult for the channel estimation model to learn the features of all DMRS sequences. If the inference sequence is a new DMRS sequence—that is, a DMRS sequence that the model has not learned—then the predicted channel value output by the model has a low similarity to the ground truth channel value, resulting in low prediction accuracy. In other words, the channel estimation model performs poorly when the inference sequence differs from the training sequence.

[0126] To address the aforementioned issues, this application provides a communication method that ensures the channel estimation model maintains consistent performance during inference with that during training when the training and inference sequences differ. Specific implementation details can be found in the embodiments shown in Figures 4-6 below.

[0127] Further, please refer to Figure 4, which is a flowchart illustrating a communication method provided in an embodiment of this application. As shown in Figure 4, this method can be executed jointly by a first communication device and a second communication device. The first communication device can be the network device 110 (e.g., a base station) shown in Figure 1a or Figure 1b, and the second communication device can be any of the terminal devices shown in Figure 1a or Figure 1b (e.g., terminal device 120). This method can include at least steps S401-S402:

[0128] In step S401, the first communication device sends first information to the second communication device. The first information is used to indicate a first pseudo-random sequence. The first pseudo-random sequence is used to train a channel estimation model. The channel estimation model is used to predict the channel between the first communication device and the second communication device. The channel is predicted based on the first pseudo-random sequence and the second pseudo-random sequence.

[0129] Correspondingly, the second communication device receives the first information from the first communication device.

[0130] In one possible implementation, the first pseudo-random sequence can be understood as the training sequence of the channel estimation model, and the second pseudo-random sequence is the inference sequence of the channel estimation model. In other words, the second pseudo-random sequence is the pseudo-random sequence transmitted by the first communication device and the second communication device during actual communication.

[0131] In this application, the pseudo-random sequence involved in the embodiments can be a sequence used to map a reference signal (i.e., a reference signal sequence). If the reference signal is a DMRS, then the pseudo-random sequence is a sequence used to map the DMRS, which can also be understood as the pseudo-random sequence being carried in the DMRS. Optionally, the pseudo-random sequence involved in this application embodiment can also be a DMRS sequence, and this will not be limited here.

[0132] For example, the first and second pseudo-random sequences here are sequences used to map DMRS, or the first and second pseudo-random sequences are DMRS sequences.

[0133] It is understandable that the first communication device sends the first information to the second communication device in order to allow the first pseudo-random sequence (i.e., the training sequence of the channel estimation model) to participate in the model inference process of the channel estimation model, so as to maintain the model performance during the training of the channel estimation model when the first pseudo-random sequence is different from the second pseudo-random sequence. Therefore, the first communication device needs to send the first information to the second communication device before performing model inference on the channel estimation model.

[0134] For example, if the training process of the channel estimation model is executed on the second communication device side, the first communication device can send the first information while transmitting the initial channel estimation model to the second communication device. That is, the first communication device not only needs to send information indicating the initial channel estimation model (i.e., the third information) to the second communication device, but also needs to send the first information. For ease of explanation, in this embodiment, the initial channel estimation model (i.e., the untrained channel estimation model) can be referred to as the first model, and the trained channel estimation model as the target model. The first model and the target model are merely names of the channel estimation model at different times; their structural parameters remain unchanged.

[0135] For example, if the training sequence changes during the model update process of the channel estimation model, the first communication device can send first information to the second communication device. Exemplarily, the first communication device can use a training sequence (e.g., a pseudo-random sequence S1) to train the first model and obtain the second model. When the second model does not meet the model convergence condition, this embodiment needs to update the second model. For example, this embodiment can retrain the second model using the original training sequence (i.e., the pseudo-random sequence S1) or a new training sequence (e.g., the pseudo-random sequence S2) until the retrained second model meets the model convergence condition, at which point the model update ends, and the target model is obtained. During the model update process, if the training sequence changes, the first communication device needs to send first information to the second communication device so that the second communication device understands the new training sequence.

[0136] In one possible implementation, the first information includes one or more of the following: parameters for generating the first pseudo-random sequence, or an identifier of the first pseudo-random sequence. For example, this first information may be carried in downlink control information (DCI).

[0137] In one possible implementation, the first information mentioned above includes parameters for generating the first pseudo-random sequence, which may include one or more of the following: time slot index (or frame index), orthogonal frequency division multiplexing (OFDM) symbol index, and scrambling code identifier (scrambling code ID), etc.

[0138] For example, the formula for generating the reference signal sequence (e.g., the DMRS sequence) can be found in the following formula (1):

[0139] Here, r(n) can be used to represent the nth element in the reference signal sequence, and c(n) can be used to represent the nth element in the pseudo-random sequence.

[0140] The initial value of the pseudo-random sequence (c) init It can satisfy the following formula (2):

[0141] The meaning of each parameter in the formula will be explained below:

[0142] The number of symbols used to represent each time slot;

[0143] Used to represent the slot index, that is, the number of slots in a frame, specifically it can be expressed as: the number of slots contained in frame f when the subcarrier spacing is μ;

[0144] l is used to represent the symbol index, that is, the number of symbols in the slot;

[0145] n SCID The value range is (0,1). If the higher-level parameter is configured with a scrambling code ID, then... If high-level parameters are not configured, then Configured as the physical cell ID of the serving cell.

[0146] In another possible implementation, the first information includes an identifier for a first pseudo-random sequence. This identifier is mapped to the first pseudo-random sequence, and this mapping is predefined. The first pseudo-random sequence is selected from a training sequence set (including N already generated pseudo-random sequences), where N is a positive integer. The selection method can be random or based on evaluation parameters (e.g., sequence generation time); this is not limited here.

[0147] Among them, the N pseudo-random sequences can be pseudo-random sequences that have reached a consensus between the first communication device and the second communication device. For example, the N pseudo-random sequences can be predefined in the communication protocols supported by the first and second communication devices, or the N pseudo-random sequences may be sent by the first communication device to the second communication device in advance.

[0148] For example, if the N pseudo-random sequences are predefined in the communication protocol, the communication protocol can also predefine the mapping relationship between the N pseudo-random sequences and their identifiers. This mapping relationship can be illustrated using a table or implemented in code; no specific limitation will be imposed here.

[0149] For ease of understanding, please refer to Table 1, which is a schematic diagram of a mapping relationship provided in an embodiment of this application. For clarity, the number N of pseudo-random sequences in Table 1 can be taken as 4, specifically including sequence S1, sequence S2, sequence S3, and sequence S4. See below for details:

[0150] Table 1

[0151] In this embodiment, an identifier can indicate one pseudo-random sequence or multiple pseudo-random sequences. As shown in Table 1 above, identifier 1 can indicate three pseudo-random sequences, i.e., sequences S1, S2, and S3 correspond to the same identifier, while identifier 2 can indicate one pseudo-random sequence (i.e., sequence S4). The three pseudo-random sequences corresponding to identifier 1 may be similar sequences, meaning that the similarity between any two sequences S1, S2, and S3 satisfies a first preset threshold. This similarity can be measured using parameters such as cosine similarity or mean squared error. Of course, the three pseudo-random sequences corresponding to identifier 1 may also be sequences generated at the same time or collected from the same device; this will not be limited here.

[0152] Optionally, the communication protocol may also predefine parameters for generating pseudo-random sequences, which may include one or more of the following: slot index (or frame index), symbol index, and scrambling code identifier (scrambling code ID), etc.

[0153] It should be noted that the items shown in Table 1 above are merely a reference format. In actual business scenarios, other items can be created according to requirements (such as parameters used to generate pseudo-random sequences, generation time of pseudo-random sequences, etc.). This application embodiment does not limit the specific form of Table 1. Furthermore, "table" is only one format; other structures such as lists can also be used, which will not be limited here.

[0154] For example, if the identifier in the first information is identifier 1 as shown in Table 1 above, then after receiving the first information, the second communication device can look up the mapping relationship of identifier 1 in Table 1. Since the mapping relationship of identifier 1 indicates three pseudo-random sequences, sequence S1, sequence S2, and sequence S3, the second communication device can select one of these three pseudo-random sequences as the first pseudo-random sequence. It can be understood that all three pseudo-random sequences participate in the model training process of the channel estimation model, that is, all three pseudo-random sequences belong to the training sequences of the channel estimation model.

[0155] In one possible implementation, the first information may include indication information and / or time-frequency location information, whereby the time-frequency location information is used to determine the second pseudo-random sequence, and the indication information is used to indicate that the second pseudo-random sequence is the same as the first pseudo-random sequence. In other words, the first information here can be used to indicate the relationship between the transmitted pseudo-random sequence and the training sequence.

[0156] In this embodiment, the first and second pseudo-random sequences can be DMRS sequences as examples. The generation method of the DMRS sequence depends on the specific waveform used. The method of mapping the DMRS sequence to physical time-frequency resource units has a clear formula definition in the communication protocol, which can generate a finite number of DMRS patterns by giving the possible values ​​(ranges) of each parameter. Specifically, the position of the DMRS in a single time-frequency resource block (RB) is mainly determined by the following parameters:

[0157] Mapping types: Specifically, there are Mapping Type A and Mapping Type B. In Type A, the DMRS time-domain structure is such that the first DMRS symbol is located in symbol #2 or symbol #3 within the time slot. Type A is primarily used in scenarios where data transmission occupies the majority of symbols in the time slot. In Type B, the first DMRS symbol is fixedly mapped to the first OFDM symbol of the Physical Downlink Shared Channel (PDSCH) / Physical Uplink Shared Channel (PUSCH). Type B is primarily used in scenarios where the PDSCH / PUSCH occupies only a small portion of the symbols in a time slot, to reduce transmission latency.

[0158] DMRS configuration type: This determines the frequency domain resource location of the DMRS. Specifically, it can include DMRS configuration type 1 (or simply type 1) and DMRS configuration type 2 (or simply type 2). DMRS configuration type 1 has a comb-like distribution in the frequency domain, divided into two code division multiplexing (CDM) groups, with CDM used between ports within each group. DMRS configuration type 2 is divided into three CDM groups, with CDM used between ports within each group.

[0159] DMRS Additional Position: Used to determine whether there is an additional DMRS in the time domain.

[0160] Maximum Length (maxLength): Used to determine whether it is a single-symbol DMRS or a double-symbol DMRS.

[0161] In non-overlay systems, DMRS and data are orthogonal in time and frequency. If DMRS occupies only a portion of OFDM symbols, the communication method provided in this application embodiment can be applied to these OFDM symbols. For example, please refer to Figure 5a, which is a schematic diagram of a basic pattern of DMRS time-frequency resources provided in this application embodiment. As shown in Figure 5a, the mapping type corresponding to this pattern can be mapping type A, and the DMRS configuration type can be configuration type 1. Its maximum length can be 1, used to indicate a single symbol. A single symbol DMRS supports a maximum of 4 antenna ports, divided into a first CDM group (e.g., {1000, 1001}) and a second CDM group (e.g., {1002, 1003}).

[0162] In the time domain, a time slot can contain 14 symbols, corresponding to indices 0-13. In the frequency domain, an RB contains 12 subcarriers, corresponding to indices 0-11. A resource element (RE) corresponds to one symbol in the time domain and one subcarrier in the frequency domain. Within the time-frequency resource grid corresponding to one symbol and one RB, the first CDM group occupies subcarriers with even-numbered indices, i.e., subcarrier indices 0, 2, 4, 6, 8, 10. The second CDM group occupies subcarriers with odd-numbered indices, i.e., subcarrier indices 1, 3, 5, 7, 9, 11. A DMRS port within an RB has 6 REs available for transmitting pilot signals. It is understood that "pilot" here can refer to "DMRS". As shown in Figure 5a, the time-frequency resource blocks corresponding to the two CDM groups represent locations carrying DMRS signals.

[0163] For example, if the first information includes time-frequency location information and indication information, and the time-frequency location information includes subcarrier index (e.g., 1, 3, 5, 7, 9, 11) and time domain index (e.g., 2), it can be understood that the first pseudo-random sequence and the second pseudo-random sequence are the same, both being the 6 DMRS signals carried by the time-frequency resource block corresponding to the second CDM group shown in Figure 5a.

[0164] In an overlay system, REs can overlay transmitted data and pilot signals (e.g., DMRS), therefore, one DMRS sequence is required for each OFDM symbol. For example, please refer to Figure 5b, which is a schematic diagram of another basic pattern of DMRS time-frequency resources provided in an embodiment of this application. As shown in Figure 5b, pilot signals can be overlaid on data for transmission. In the time domain, a time unit (e.g., a subframe or time slot) can contain 14 symbols, with corresponding indices from 0 to 13; in the frequency domain, an RB can contain 12 subcarriers, with corresponding indices from 0 to 11. One resource unit corresponds to one symbol in the time domain and one subcarrier in the frequency domain. Sequence S0 can be used to represent the DMRS sequence transmitted on the 0th symbol, sequence S1 can be used to represent the DMRS sequence transmitted on the 1st symbol, and so on. 13 It can be used to represent a DMRS sequence sent on the 13th symbol.

[0165] For example, if the first information includes time-frequency location information and indication information, and the time-frequency location information includes a time-domain index (e.g., 3), it can be understood that the first pseudo-random sequence and the second pseudo-random sequence are the same, both being the sequence S3 shown in Figure 5b.

[0166] Optionally, before the first communication device informs the second communication device of the first pseudo-random sequence, the second communication device may have already received the second pseudo-random sequence from the first communication device. Therefore, the first communication device does not need to repeatedly inform the second communication device of the second pseudo-random sequence. That is, the first information sent by the first communication device to the second communication device may not include time-frequency location information. In other words, the first information at this time includes indication information. Generally speaking, the data volume of the indication information is small (e.g., 1 bit). This can effectively reduce the transmission overhead between the first and second communication devices and improve communication performance.

[0167] In step S402, the first communication device sends a second pseudo-random sequence to the second communication device.

[0168] Correspondingly, the second communication device can receive the second observation sequence, which is obtained by transmitting the second pseudo-random sequence through the channel between the first and second communication devices. In other words, the second observation sequence refers to the observation sequence corresponding to the inference sequence of the channel estimation model. The first communication device can send the second pseudo-random sequence to the second communication device on the PDSCH.

[0169] The order of steps S402 and S401 is not limited. They can be executed simultaneously, or step S402 can be executed first and then step S401 can be executed first and then step S401.

[0170] It is understandable that the second communication device can also acquire the second pseudo-random sequence. For example, the first communication device can send parameters for generating the second pseudo-random sequence to the second communication device so that the second communication device can generate the second pseudo-random sequence based on the parameters. Or, for example, the first communication device can send time-frequency location information to the second communication device so that the second communication device can determine the second pseudo-random sequence based on the time-frequency location information. Here, the method by which the second communication device acquires the second pseudo-random sequence will not be limited.

[0171] In one possible implementation, after acquiring the second pseudo-random sequence, the first pseudo-random sequence, and the second observation sequence, the second communication device can perform model inference on the channel estimation model based on these three pseudo-random sequences. For example, the second communication device can input these three pseudo-random sequences into the channel estimation model, and predict the channel between the first and second communication devices through the channel estimation model. In other words, the equivalent information in this embodiment is predicted based on the first pseudo-random sequence, the second pseudo-random sequence, and the second observation sequence. That is, the input to the channel estimation model includes not only the second pseudo-random sequence and the second observation sequence, but also the first pseudo-random sequence. This allows for accurate channel prediction even when the first and second pseudo-random sequences are different, effectively maintaining the model performance during channel estimation model training.

[0172] For ease of explanation, in this embodiment, the pseudo-random sequence after the first pseudo-random sequence is transmitted through the channel between the first communication device and the second communication device can be referred to as the first observation sequence (i.e., the observation sequence of the training sequence). It is understood that when the first pseudo-random sequence and the second pseudo-random sequence are the same, the observation sequence of the training sequence and the observation sequence of the inference sequence should be the same. However, when the first pseudo-random sequence and the second pseudo-random sequence are different, there will be a difference between the observation sequence of the training sequence and the observation sequence of the inference sequence. Therefore, in this embodiment, the observation sequence of the inference sequence needs to be preprocessed to more accurately represent the observation sequence of the training sequence. The method of preprocessing the observation sequence of the inference sequence (represented by y2) on each RE can be found in the following formula (3):

[0173] Wherein, P1 can be used to represent the training sequence of the channel estimation model (i.e., the first pseudo-random sequence), P2 can be used to represent the inference sequence of the channel estimation model (i.e., the second pseudo-random sequence), and y1 can be used to represent the pseudo-random sequence after the training sequence is transmitted through the channel (i.e., the first observation sequence, the observation sequence of the training sequence).

[0174] In this embodiment, before performing model inference on the channel estimation model, the first communication device needs to send not only the first information to the second communication device, but also the second pseudo-random sequence. This means that the second communication device not only knows that the inference sequence of the channel estimation model is the second pseudo-random sequence, but also that the training sequence of the channel estimation model is the first pseudo-random sequence. Subsequently, during model inference, the input to the channel estimation model includes not only the second pseudo-random sequence and the second observation sequence, but also the first pseudo-random sequence. In other words, the training sequence of the channel estimation model also participates in the model inference process. Through the first pseudo-random sequence, the second pseudo-random sequence, and the second observation sequence, the features already learned by the channel estimation model (i.e., the observation sequence of the first pseudo-random sequence) can be constructed as much as possible. Thus, even if there are differences between the first and second pseudo-random sequences, the channel between the first and second communication devices can still be accurately predicted through the channel estimation model. In other words, this embodiment does not require the training sequence and the inference sequence to be the same; that is, when the training sequence and the inference sequence are different, the model performance during training can be effectively maintained.

[0175] Generally, the training process of the channel estimation model is performed by the network side (e.g., the first communication device, or the server of the first communication device), or by the terminal side (e.g., the second communication device, or the server of the second communication device), and will not be limited here.

[0176] In one possible implementation, if the training process of the channel estimation model is performed by the network side (e.g., the first communication device or its server), then upon completion of the channel estimation model training, the first communication device needs to transmit the trained channel estimation model to the second communication device. For example, the first communication device needs to send second information to the second communication device, which instructs the channel estimation model and may include structural parameters and weights of the channel estimation model.

[0177] For example, if the training process of the channel estimation model is executed by the server of the first communication device, the first communication device also needs to transmit a first observation sequence and a first pseudo-random sequence to its server. The first observation sequence is obtained by transmitting the first pseudo-random sequence through the channel between the first and second communication devices. It is understood that the first observation sequence can be obtained by transmitting the first pseudo-random sequence through an actual channel between the first and second communication devices, or it can be obtained by transmitting the first pseudo-random sequence through a simulated channel between the first and second communication devices; this is not limited here. The first pseudo-random sequence and the first observation sequence are used to train the channel estimation model. After training, the first communication device can obtain second information from its server.

[0178] The channel estimation model can be implemented on the AI / Graphics Processing Unit (GPU) chip inside the UE terminal, or it can be implemented outside the device, such as in the host of the over-the-top system or a cloud server. In other words, the inference process of the channel estimation model can be executed by the second communication device or by the server of the second communication device; this will not be limited here.

[0179] For ease of understanding, please refer to Figure 6, which is a flowchart illustrating another communication method provided in this application embodiment. As shown in Figure 6, this method can be jointly executed by a first communication device, a second communication device, and a server of the second communication device. The first communication device can be the network device 110 (e.g., a base station) shown in Figure 1a or Figure 1b, and the second communication device can be any of the terminal devices shown in Figure 1a or Figure 1b (e.g., terminal device 120). This method includes at least a model training process and a model inference process. The model training process is mainly executed by the first communication device, specifically including steps S601-S604, while the model inference process is mainly executed by the server of the second communication device, specifically including steps S605-S609, as shown below:

[0180] Step S601: The first communication device configures the first pseudo-random sequence.

[0181] Here, the first pseudo-random sequence can be a single pseudo-random sequence, or multiple pseudo-random sequences corresponding to the same identifier, or it may be selected from a finite number of pseudo-random sequences predefined by the communication protocol. No restrictions will be placed on it here.

[0182] It is understood that the embodiments of this application do not require a large number of training sequences to participate in the model training process of the channel estimation model. Instead, the first communication device can specify a uniform pseudo-random sequence to train the channel estimation model. This can not only reduce the time consumed by model training, but also reduce the difficulty of model training.

[0183] In step S602, the first communication device sends a first pseudo-random sequence to the second communication device.

[0184] If the first pseudo-random sequence is a single pseudo-random sequence, then the pseudo-random sequence transmitted by the first communication device on each symbol is the same. For example, if the basic pattern of the time-frequency resources of the first pseudo-random sequence is as shown in Figure 5b above, then sequence S0, sequence S1, ..., and sequence S... 13 Both can represent the same pseudo-random sequence.

[0185] Step S603: The first communication device acquires the first observation sequence.

[0186] The first observation sequence is obtained by transmitting the first pseudo-random sequence through the channel between the first communication device and the second communication device.

[0187] Understandably, after executing steps S602 and S603, the first communication device can train the channel estimation model based on the first pseudo-random sequence and the first observation sequence. For example, the first communication device can input the first pseudo-random sequence and the first observation sequence into an initial channel estimation model (i.e., the first model), and the first model outputs the predicted features of the channel. Then, the first communication device determines the loss value of the first model based on the predicted features of the channel and the actual features of the channel. This loss value is used to characterize the similarity between the predicted features of the channel and the actual features of the channel.

[0188] If the first model meets the model convergence condition, then the first model is determined as the trained channel estimation model (i.e., the target model). If the first model does not meet the model convergence condition, then the model parameters of the first model need to be adjusted based on the loss value of the first model until the adjusted first model meets the model convergence condition, thus obtaining the target model. Here, the model convergence condition can be that the model loss has not continued to decrease for N rounds (e.g., 10 rounds), i.e., model training stops. Optionally, the model convergence condition can also be that the model loss is less than the loss threshold in the model convergence condition, i.e., model training stops. This will not be limited here.

[0189] In step S604, the first communication device sends the second information to the server of the second communication device.

[0190] Here, the second piece of information indicates the channel estimation model, which can refer to a trained channel estimation model. This second piece of information may include the structural parameters and weights of the trained channel estimation model.

[0191] In step S605, the first communication device sends first information to the second communication device.

[0192] The first information is used to indicate the first pseudo-random sequence.

[0193] Step S606: The first communication device sends a second pseudo-random sequence to the second communication device.

[0194] For the specific implementation of steps S605-S606, please refer to the description of steps S401-S402 in the embodiment corresponding to Figure 4 above, which will not be repeated here.

[0195] In step S607, the second communication device transmits the first pseudo-random sequence, the second pseudo-random sequence, and the second observation sequence to the server of the second communication device.

[0196] The second observation sequence is obtained by transmitting the second pseudo-random sequence through the channel between the first and second communication devices.

[0197] Step S608: The server of the second communication device predicts the channel.

[0198] For example, the server of the second communication device can refer to the above formula (3), first preprocess the second observation sequence to construct the observation sequence of the first pseudo-random sequence, and then learn the first pseudo-random sequence and the observation sequence of the first pseudo-random sequence through the trained channel estimation model to predict the channel between the first communication device and the second communication device.

[0199] Step S609: The second communication device acquires the characteristics of the channel from the server of the second communication device.

[0200] In the embodiments of this application, the first communication device and the second communication device can perform signaling interaction and model distribution operations. The deployment of the channel estimation model may not be in the same physical entity as the second communication device. That is to say, the signaling interaction here can also be the interaction between the first communication device and other network elements (e.g., OTT) where the model is deployed. In other words, the communication method provided in the embodiments of this application is also applicable to the ORAN system. This not only improves the model performance when maintaining the channel estimation model during training, but also improves the flexibility of model deployment and saves costs.

[0201] The foregoing details the method provided in this application. To facilitate the implementation of the above-described solutions in the embodiments of this application, corresponding apparatus or devices are also provided in the embodiments of this application.

[0202] This application divides the communication device into functional modules according to the above method embodiments. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated modules can be implemented in hardware or as software functional modules. It should be noted that the module division in this application is illustrative and only represents one logical functional division; other division methods may be used in actual implementation. The communication device of the embodiments of this application will be described in detail below with reference to Figures 7 and 8.

[0203] Referring to Figure 7, which is a schematic diagram of a communication device provided in an embodiment of this application, the communication device 1 includes at least one of a transceiver module 71 and a processing module 72. These modules can perform the corresponding functions of the communication device in the above method embodiment. The transceiver module 71 can implement the corresponding communication function, and the processing module 72 is used to implement the corresponding processing function. For example, the transceiver module 71 can also be referred to as an interface, a communication interface, or a communication module, etc.

[0204] In some feasible implementations, the communication device 1 may correspond to the first communication device mentioned above, or to a component (such as a circuit, chip, or chip system) configured in the first communication device.

[0205] In a specific implementation, the transceiver module 71 is used to send first information to the second communication device. The first information is used to indicate a first pseudo-random sequence. The first pseudo-random sequence is used to train a channel estimation model. The channel estimation model is used to predict the channel between the first communication device and the second communication device. The channel is predicted based on the first pseudo-random sequence and the second pseudo-random sequence. The transceiver module 71 is also used to send a second pseudo-random sequence to the second communication device.

[0206] In one possible implementation, the second pseudo-random sequence is the inference sequence of the channel estimation model.

[0207] In one possible implementation, the first pseudo-random sequence and the second pseudo-random sequence are sequences used to map the demodulation reference signal DMRS.

[0208] In one possible implementation, the first information includes one or more of the following: an identifier of the first pseudo-random sequence, or parameters used to generate the first pseudo-random sequence.

[0209] In one possible implementation, there is a mapping relationship between the identifier of the first pseudo-random sequence and the first pseudo-random sequence, and the mapping relationship is predefined.

[0210] In one possible implementation, the first information includes indication information and / or time-frequency location information, the time-frequency location information being used to determine the second pseudo-random sequence, and the indication information being used to indicate that the second pseudo-random sequence is the same as the first pseudo-random sequence.

[0211] In one possible implementation, the first information is carried in the downlink control information.

[0212] In one possible implementation, the transceiver module 71 is further configured to send second information to a second communication device, the second information being used to indicate a channel estimation model.

[0213] In one possible implementation, the transceiver module 71 is further configured to transmit a first observation sequence and a first pseudo-random sequence to the server of the first communication device. The first observation sequence is obtained by transmitting the first pseudo-random sequence through the channel between the first communication device and the second communication device. The first pseudo-random sequence and the first observation sequence are used to train the channel estimation model. The processing module 72 is configured to obtain second information from the server of the first communication device.

[0214] The specific implementation methods of the transceiver module 71 and the processing module 72 can be found in the description of steps S401-S402 in the embodiment corresponding to Figure 4 above, or the description of steps S601-S609 in the embodiment corresponding to Figure 6, and will not be repeated here. In addition, the beneficial effects of using the same method will not be repeated here either.

[0215] In some feasible implementations, the communication device 1 may correspond to the second communication device mentioned above, or to a component (such as a circuit, chip, or chip system) configured in the second communication device.

[0216] In the specific implementation, the transceiver module 71 is used to receive first information from the first communication device. The first information is used to indicate a first demodulation reference signal pseudo-random sequence. The first pseudo-random sequence is used to train the channel estimation model. The processing module 72 is used to obtain a second pseudo-random sequence. The channel estimation model is used to predict the channel between the first communication device and the second communication device. The channel is predicted based on the first pseudo-random sequence and the second pseudo-random sequence.

[0217] In one possible implementation, the second pseudo-random sequence is the inference sequence of the channel estimation model.

[0218] In one possible implementation, the first pseudo-random sequence and the second pseudo-random sequence are sequences used to map the demodulation reference signal DMRS.

[0219] In one possible implementation, the transceiver module 71 is further configured to receive a second observation sequence, which is obtained by transmitting a second pseudo-random sequence through a channel between the first communication device and the second communication device; the channel is predicted based on the first pseudo-random sequence and the second pseudo-random sequence, including: the channel is predicted based on the first pseudo-random sequence, the second pseudo-random sequence and the second observation sequence.

[0220] In one possible implementation, the first information includes one or more of the following: an identifier of the first pseudo-random sequence, or parameters used to generate the first pseudo-random sequence.

[0221] In one possible implementation, there is a mapping relationship between the identifier of the first pseudo-random sequence and the first pseudo-random sequence, and the mapping relationship is predefined.

[0222] In one possible implementation, the first information includes indication information and / or time-frequency location information, the time-frequency location information being used to determine the second pseudo-random sequence, and the indication information being used to indicate that the second pseudo-random sequence is the same as the first pseudo-random sequence.

[0223] In one possible implementation, the first information is carried in the downlink control information.

[0224] In one possible implementation, the transceiver module 71 is also used to receive second information, which is used to indicate the channel estimation model.

[0225] In one possible implementation, the transceiver module 71 is further configured to transmit a first pseudo-random sequence, a second pseudo-random sequence, and a second observation sequence to the server of the second communication device, wherein the second observation sequence is obtained after the second pseudo-random sequence is transmitted through the channel between the first and second communication devices; the processing module 72 is further configured to acquire the characteristics of the channel from the server of the second communication device.

[0226] The specific implementation methods of the transceiver module 71 and the processing module 72 can be found in the description of steps S601-S609 in the embodiment corresponding to Figure 6 above, and will not be repeated here. Furthermore, the beneficial effects of using the same method will also not be repeated here.

[0227] Please refer to Figure 8, which is a schematic diagram of another communication device provided in an embodiment of this application. This communication device 2 can be used to implement the operations performed by the first or second communication device in the above embodiments, or it can be the first or second communication device mentioned above. The communication device 2 includes: a processor 81, a memory 82, and a bus system 83.

[0228] The memory 82 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM). The memory 82 is used to store related instructions and data. The memory 82 stores executable modules or data structures, or subsets thereof, or extended sets thereof:

[0229] Operation instructions: This includes various operation instructions used to perform various operations.

[0230] Operating system: includes various system programs used to implement various basic business functions and handle hardware-based tasks.

[0231] Figure 8 shows only one memory, but of course, multiple memories can be set as needed.

[0232] The communication device 2 may further include a transceiver 84. The transceiver 84 may be a communication module or a transceiver circuit. In the embodiments of this application, the transceiver 84 is used to perform the transmission and reception operations involved in the above embodiments.

[0233] Processor 81 can be a controller, central processor (CPU), general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Processor 81 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0234] In practical applications, the various components of communication device 2 are coupled together through bus system 83. Bus system 83 includes not only a data bus but may also include a power bus, control bus, and status signal bus. However, for clarity, all buses are labeled as bus system 83 in Figure 8. For ease of illustration, Figure 8 is only schematically shown.

[0235] In specific implementation, the communication device 2 can execute the steps of the method performed by the first communication device or the second communication device in the above embodiments. Specifically, when the communication device 2 is used to implement the various steps performed by the first communication device or the second communication device in the communication method provided in the embodiments, the processor 81 can implement the function of the processing module 72, and the transceiver 84 can implement the function of the transceiver module 71.

[0236] It should be noted that in practical applications, the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0237] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be ROM, programmable read-only memory (PROM), EPROM, electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be RAM, which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory described in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0238] This application also provides a chip, which includes at least a processor. The processor is used to execute computer execution instructions to cause a device on which the chip is mounted to perform the method steps performed by the first communication device or the second communication device in the above embodiments.

[0239] Optionally, the chip may also include interface circuitry. This interface circuitry is used to receive computer execution instructions and transmit them to the processor.

[0240] This application also provides a chip system including a processor for supporting the apparatus on which the chip system is mounted to implement the method steps performed by the first or second communication device in the above embodiments, such as generating or processing data and / or information involved in the above methods. In one possible design, the chip system further includes a memory for storing program instructions and data necessary for the data transmission device. The chip system may be composed of chips or may include chips and other discrete devices.

[0241] This application provides a communication system, which includes at least a first communication device and a second communication device. The first communication device and the second communication device work together to implement the communication method described in the preceding embodiments.

[0242] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer, implements the method steps performed by the first communication device or the second communication device in the above embodiments.

[0243] This application also provides a computer program product that, when executed by a computer, implements the method steps performed by the first communication device or the second communication device in the above embodiments.

[0244] In the above method embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0245] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0246] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The order of the process numbers described above does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0247] The above are merely preferred embodiments of the technical solutions of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A communication method characterized by comprising: Applied to a first communication device, the method includes: Send first information to the second communication device, the first information being used to indicate a first pseudo-random sequence, the first pseudo-random sequence being used to train a channel estimation model, the channel estimation model being used to predict the channel between the first communication device and the second communication device, the channel being predicted based on the first pseudo-random sequence and the second pseudo-random sequence; The second pseudo-random sequence is sent to the second communication device.

2. The method of claim 1, wherein, The second pseudo-random sequence is the inference sequence of the channel estimation model.

3. The method according to claim 1 or 2, characterized in that, The first pseudo-random sequence and the second pseudo-random sequence are sequences used to map the demodulation reference signal DMRS.

4. The method according to any one of claims 1 to 3, characterized in that, The first information includes one or more of the following: the identifier of the first pseudo-random sequence, or parameters used to generate the first pseudo-random sequence.

5. The method of claim 4, wherein, The identifier of the first pseudo-random sequence is mapped to the first pseudo-random sequence, and the mapping relationship is predefined.

6. The method according to any one of claims 1 to 3, characterized in that, The first information includes indication information and / or time-frequency location information, wherein the time-frequency location information is used to determine the second pseudo-random sequence, and the indication information is used to indicate that the second pseudo-random sequence is the same as the first pseudo-random sequence.

7. The method according to any one of claims 1 to 6, characterized in that, The first information is carried in the downlink control information.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Send a second message to the second communication device, the second message being used to instruct the channel estimation model.

9. The method of claim 8, wherein, The method further includes: The first observation sequence and the first pseudo-random sequence are transmitted to the server of the first communication device. The first observation sequence is obtained by transmitting the first pseudo-random sequence through the channel between the first communication device and the second communication device. The first pseudo-random sequence and the first observation sequence are used to train the channel estimation model. Obtain the second information from the server of the first communication device.

10. A communication method characterized by comprising: Applied to a second communication device, the method includes: Receive first information from a first communication device, the first information being used to indicate a first demodulation reference signal pseudo-random sequence, the first pseudo-random sequence being used to train a channel estimation model; A second pseudo-random sequence is obtained, and the channel estimation model is used to predict the channel between the first communication device and the second communication device. The channel is predicted based on the first pseudo-random sequence and the second pseudo-random sequence.

11. The method of claim 10, wherein, The second pseudo-random sequence is the inference sequence of the channel estimation model.

12. The method according to claim 10 or 11, characterized in that, The first pseudo-random sequence and the second pseudo-random sequence are sequences used to transmit the demodulation reference signal DMRS.

13. The method according to any one of claims 10-12, characterized in that, The method further includes: Receive a second observation sequence, which is obtained by transmitting the second pseudo-random sequence through the channel between the first communication device and the second communication device; The channel is predicted based on the first pseudo-random sequence and the second pseudo-random sequence, including: The channel is predicted based on the first pseudo-random sequence, the second pseudo-random sequence, and the second observation sequence.

14. The method according to any one of claims 10 to 13, characterized in that, The first information includes one or more of the following: the identifier of the first pseudo-random sequence, or parameters used to generate the first pseudo-random sequence.

15. The method of claim 14, wherein, The identifier of the first pseudo-random sequence is mapped to the first pseudo-random sequence, and the mapping relationship is predefined.

16. The method according to any one of claims 10-13, characterized in that, The first information includes indication information and / or time-frequency location information, wherein the time-frequency location information is used to determine the second pseudo-random sequence, and the indication information is used to indicate that the second pseudo-random sequence is the same as the first pseudo-random sequence.

17. The method according to any one of claims 10-16, characterized in that, The first information is carried in the downlink control information.

18. The method according to any one of claims 10-17, characterized in that, The method further includes: Receive second information, which is used to instruct the channel estimation model.

19. The method according to any one of claims 10-18, characterized in that, The method further includes: The server of the second communication device transmits a first pseudo-random sequence, a second pseudo-random sequence, and a second observation sequence, wherein the second observation sequence is obtained by transmitting the second pseudo-random sequence through the channel between the first communication device and the second communication device. The characteristics of the channel are obtained from the server of the second communication device.

20. A communications device, characterized by The device includes a processor and a transceiver, the transceiver being used to send and receive information, and the processor being used to cause the communication device to implement the method as described in any one of claims 1 to 9, or to implement the method as described in any one of claims 10 to 19.

21. A communications device, characterized by Includes a processor, the processor being configured to cause the communication device to implement the method as described in any one of claims 1 to 9, or to implement the method as described in any one of claims 10 to 19.

22. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when executed by a processor, causes a communication device including the processor to implement the method as described in any one of claims 1 to 9, or to implement the method as described in any one of claims 10 to 19.

23. A computer program product, characterised in that, The computer program product includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 9, or to perform the method as described in any one of claims 10 to 19.

Images