Communication method and related apparatus

Abstract

The present application provides a communication method and a related apparatus. The method comprises: a first device sending first information, the first information being used for indicating a first reference signal pattern, and the first reference signal pattern being determined on the basis of a first model; and sending a first reference signal on the basis of the first reference signal pattern, the first reference signal and a second model being used for channel reconstruction, wherein there is a correspondence between a first processing order used by the first model in multiple dimensions and a second processing order used by the second model in the multiple dimensions, and the multiple dimensions comprise at least two of a time domain, a frequency domain, and a spatial domain. The method can improve the performance of channel reconstruction and improve the accuracy of channel reconstruction.

Description

Communication methods and related devices

[0001] This application claims priority to Chinese Patent Application No. 202510074764.3, filed on January 16, 2025, entitled "Communication Method and Related Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to communication methods and related devices. Background Technology

[0003] Machine learning is an important branch of artificial intelligence and a technological means to achieve artificial intelligence. Among the many research directions in machine learning, neural networks have become a highly promising technique due to their ability to infinitely approximate any continuous function, granted by the universal approximation theorem. They can accurately abstract and model complex high-dimensional problems.

[0004] How to reconstruct channels using neural networks is a topic worthy of discussion in the industry. Summary of the Invention

[0005] This application provides a communication method and related apparatus for improving the accuracy of channel reconstruction.

[0006] 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.

[0007] In a first aspect, this application provides a communication method that can be executed by a first device, which may be a terminal or a chip, chip system, module, or control unit in the terminal; or, the first device may be a network device or a chip, chip system, module, or control unit in the network device, such as a server on the network side or a component (e.g., circuit, chip, or chip system) in the server, and this application does not limit the specific device.

[0008] It should be noted that, in this application, the term "terminal" can refer to either the terminal itself or the chip, functional module, or integrated circuit within the terminal that performs the methods provided in this application; no specific limitation is made in this application. For example, the chips in this application include, but are not limited to, modem chips, also known as baseband chips, or system-on-chip (SoC) chips or system-in-package (SIP) chips containing modem cores, which will not be elaborated further below.

[0009] It should be noted that, in this application, when referring to network equipment, it may refer to the network equipment itself, or to the chip, functional module, or integrated circuit in the network equipment that performs the method provided in this application, and this application does not make any specific limitation.

[0010] In this application, a first device is used to transmit a first reference signal, and a second device is used to receive the first reference signal. For example, if the first device is a network device, the second device can be a terminal; or, if the first device is a terminal, the second device can be a network device.

[0011] In the first aspect and its possible implementations, the method is described as being performed by a first device. The method includes: the first device sending first information, the first information indicating a first reference signal pattern, the first reference signal pattern being determined based on a first model; based on the first reference signal pattern, sending a first reference signal, the first reference signal and a second model being used for channel reconstruction; wherein a first processing order adopted by the first model in multiple dimensions and a second processing order adopted by the second model in multiple dimensions correspond to each other, the multiple dimensions including at least two of the time domain, frequency domain, and spatial domain.

[0012] In this application, reference signal pattern design and channel reconstruction are performed based on neural networks (i.e., the first model and the second model). In the process of reference signal pattern design and channel reconstruction, the first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in multiple dimensions are taken into consideration. This can realize the correspondence between the processing order of reference signal pattern design and channel reconstruction in multiple dimensions, improve the performance of channel reconstruction, and increase the accuracy of channel reconstruction.

[0013] For example, the use of a first reference signal and a second model for channel reconstruction can mean: the first reference signal and the second model are used by a second device to perform channel reconstruction; or, the first reference signal is used for channel estimation to obtain second channel information, and the second channel information and the second model are used for channel reconstruction; or, the first reference signal is used by the second device for channel estimation to obtain second channel information, and the second channel information is used as input to the second model for channel reconstruction to obtain first channel information; or, the second channel information is used as input to the second model, and the second model is used for channel reconstruction to obtain first channel information, wherein the first channel information is the channel information obtained by the second model for channel reconstruction.

[0014] For example, the first processing order adopted by the first model in multiple dimensions can refer to: the processing order adopted by the first model in designing reference signal patterns in multiple dimensions; or, the design order of the first model in designing reference signal patterns in multiple dimensions; or, the order adopted by the first model in determining the first reference signal pattern in multiple dimensions; or, the processing order adopted by the first device in determining the first reference signal pattern using the first model in multiple dimensions; or, the resource selection order in multiple dimensions in the process of the first model designing (or determining) the first reference signal pattern.

[0015] For example, the second processing order adopted by the second model in multiple dimensions can refer to: the processing order adopted by the second model in channel reconstruction in multiple dimensions; or, the reconstruction order of the second model in channel reconstruction in multiple dimensions; or, the processing order adopted by the second model in the process of channel reconstruction based on the first reference signal (or the aforementioned second channel information); the processing order adopted by the second device in the process of channel reconstruction based on the first reference signal (or the aforementioned second channel information); or, the resource selection order in multiple dimensions during the process of channel reconstruction (or determination of the first channel information) by the second model.

[0016] The first processing order can also be referred to as the reference signal pattern design order of the first model, and the second processing order can also be referred to as the channel reconstruction order of the second model. The first model is a neural network used to design the reference signal pattern; it can also be called a reference signal pattern design network or a reference signal pattern design model. The second model is a neural network used for channel reconstruction; it can also be called a channel reconstruction network or a channel reconstruction model. This application does not limit the specific neural network structure of the first and second models. For example, the first model can be deployed on a first device or other devices, and the second model can be deployed on a second device or other devices.

[0017] The first reference signal pattern is determined based on the first model, which may mean that: the first reference signal pattern corresponds to the first model, or the first reference signal pattern is designed (or generated) based on the first model; or the output of the first model includes the first reference signal pattern; or the output of the first model is used to obtain the first reference signal pattern, such as the output of the first model being the channel information of the first reference signal position.

[0018] For example, the first device determines a first reference signal pattern based on a first model, and then sends first information to the second device, the first information being used to indicate the first reference signal pattern; based on the first reference signal pattern, a first reference signal is sent; the second device receives the first reference signal based on the first reference signal pattern, and then performs channel reconstruction based on the first reference signal and the second model; wherein, the first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in multiple dimensions have a corresponding relationship, and the multiple dimensions include at least two of the time domain, frequency domain, and spatial domain.

[0019] In conjunction with the first aspect, in one possible implementation, the first model includes multiple first sub-models, the second model includes multiple second sub-models, the multiple first sub-models correspond one-to-one with multiple dimensions, and the multiple second sub-models correspond one-to-one with multiple dimensions; wherein, the first processing order is the running order of the multiple first sub-models, and the second processing order is the running order of the multiple second sub-models.

[0020] In this application, the first model can be a single neural network, or it can include multiple neural networks (i.e., the aforementioned multiple first sub-models). These multiple first sub-models can be trained separately, and this application does not impose any limitations on this. This method improves the flexibility of obtaining the first model.

[0021] For example, the multiple first sub-models include at least one of the following: a first sub-model corresponding to the time domain, a first sub-model corresponding to the frequency domain, and a first sub-model corresponding to the spatial domain. The first sub-model corresponding to the time domain is used to design a reference signal pattern in the time domain, the first sub-model corresponding to the frequency domain is used to design a reference signal pattern in the frequency domain, and the first sub-model corresponding to the spatial domain is used to design a reference signal pattern in the spatial domain.

[0022] Another example is that the multiple second sub-models include at least one of the following: a second sub-model corresponding to the time domain, a second sub-model corresponding to the frequency domain, and a second sub-model corresponding to the spatial domain, wherein the second sub-model corresponding to the time domain is used for channel reconstruction in the time domain, the second sub-model corresponding to the frequency domain is used for channel reconstruction in the frequency domain, and the second sub-model corresponding to the spatial domain is used for channel reconstruction in the spatial domain.

[0023] In conjunction with the first aspect, in one possible implementation, the reverse of the first processing order is the second processing order.

[0024] In this application, the first processing order and the second processing order may not be reversed, and this application does not impose any restrictions on this.

[0025] In conjunction with the first aspect, in one possible implementation, the multiple dimensions are a first dimension, a second dimension, and a third dimension, the first processing order is the first dimension, the second dimension, and the third dimension, and the second processing order is the third dimension, the second dimension, and the first dimension; or, the first processing order is the first dimension and the second dimension being processed simultaneously, and the third dimension being processed simultaneously, and the second processing order is the third dimension, the first dimension, and the second dimension being processed simultaneously; or, the first processing order is the first dimension, the second dimension, and the third dimension being processed simultaneously, and the second processing order is the second dimension and the third dimension being processed simultaneously, and the first dimension being processed simultaneously.

[0026] For example, the first dimension is the time domain, the second dimension is the frequency domain, and the third dimension is the spatial domain; or, the first dimension is the frequency domain, the second dimension is the time domain, and the third dimension is the spatial domain; or, the first dimension is the spatial domain, the second dimension is the time domain, and the third dimension is the frequency domain; or, the first dimension is the time domain, the second dimension is the spatial domain, and the third dimension is the frequency domain; or, the first dimension is the frequency domain, the second dimension is the spatial domain, and the third dimension is the time domain; or, the first dimension is the spatial domain, the second dimension is the frequency domain, and the third dimension is the time domain.

[0027] In conjunction with the first aspect, in one possible implementation, the method further includes: a first device receiving second information, the second information being used to indicate a first model, or the second information being used to indicate a second model, or the second information being used to indicate a first model group, the first model group including a first model and a second model.

[0028] In this embodiment, the first model can be determined by the second device, and the first device can determine the first model based on the instructions of the second device. This method can reduce the computational load on the first device side.

[0029] For example, the second information may be the model identifier of the first model, the model identifier of the second model, the model identifier of the first model group, the first processing order, or the second processing order.

[0030] In conjunction with the first aspect, in one possible implementation, before the first device receives the second information, the method further includes: the first device sending third information, wherein the third information is used to indicate multiple reference signal pattern design models, or, the third information is used to indicate multiple channel reconstruction models, or, the third information is used to indicate multiple model groups; wherein the multiple reference signal pattern design models include a first model, the multiple channel reconstruction models include a second model, and the multiple model groups include a first model group. In this embodiment, the first device sends multiple selections (i.e., the aforementioned third information) to the second device so that the second device can determine the first model from the multiple selections. This method can align the models of the first device and the second device, avoiding waste of communication and computing resources caused by the first device not supporting the first model determined by the second device.

[0031] Optionally, each of the multiple model groups may include a reference signal pattern design model and a channel reconstruction model.

[0032] Optionally, the above-mentioned multiple reference signal pattern design models and the above-mentioned multiple channel reconstruction models are in one-to-one correspondence, and / or, the above-mentioned multiple reference signal pattern design models and the above-mentioned multiple model groups are in one-to-one correspondence, and / or, the above-mentioned multiple channel reconstruction models and the above-mentioned multiple model groups are in one-to-one correspondence.

[0033] For example, each of the multiple model groups may include one of the reference signal pattern design models and one of the channel reconstruction models mentioned above.

[0034] Among them, the reference signal pattern design model in the first model group is the first model mentioned above, and the channel reconstruction model in the first model group is the second model mentioned above.

[0035] For example, the third information may be the model identifier corresponding to each model in multiple reference signal pattern design models, or the model identifier corresponding to each model in multiple channel reconstruction models, or the model identifier corresponding to each model group in multiple model groups, or the processing order corresponding to each model in multiple reference signal pattern design models, or the processing order corresponding to each model in multiple channel reconstruction models.

[0036] In conjunction with the first aspect, in one possible implementation, the method further includes: a first device receiving third information, the third information being used to indicate multiple reference signal pattern design models, or, the third information being used to indicate multiple channel reconstruction models, or, the third information being used to indicate multiple model groups, wherein the multiple reference signal pattern design models include a first model, the multiple channel reconstruction models include a second model, the multiple model groups include a first model group, and the first model group includes a first model and a second model; and determining the first model or the second model or the first model group based on the third information.

[0037] In this embodiment, a second device (or other device) sends multiple options (i.e., the aforementioned third information) to a first device, allowing the first device to determine a first model from among these options. This method can align the models of the first and second devices, avoiding waste of communication and computing resources caused by the second device not supporting the second model determined by the first device.

[0038] In conjunction with the first aspect, in one possible implementation, the method further includes: the first device sending fourth information, the fourth information being used to indicate a second model or the fourth information being a second model.

[0039] In this embodiment, if the second device stores the second model, the first device can indicate the fourth information to the second device (i.e., the fourth information is used to indicate the second model); if the second device does not store the second model, the second device can download the second model from the first device (i.e., the fourth information is the second model). This method can improve the flexibility of data transmission and reduce communication overhead.

[0040] For example, the fourth information is used to indicate the second model, such as the model identifier of the second model or the second processing order; or, the fourth information is the second model, such as the model data corresponding to the second model, such as model parameters or model structure.

[0041] In conjunction with the first aspect, in one possible implementation, the method further includes, prior to: a first device sending or receiving fifth information, the fifth information being used to indicate a reference signal pattern employing a neural network.

[0042] Optionally, the fifth information used to indicate a reference signal pattern employing a neural network may refer to: the fifth information used to indicate that the first device supports a reference signal pattern employing a neural network; or, the fifth information used to indicate that the second device supports a reference signal pattern employing a neural network; or, the fifth information used to indicate that the first device supports a reference signal pattern employing a neural network for reference signal pattern design; or, the fifth information used to indicate that the second device supports a reference signal pattern employing a neural network for channel reconstruction.

[0043] Optionally, if the fifth information is used to indicate that the first device supports a reference signal pattern using a neural network, or if the fifth information is used to indicate that the first device supports designing a reference signal pattern using a neural network, then the fifth information can also be referred to as the capability of the first device. If the first device is a terminal, then the fifth information can also be referred to as the capability of the terminal. If the fifth information is used to indicate that the second device supports a reference signal pattern using a neural network, or if the fifth information is used to indicate that the second device supports channel reconstruction using a reference signal pattern using a neural network, then the fifth information can also be referred to as the capability of the second device. This application does not limit the name of the fifth information.

[0044] In this embodiment of the application, the fifth information can avoid the waste of communication resources caused by the first device still sending the first information and the first reference signal to the second device when the second device does not support the reference signal pattern corresponding to the neural network.

[0045] In conjunction with the first aspect, in one possible implementation, the first reference signal is a demodulation reference signal (DMRS), a channel state information reference signal (CSI-RS), or a sounding reference signal (SRS).

[0046] Optionally, the first reference signal image can be a downlink reference signal. This method provides a procedural specification for designing downlink reference signal patterns and channel reconstruction based on a dual-end network (i.e., the first and second models mentioned above) for downlink reference signal scenarios.

[0047] Optionally, the first reference signal image can be an uplink reference signal. This method provides a procedural specification for designing uplink reference signal patterns and channel reconstruction based on a dual-end network (i.e., the first and second models mentioned above) for uplink reference signal scenarios.

[0048] In conjunction with the first aspect, in one possible implementation, the first model is trained based on the first channel reconstruction method, wherein the second model uses the first channel reconstruction method. For example, the first model is obtained by training the neural network multiple times based on the first channel reconstruction method, and the first reference signal pattern is generated by the first model.

[0049] Secondly, this application provides a communication method that can be executed by a second device, which may be a terminal or a chip, chip system, module, or control unit in the terminal; or, the second device may be a network device or a chip, chip system, module, or control unit in the network device, such as a server on the network side or a component (e.g., circuit, chip, or chip system) in the server, and this application does not limit the specific device.

[0050] In the second aspect and its possible implementations, the method is described as being performed by a second device. The method includes: the second device receiving first information, the first information indicating a first reference signal pattern, the first reference signal pattern being determined based on a first model; receiving a first reference signal based on the first reference signal pattern; and obtaining first channel information based on the first reference signal and a second model, wherein a first processing order adopted by the first model in multiple dimensions and a second processing order adopted by the second model in multiple dimensions correspond to each other, the multiple dimensions including at least two of the time domain, frequency domain, and spatial domain.

[0051] In conjunction with the second aspect, in one possible implementation, the first model includes multiple first sub-models, the second model includes multiple second sub-models, the multiple first sub-models correspond one-to-one with multiple dimensions, and the multiple second sub-models correspond one-to-one with multiple dimensions; wherein, the first processing order is the running order of the multiple first sub-models, and the second processing order is the running order of the multiple second sub-models.

[0052] In conjunction with the second aspect, in one possible implementation, the reverse of the first processing order is the second processing order.

[0053] In conjunction with the second aspect, in one possible implementation, the multiple dimensions are a first dimension, a second dimension, and a third dimension, the first processing order is the first dimension, the second dimension, and the third dimension, and the second processing order is the third dimension, the second dimension, and the first dimension; or, the first processing order is the first dimension and the second dimension being processed simultaneously, and the third dimension being processed simultaneously, and the second processing order is the third dimension, the first dimension, and the second dimension being processed simultaneously; or, the first processing order is the first dimension, the second dimension, and the third dimension being processed simultaneously, and the second processing order is the second dimension and the third dimension being processed simultaneously, and the first dimension being processed simultaneously.

[0054] In conjunction with the second aspect, in one possible implementation, the method further includes: a second device sending second information, the second information being used to indicate a first model, or the second information being used to indicate a second model, or the second information being used to indicate a first model group, the first model group including a first model and a second model.

[0055] In conjunction with the second aspect, in one possible implementation, before sending the second information, the method further includes: the second device receiving third information, the third information being used to indicate multiple reference signal pattern design models, or, the third information being used to indicate multiple channel reconstruction models, or, the third information being used to indicate multiple model groups; wherein the multiple reference signal pattern design models include a first model, the multiple channel reconstruction models include a second model, and the multiple model groups include a first model group.

[0056] In conjunction with the second aspect, in one possible implementation, the method further includes: the second device determining the second information based on at least one of data requirements, communication quality requirements, or channel environment characteristics, and the third information.

[0057] In this embodiment of the application, a reference signal pattern design model (i.e., the first model) and / or a channel reconstruction model (i.e., the second model) are determined based on at least one of data requirements, communication quality requirements, or channel environment characteristics. This method can improve the accuracy of channel reconstruction.

[0058] In conjunction with the second aspect, in one possible implementation, the method further includes: a second device sending third information, the third information being used to indicate a plurality of reference signal pattern design models, or, the third information being used to indicate a plurality of channel reconstruction models, or, the third information being used to indicate a plurality of model groups, wherein the plurality of reference signal pattern design models include a first model, the plurality of channel reconstruction models include a second model, the plurality of model groups include a first model group, and the first model group includes a first model and a second model.

[0059] In conjunction with the second aspect, in one possible implementation, the method further includes: the second device receiving fourth information, the fourth information being used to indicate a second model or the fourth information being a second model.

[0060] In conjunction with the second aspect, in one possible implementation, the method further includes, prior to: a second device sending or receiving fifth information, the fifth information being used to indicate a reference signal pattern employing a neural network.

[0061] Optionally, the second device may change the channel reconstruction model (i.e., the second model mentioned above) when the channel reconstruction accuracy changes, etc., and this application does not limit this.

[0062] Thirdly, this application provides a communication device, which may be a first device or a chip / circuit therein. The communication device is used to perform the methods of the first aspect or any possible implementation thereof. The communication device includes units having the ability to perform the methods of the first aspect or any possible implementation thereof.

[0063] Fourthly, this application provides a communication device, which may be a second device or a chip / circuit therein. The communication device is used to perform the methods in any possible implementation of the second aspect, the third aspect, or any of the aspects. The communication device includes units having the ability to perform the methods in any possible implementation of the second aspect, the third aspect, or any of the aspects.

[0064] In the third or fourth 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 to fourth aspects can be referred to the relevant descriptions of the first to third aspects above, and will not be repeated here.

[0065] Fifthly, this application provides a communication device, which includes a processor for executing the method described in any possible implementation of the first aspect, the second aspect, the third aspect, or any of the above aspects.

[0066] In a sixth aspect, this application provides a communication device including a processor coupled to a memory storing instructions that, when executed by the processor, cause the communication device to perform the method described in any possible implementation of the first aspect, the second aspect, the third aspect, or any of the above aspects.

[0067] In one possible implementation, the communication device further includes a memory. Optionally, the processor and memory are integrated (i.e., the memory is built-in memory). Optionally, the memory and processor are independently configured (i.e., the memory is external memory).

[0068] In a seventh aspect, this application provides a communication device that may include a processor and an interface circuit connected together. The interface circuit is used for exchanging (or sending / receiving or inputting / outputting) information or data, and the processor is used to execute program instructions that cause the communication device to perform the methods described in any possible implementation of the first aspect, the second aspect, the third aspect, or any of these aspects. The interface circuit may be a communication interface or a transceiver. The transceiver may be a radio frequency module in the communication device, or a combination of a radio frequency module and an antenna, or an input / output interface of a chip or circuit.

[0069] Eighthly, this application provides a readable storage medium storing program instructions that, when run on a computer, cause the computer to perform the method described in any possible implementation of the first aspect, the second aspect, the third aspect, or any of the aspects described above.

[0070] Ninthly, this application provides a program product containing program instructions that, when executed, cause the method described in any possible implementation of the first aspect, the second aspect, the third aspect, or any of the aspects to be performed.

[0071] Tenthly, this application provides an apparatus, which can be implemented as a chip or as a device, including a processor. The processor is used to read and execute a program stored in a memory to execute one or more of the first, second, or third aspects described above, or one or more of any possible implementations of any of these aspects, providing an information interaction method. Optionally, the apparatus further includes a memory connected to the processor via a circuit. Further optionally, the apparatus includes a communication interface connected to the processor. The communication interface is used to receive information to be processed, the processor obtains the information from the communication interface, processes the information, and outputs the processing result through the communication interface. The communication interface can be an input / output interface.

[0072] In one possible implementation, the processor and memory can be physically independent units, or the memory can be integrated with the processor.

[0073] Eleventhly, this application provides a communication system, which includes a first device and a second device; wherein the first device is used to perform the method described in the first aspect or any possible implementation of the first aspect, and the second device is used to perform the method described in the second aspect or the third aspect or any possible implementation thereof.

[0074] 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

[0075] Figure 1A is a schematic diagram of a communication system provided in an embodiment of this application;

[0076] Figure 1B is a schematic diagram of an open RAN (O-RAN or ORAN) system provided in an embodiment of this application;

[0077] Figure 1C is a schematic diagram of the structure of an access network device provided in an embodiment of this application;

[0078] Figure 1D is a schematic diagram of the communication device provided in an embodiment of this application;

[0079] Figure 2 is a schematic diagram of a feedforward neural network provided in an embodiment of this application;

[0080] Figure 3A is a flowchart illustrating a communication method provided in an embodiment of this application;

[0081] Figure 3B illustrates an exemplary flowchart of the process for obtaining first channel information;

[0082] Figure 4 is a flowchart illustrating another communication method provided in an embodiment of this application;

[0083] Figure 5 is a flowchart illustrating another communication method provided in an embodiment of this application;

[0084] Figure 6 is a flowchart illustrating another communication method provided in an embodiment of this application;

[0085] Figure 7 is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0086] Figure 8 is a schematic diagram of another communication device provided in an embodiment of this application;

[0087] Figure 9 is a schematic diagram of another communication device provided in an embodiment of this application;

[0088] Figure 10 is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0089] Figure 11 is a schematic diagram of the structure of a network device provided in an embodiment of this application. Detailed Implementation

[0090] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0091] References to "one embodiment" or "some embodiments" as described in this application mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0092] In the description of this application, 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. Furthermore, "at least one" means one or more, and "multiple" means two or more. "At least one 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.

[0093] It is understood that in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information to indicate A, it can be understood that the instruction information carries A, directly indicates A, or indirectly indicates A.

[0094] Furthermore, in this application, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as an "example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present concepts in a concrete manner. In this application, "of," "corresponding, relevant," and "corresponding" are sometimes used interchangeably, and it should be noted that their intended meanings are consistent unless their distinction is emphasized.

[0095] The technical solutions of this application can be applied to various communication systems. For example, 5th generation (5G) systems, new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, universal mobile telecommunication system (UMTS), mobile communication systems after 5G networks (e.g., future mobile communication systems), vehicle-to-everything (V2X) communication systems, device-to-device (D2D) communication systems, Internet of Things (IoT) communication systems, industrial internet communication systems, or satellite communication systems, etc. The wireless communication systems involved in this application also include, but are not limited to, narrowband Internet of Things (NB-IoT) systems.

[0096] Please refer to Figure 1A, which is a schematic diagram of the architecture of the communication system applied in the embodiments of this application. It should be noted that Figure 1A is a possible, non-limiting system schematic diagram. As shown in Figure 1A, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system 10 may also include the Internet 300. RAN 100 includes at least one RAN node (110a and 110b in Figure 1A, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1A, collectively referred to as 120). RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1A). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is connected to core network 200 wirelessly or via a wired connection. The core network elements in core network 200 and RAN nodes 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions, or a single physical device integrating some core network element functions and some RAN node 110 functions. Terminals can be interconnected with each other, and RAN nodes 110 can be interconnected with each other via wired or wireless means. Figure 1A is only a schematic diagram; this communication system may also include other network devices, such as wireless relay devices and wireless backhaul devices. Each device may also include different functional units, which are not shown in Figure 1A.

[0097] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems. RAN 100 can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0098] RAN node 110, sometimes also referred to as radio access network equipment, access network device, network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, in Figure 1A, network element 120i can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station (BS); but for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, in Figure 1A, network elements 110a and 110b can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0099] In one possible scenario, RAN node 110 can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a WiFi system. RAN node 110 can be a macro base station (as shown in Figure 1A, 110a), a micro base station or indoor station (as shown in Figure 1A, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, RAN node 110 can also be a server, a wearable device, a vehicle, or in-vehicle equipment. For example, the access network device in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of RAN node 110 in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). In this application, RAN node 110 can also be a logical node, logical module, or software that can implement all or part of the functions of RAN node 110.

[0100] In another possible scenario, multiple RAN nodes 110 collaborate to assist the terminal in achieving wireless access, with each RAN node 110 implementing a portion of the base station's functions. For example, a RAN node 110 can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0101] 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. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. 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 and hardware modules.

[0102] In this application, the aforementioned RAN node 110 may also be referred to as a network device.

[0103] In this application, the first device can be the RAN node 110 mentioned above, and the second device can be the terminal 120 mentioned above; or, the second device can be the RAN node 110 mentioned above, and the first device can be the terminal 120 mentioned above.

[0104] For example, the first device is a network device, the second device is a terminal, and the first reference signal is a downlink reference signal.

[0105] In another example, the first device is a terminal, the second device is a network device, and the first reference signal is an uplink reference signal.

[0106] The following section introduces network devices and terminals.

[0107] The terminal can be a wireless terminal capable of receiving network device scheduling information and instruction information. The terminal can be a device that provides voice and / or data connectivity to the user, a handheld device with wireless connectivity, or other processing device connected to a wireless modem.

[0108] A terminal, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), customer premises equipment (CPE), etc., is a device that includes wireless communication capabilities (providing voice / data connectivity to users). A terminal can be a transportation vehicle or communication module with wireless communication capabilities. For example, it can be a handheld device with wireless connectivity or an in-vehicle device. Currently, examples of such terminals include: mobile phones, smart devices, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, robots, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in vehicle-to-everything (V2X) communication, wireless terminals in self-driving cars, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, and wireless terminals in smart homes. For example, wireless terminals in self-driving cars can be drones, helicopters, or airplanes. For example, wireless terminals in V2X communication can be in-vehicle equipment, vehicle equipment, in-vehicle modules, vehicles, or ships. Wireless terminals in industrial control can be cameras, robots, or robotic arms. Wireless terminals in smart homes can be televisions, air conditioners, robot vacuums, speakers, or set-top boxes.

[0109] It should be noted that the terminal can be a device or apparatus with a chip, or a device or apparatus with integrated circuitry, or a chip, chip system, module, or control unit in the device or apparatus shown above; the specific application is not limited to any particular type. It should also be noted that in this application, the term "terminal" can refer to the terminal itself, or to the chip, functional module, or integrated circuit within the terminal that performs the method provided in this application; the specific application is not limited to any particular type.

[0110] Optionally, in a device-to-device (D2D) scenario, the network device can also be a terminal that has the network device functions described in this application.

[0111] A network device is a device deployed in a radio access network to provide wireless communication functions for terminals. Network devices may also be referred to as radio access network (RAN) entities, access nodes, network nodes, access network equipment, or communication devices, etc.

[0112] Specifically, the network equipment can be access network equipment for cellular systems related to the 3rd Generation Partnership Project (3GPP). For example, fourth-generation (4G) mobile communication systems, 5G mobile communication systems, or future mobile communication systems. The network equipment can also be access network equipment in open RAN (O-RAN or ORAN) or cloud radio access network (CRAN). Alternatively, the network equipment can also be access network equipment in a communication system resulting from the integration of two or more of the above communication systems.

[0113] Network equipment includes, but is not limited to: evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved NodeB, or home Node B, HNB), baseband unit (BBU), access point (AP) in wireless fidelity (WIFI) systems, macro base station, micro base station, wireless relay node, donor node, radio controller in CRAN scenarios, wireless backhaul node, transmission point (TP), or transmission and reception point (TRP). Network equipment can also be access network equipment in 5G mobile communication systems. For example, next-generation Node B (gNB), TRP, TP in new radio (NR) systems, or one or more antenna panels (including multiple antenna panels) of a base station in a 5G mobile communication system. Alternatively, network devices can also be network nodes constituting a gNB or transmission point. Examples include centralized units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs). CUs and DUs can be separate entities or included in the same network element, such as a BBU. RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). Alternatively, network devices can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in V2X technology, network devices can be roadside units (RSUs).

[0114] It should be noted that CU (or CU-CP and CU-UP), DU, or RU may have different names in different systems, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called an open centralized unit (O-CU) or an open CU, DU can also be called an open distributed unit (O-DU), centralized unit control plane (CU-CP) can also be called an open centralized unit control plane (O-CU-CP) or an open CU-CP, centralized unit user plane (CU-UP) can also be called an open centralized unit user plane (O-CU-UP) or an open CU-UP, and RU can also be called an open radio unit (O-RU). This application does not impose any specific limitations. Any of the units CU, CU-CP, CU-UP, DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0115] Figure 1B is a schematic diagram of an open RAN (O-RAN or ORAN) system provided in an embodiment of this application. The ORAN system includes a core network, access network equipment, and UE. Optionally, the ORAN system may also include other components besides those shown in Figure 1B, which is not limited in this application.

[0116] This application can be applied to the system shown in Figure 1B. Therefore, the network device in this application can be the access network device in Figure 1B, such as the CU (CU-CP or CU-UP) or DU or RU mentioned above, and the terminal in this application can be the UE in Figure 1B.

[0117] Access network devices can communicate with the core network (CN) via a backhaul link. Access network devices can also communicate with the UE via an air interface. Specifically, the BBU in the access network device communicates with the core network via a backhaul link. The RU in the access network device communicates with at least one UE via an air interface. The BBU communicates with at least one RU via a fronthaul link; the BBU and RU may or may not be co-located.

[0118] A BBU includes at least one CU and at least one DU, and the CU and DU can communicate with each other via at least one midhaul link.

[0119] In one possible implementation, as shown in Figure 1C, the CU is a logical node carrying the radio resource control (RRC), service data adaptation protocol (SDAP) layer, packet data convergence protocol (PDCP) layer, and other control functions of the access network equipment. The CU can connect to network nodes such as the core network through interfaces, such as the E2 interface. Optionally, the CU can have some core network functions. The CU (e.g., the PDCP layer and / or higher) connects to the DU (e.g., the radio link control (RLC) layer and lower layers of the DU) through interfaces, such as the F1 interface. Optionally, the F1 interface can provide control plane (C-Plane) and user plane (U-Plane) functions (e.g., interface management, system information management, UE context management, RRC message transmission, etc.). F1AP is the application protocol of the F1 interface, defining the signaling procedures of F1 in some examples. The F1 interface supports control plane F1-C and user plane F1-U.

[0120] Optionally, as shown in Figure 1C, the CU can be split into CU-CP and CU-UP. CU-CP is a logical node carrying the control plane (PDCP-C) layer, which carries the RRC layer and the Packet Data Convergence Protocol layer, and is used to implement the CU's control plane functions. CU-CP can interact with network elements in the core network used to implement control plane functions. These network elements in the core network can be access and mobility function (AMF) network elements, such as the access and mobility management (AMF) function in a 5G system. The AMF network element is responsible for mobility management in the mobile network, such as terminal location updates, terminal registration with the network, and terminal handover. CU-UP is a logical node carrying the user plane (PDCP-U) layer, which carries the SDAP layer and the Packet Data Convergence Protocol layer, and is used to implement the CU's user plane functions. CU-UP can interact with network elements in the core network used to implement user plane functions. In the core network, network elements used to implement user plane functions, such as the user plane function (UPF) in a 5G system, are responsible for forwarding and receiving data in terminals. The above configuration of CU and DU is merely an example; in practical applications, the functions of CU and DU can be configured as needed. For example, CU or DU can be configured to have more protocol layer functions, or to have only some protocol layer processing functions. For instance, some functions of the RLC layer and protocol layer functions above the RLC layer can be placed in the CU, while the remaining functions of the RLC layer and protocol layer functions below the RLC layer can be placed in the DU. Furthermore, the functions of CU or DU can be divided according to service type or other system requirements, such as by latency, placing functions that need to meet low latency requirements in the DU and functions that do not need to meet such latency requirements in the CU.

[0121] In one possible implementation, as shown in Figure 1C, the DU is a logical node carrying the RLC layer, medium access control (MAC) layer, higher physical layer (Higher PHY) layer, and other functions. In some examples, the DU can control at least one RU. The DU connects to the RU through interfaces, which can be fronthaul interfaces. In some examples, the Higher PHY layer includes the PHY layer processing, such as forward error correction (FEC) encoding and decoding, scrambling, modulation, and demodulation.

[0122] In one possible implementation, as shown in Figure 1C, the RU is a logical node carrying both lower physical layer (PHY) and radio frequency (RF) processing. In some examples, the RU may be a 3GPP TRP, a remote radio head (RRH), or other similar entity. In some examples, the Low-PHY includes PHY processing functions such as fast fourier transform (FFT), inverse fast fourier transform (IFFT), digital beamforming, and filtering. The RU communicates with one or more UEs via a radio link.

[0123] The DU and RU can be co-located or not. The DU and RU exchange control plane and user plane information via a fronthaul link through a lower-layer split CUS-Plane (LLS-CUS) interface. LLS-CUS may include a lower-layer split control (LLS-C) interface and a lower-layer split user (LLS-U) interface, providing the control plane (C-Plane) and user plane (U-Plane) respectively. In some examples, the control plane (C-Plane) refers to real-time control between the DU and RU. The DU and RU exchange management information via an LLS-M interface on the fronthaul link; the management plane (M-Plane) refers to non-real-time management operations between the DU and RU.

[0124] DU and RU can cooperate to implement the functions of the PHY layer. A DU can be connected to one or more RUs. The functions of DU and RU can be configured in various ways depending on the design. For example, a DU can be configured to implement baseband functions, and an RU can be configured to implement mid-RF functions. Another example is that a DU can be configured to implement higher-level functions in the PHY layer, and an RU can be configured to implement lower-level functions in the PHY layer, or to implement both lower-level and RF functions. Higher-level functions in the physical layer can include a portion of the physical layer's functions that are closer to the MAC layer, while lower-level functions in the physical layer can include another portion of the physical layer's functions that are closer to the mid-RF side.

[0125] 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. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples.

[0126] For example, as shown in Figure 1D, network devices (such as base stations) and terminals (such as UEs) may include an RRC signaling interaction module, a MAC signaling interaction module, and a PHY interaction module. The RRC signaling interaction module is used to send and receive RRC signaling, the MAC signaling interaction module is used to send and receive MAC-CE (medium access control element) signaling, and the PHY interaction module is used to send and receive uplink / downlink control signaling and uplink / downlink data, such as transmitting physical downlink control channel (PDCCH), physical downlink shared channel (PDSCH), physical uplink control channel (PUCCH), and physical uplink shared channel (PUSCH).

[0127] It should be noted that network devices can be devices or apparatuses with chips, or devices or apparatuses with integrated circuits, or chips, chip systems, modules, or control units in the devices or apparatuses shown above; this application does not impose any specific limitations. It should also be noted that in this application, the term "network device" can refer to the network device itself, or to chips, functional modules, or integrated circuits within the network device that implement the methods provided in this application; this application does not impose any specific limitations.

[0128] First, let me introduce some of the technical terms used in this application.

[0129] 1. Artificial intelligence (AI)

[0130] (1) AI can enable machines to possess human-like intelligence, for example, allowing machines to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be used. In machine learning, machines learn (or train) a model using training data. This model represents the mapping between input and output. 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 (or prediction result).

[0131] (2) A neural network (NN) is a specific model in machine learning. According to the general approximation theorem, a neural network can theoretically approximate any continuous function, thus enabling it to learn arbitrary mappings. Traditional communication systems require extensive expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0132] Neural networks are, for example, deep neural networks (DNNs). For instance, DNNs can include feedforward neural networks (FNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and fully connected neural networks.

[0133] DNNs are typically multi-layered structures. Increasing the depth and width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. DNNs can include feedforward neural networks and feedback neural networks, among others.

[0134] Figure 2 illustrates a schematic diagram of a feedforward neural network. Figure 2 shows three neural network layers: an input layer, hidden layers, and an output layer. The input layer is used to input the information to be processed; a DNN typically contains more than one hidden layer, which extracts information features to varying degrees; the output layer maps the extracted feature information to the desired output information. Circular symbols represent neurons in each layer. The connection method and activation function used for each neuron determine the neural network's expression function.

[0135] In this application, the first model is based on a neural network, such as a DNN, specifically an RNN, a CNN, or others, and this application does not limit it.

[0136] In this application, the second model is based on a neural network, such as a DNN, specifically an RNN, a CNN, or others; this application does not limit this. In this application, the neural structures of the first and second models can be the same or different; this application does not limit this.

[0137] In this application, the model (such as the first model and the second model) may also be referred to as 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 may 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 dissemination, etc. AI functions may also be referred to as AI (related) operations or AI-related functions.

[0138] The communication system provided in this application (such as the system in Figure 1A above) can incorporate AI network elements to implement some or all AI-related operations (such as training a first model and / or a second model). AI network elements can also be referred to as AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. These AI network elements can be built into the network elements of the communication system. For example, an AI network element can be an AI module built into: access network equipment, core network equipment, cloud server, or operation, administration and maintenance (OAM) management system, used to implement AI-related functions. The aforementioned OAM can be the management system of the core network equipment and / or the management system of the access network equipment. Alternatively, the aforementioned AI network element can also be a network element independently set up in the communication system. Optionally, the terminal or the chip built into the terminal can also include an AI entity to implement AI-related functions.

[0139] 2. Reference signal (RS)

[0140] RS can also be referred to as a pilot, reference sequence, etc. In the embodiments of this application, the reference signal can be a reference signal used for channel measurement. For example, the reference signal can be a CSI-RS used for downlink channel measurement or an SRS used for uplink channel measurement.

[0141] It should be understood that the reference signals listed above are merely examples and should not be construed as limiting this application in any way. This application does not preclude the possibility of defining other reference signals in future agreements to achieve the same or similar functions, nor does it preclude the possibility of defining other reference signals in future agreements to achieve different functions.

[0142] Currently, the scheme for channel reconstruction using neural networks is not mature and there is no complete design scheme.

[0143] In view of this, this application provides a communication method and related apparatus. In this method, a reference signal pattern is designed and a channel is reconstructed based on a neural network (i.e., a first model and a second model). In the process of designing the reference signal pattern and reconstructing the channel, the first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in multiple dimensions are taken into consideration. This can realize the correspondence between the processing order of the reference signal pattern design and the channel reconstruction in multiple dimensions, improve the performance of the channel reconstruction, and increase the accuracy of the channel reconstruction.

[0144] Optionally, the multiple dimensions include at least two of the time domain, frequency domain, and spatial domain. This method considers the resource selection order (as described in the first processing order) of the reference signal pattern design model (such as the first model above) in the time domain, frequency domain, and spatial domain, and the channel reconstruction order (as described in the second processing order) of the channel reconstruction model (such as the second model above) in the time domain, frequency domain, and spatial domain. Through the correspondence between the resource selection order and the channel reconstruction order, an appropriate resource selection order and channel reconstruction order can be selected to improve the performance and accuracy of channel reconstruction.

[0145] The technical solution of this application is described below with reference to specific embodiments. Figure 3A is a schematic flowchart of a communication method provided by an embodiment of this application.

[0146] Referring to Figure 3A, the method may include the following steps:

[0147] Step S301: The first device sends first information to the second device. The first information is used to indicate the first reference signal pattern. The first reference signal pattern is determined based on the first model.

[0148] Correspondingly, the second device receives the first information sent by the first device.

[0149] For example, the first information can be sent via downlink control information (DCI), or it can be sent via other methods, which are not limited in this application.

[0150] In some embodiments of this application, the first device may determine a first model, then determine a first reference signal pattern based on the first model, and then send the aforementioned first information to the second device.

[0151] The first reference signal pattern is determined based on the first model, which may mean that: the first reference signal pattern corresponds to the first model, or the first reference signal pattern is designed (or generated) based on the first model; or the output of the first model includes the first reference signal pattern; or the output of the first model is used to obtain the first reference signal pattern, such as the output of the first model being the channel information of the first reference signal position.

[0152] For example, the input of the reference signal pattern design model (or pilot pattern design network, such as the first model) in this application can be complete channel information, and its output can be local channel information (or the time-frequency spatial domain resources corresponding to the local channel information, i.e., the reference signal pattern), wherein the local channel information is used to obtain the reference signal pattern.

[0153] In this application, channel information refers to information that reflects channel characteristics and / or channel quality. As an example, channel information includes at least one of the following: channel state information (CSI), time-varying channel information, or channel frequency offset information, or information obtained based on channel state information (such as information obtained by multiplying CSI by a precoding matrix). That is to say, the input and output of the aforementioned neural network (such as the first model) can be the aforementioned channel information.

[0154] For example, CSI may include at least one of the following: precoding matrix indicator (PMI), channel quality indicator (CQI), rank indicator (RI), layer indicator (LI), reference signal received power (RSRP), CSI-RS resource indicator (CRI), synchronization signal / physical broadcast channel block resource indicator (SSBRI), etc. In this application, the first model may be obtained by training a first initial neural network multiple times; that is, the trained neural network is the first model, and the output of the first model is the first reference signal pattern, or the output of the first model is used to obtain the first reference signal pattern.

[0155] For example, the criteria for determining whether training is complete may be: the total number of iterations (i.e., the number of training iterations, or the number of epochs) reaches a first value; or the loss function value obtained based on the input and output reaches a first threshold; or other conditions, which are not limited in this application.

[0156] Optionally, the training of the first model can be performed by the first device or by other devices (such as a server), and this application does not limit this.

[0157] The following are two exemplary implementations of determining the first model.

[0158] In one implementation, the first device may receive second information (such as second information from a second device), and then determine a first model based on the second information. The second information may be used to indicate the first model, or to indicate a second model, or to indicate a first model group, the first model group including the first model and the second model.

[0159] For example, the second information may be the model identifier of the first model, the model identifier of the second model, the model identifier of the first model group, the first processing order, or the second processing order.

[0160] For example, if the second information indicates a second model that corresponds to the first model, then the first device can determine the first model based on the second information and this correspondence. For instance, this correspondence can be found in the second and third columns of Table 1, or in the columns containing the reference signal pattern design model and the channel reconstruction model in Table 2. Optionally, the first device can store the correspondence between the first and second models. For example, the first device can store part or all of the information in Table 1 or Table 2, such as storing the second and third columns of Table 1, or storing the columns containing the reference signal pattern design model and the channel reconstruction model in Table 2.

[0161] For example, if the second information indicates a first model group, and there is a correspondence between the first model group and the first model, then the first device can determine the first model based on the second information and this correspondence. For instance, this correspondence can be found in the first and second columns of Table 1, or in the column containing the model group identifier and reference signal pattern in Table 2. Optionally, the first device can store the correspondence between the first model group and the second model. For example, the first device can store part or all of the information in Table 1 or Table 2, such as storing the first and second columns of Table 1, or storing the column containing the model group identifier and reference signal pattern in Table 2.

[0162] For example, the first device can obtain the correspondence between multiple sets of model groups (such as Table 1 or Table 2); if the second information is used to indicate the second model or the first model group, the first device can determine the first model based on the correspondence between the multiple sets of model groups and the second information. It should be noted that this application exemplarily represents the correspondence between multiple sets of model groups through a table, but this application can also represent the above correspondence through text or other methods, and this application does not limit this.

[0163] Optionally, the first device may also store the correspondence between multiple model groups, such as Table 1 or Table 2.

[0164] Table 1 illustrates three model groups as examples.

[0165] Table 1

[0166] Assuming the second information mentioned above can be model group identifier 1, or model identifier 1-1, or model identifier 1-2, then the first device can determine the first model as the reference signal pattern design model with model identifier 1-1 based on Table 1.

[0167] Table 2 illustrates three model groups as examples.

[0168] Table 2

[0169] The numbers in the columns for spatial, temporal, and frequency domains in Table 2 are used to indicate the processing order of that dimension. For example, spatial domain is 1, temporal domain is 2, and frequency domain is 3. This indicates that the processing order of the model is: spatial domain, temporal domain, and frequency domain. That is, spatial domain processing is performed first, followed by temporal domain processing, and finally frequency domain processing.

[0170] For example, the second line means: Model group 1 includes Reference Signal Pattern Design Model 1 and Channel Reconstruction Model 1. Reference Signal Pattern Design Model 1 designs the reference signal pattern first in the spatial domain, then in the time domain, and finally in the frequency domain. Channel Reconstruction Model 1 performs channel reconstruction first in the spatial domain, then in the time domain, and finally in the frequency domain. Similarly, the third line means: Model group 2 includes Reference Signal Pattern Design Model 2 and Channel Reconstruction Model 2. Reference Signal Pattern Design Model 2 designs the reference signal pattern first in the spatial domain, then in the frequency domain, and finally in the time domain. Channel Reconstruction Model 2 performs channel reconstruction first in the time domain, then in the frequency domain, and finally in the spatial domain. For example, the meaning represented by the fourth line is: the model group identified by model group 3 includes reference signal pattern design model 3 and channel reconstruction model 3. The reference signal pattern design model 3 first performs reference signal pattern design in both the time domain and frequency domain, and then performs reference signal pattern design in the spatial domain. The channel reconstruction model 3 first performs channel reconstruction in the spatial domain, and then performs channel reconstruction in both the time domain and frequency domain.

[0171] For example, if the second information is used to indicate the first processing order, and the second information is 123, then the second information is used to indicate that the first model is the above-mentioned reference signal pattern design model 1; or, if the second information is used to indicate the second processing order, and the second information is 321, then the second information is used to indicate that the second model is the above-mentioned channel reconstruction model 1. The second model can be determined to be the above-mentioned reference signal pattern design model 1 based on the correspondence shown in Table 2.

[0172] Optionally, before receiving the second information, the first device may send third information to the second device. The third information may indicate multiple reference signal pattern design models, multiple channel reconstruction models, or multiple model groups, wherein the multiple reference signal pattern design models include a first model, the multiple channel reconstruction models include a second model, and the multiple model groups include a first model group. For example, the third information may be a model identifier, a channel reconstruction order, or a reference signal pattern design order.

[0173] For example, the first device broadcasts the aforementioned third information, and correspondingly, the second device receives the aforementioned third information; then, based on the third information, the second device determines a first model, a second model, or a group of first models, such as determining a first model from multiple reference signal pattern design models, or determining a second model from multiple channel reconstruction models, or determining a first model group from the aforementioned multiple model groups, or determining a first processing order (i.e., determining the first model) from the processing orders corresponding to multiple reference signal pattern design models, or determining a second processing order (i.e., determining the second model) from the processing orders corresponding to multiple reference signal pattern design models; then, the second device sends the aforementioned second information to the first device. Each reference signal pattern design model corresponds to a processing order, and each channel reconstruction model corresponds to a processing order, as exemplified in Table 2.

[0174] Optionally, the third information is used to indicate multiple reference signal pattern design models supported by the first device, or multiple channel reconstruction models corresponding to the multiple reference signal pattern design models supported by the first device, or multiple model groups corresponding to the multiple reference signal pattern design models supported by the first device. Wherein, the third information is used to indicate multiple reference signal pattern design models, or multiple channel reconstruction models, or multiple model groups, the multiple reference signal pattern design models include a first model, the multiple channel reconstruction models include a second model, and the multiple model groups include a first model group.

[0175] In another implementation, the first device can receive third information and then, based on the third information, determine the first model, the second model, or the first model group.

[0176] For example, the second device sends third information to the first device, and the first device receives the third information accordingly. Then, based on the third information, the first device determines a first model, a second model, or a group of first models. For instance, it determines a first model from multiple reference signal pattern design models, or a second model from multiple channel reconstruction models, or a group of first models from the aforementioned multiple model groups, or a first processing order (i.e., determining the first model) from the processing order corresponding to multiple reference signal pattern design models, or a second processing order (i.e., determining the second model) from the processing order corresponding to multiple reference signal pattern design models. Each reference signal pattern design model corresponds to a processing order, and each channel reconstruction model corresponds to a processing order; see Table 2 for examples.

[0177] For example, if the data requirement is to reduce computation or save energy, the first device can select a model or model group from the models indicated by the third information that only performs processing in the time and frequency domains. As another example, if the communication quality requirement is high, the first device can select a model or model group from the models indicated by the third information that performs processing in the time, frequency, and spatial domains. Furthermore, if the channel environment is characterized by relative stability in the frequency domain, the first device can select a model or model group from the models indicated by the third information that does not perform processing in the frequency domain.

[0178] It should be noted that the third information sent by the first device to the second device may be the same as or different from the third information sent by the second device to the first device. This application does not limit this. For example, the third information sent by the first device to the second device corresponds to the reference signal pattern design model supported by the first device, and the third information sent by the second device to the first device corresponds to the channel reconstruction model indicated by the second device.

[0179] Optionally, the third information is used to indicate multiple channel reconstruction models supported by the second device, or multiple reference signal pattern design models corresponding to the multiple channel reconstruction models supported by the second device, or multiple model groups corresponding to the multiple channel reconstruction models supported by the second device.

[0180] For example, the third information may be the model identifier corresponding to each model in multiple reference signal pattern design models, or the model identifier corresponding to each model in multiple channel reconstruction models, or the model identifier corresponding to each model group in multiple model groups, or the processing order corresponding to each model in multiple reference signal pattern design models, or the processing order corresponding to each model in multiple channel reconstruction models. For example, see Table 1 or Table 2.

[0181] This application does not limit the signaling that carries third information. For example, the third information may be carried in DCI, MAC-CE, or RRC.

[0182] Optionally, the first device may send fourth information to the second device, the fourth information being used to indicate the second model or the fourth information being the second model. For example, after determining the first model, the first device determines the second model based on the first model, and then sends the fourth information to the second device. Another example is that the first device sends the fourth information to the second device after determining the second model. Yet another example is that the first device sends the fourth information to the second device after determining the first model group.

[0183] For example, the fourth information is used to indicate the second model, such as the model identifier of the second model or the second processing order; or, the fourth information is the second model, such as the model data corresponding to the second model, such as model parameters or model structure.

[0184] This application does not limit the signaling carrying the fourth information. For example, the fourth information can be carried in DCI, MAC-CE, or RRC. For example, if the fourth information is a second model, it can also refer to: the second device downloading the second model from the first device. For example, see step S404 in the embodiment shown in FIG4.

[0185] Optionally, the first model can be a neural network, or the first model includes multiple first sub-models, each corresponding to a different dimension, wherein the first processing order is the running order of the multiple first sub-models.

[0186] Optionally, before performing step S301, the first device may send or receive fifth information, which is used to indicate a reference signal pattern employing a neural network.

[0187] Optionally, the fifth information used to indicate a reference signal pattern employing a neural network may refer to: the fifth information used to indicate that the first device supports a reference signal pattern employing a neural network; or, the fifth information used to indicate that the second device supports a reference signal pattern employing a neural network; or, the fifth information used to indicate that the first device supports a reference signal pattern employing a neural network for reference signal pattern design; or, the fifth information used to indicate that the second device supports a reference signal pattern employing a neural network for channel reconstruction.

[0188] Optionally, if the fifth information is used to indicate that the first device supports a reference signal pattern using a neural network, or if the fifth information is used to indicate that the first device supports designing a reference signal pattern using a neural network, then the fifth information can also be referred to as the capability of the first device. If the first device is a terminal, then the fifth information can also be referred to as the capability of the terminal. If the fifth information is used to indicate that the second device supports a reference signal pattern using a neural network, or if the fifth information is used to indicate that the second device supports channel reconstruction using a reference signal pattern using a neural network, then the fifth information can also be referred to as the capability of the second device. This application does not limit the name of the fifth information.

[0189] This application does not limit the signaling that carries the fifth information. For example, the fifth information can be carried in DCI, MAC-CE, or RRC.

[0190] Step S302: The first device sends a first reference signal to the second device based on the first reference signal pattern. The first reference signal and the second model are used for channel reconstruction. The first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in multiple dimensions have a corresponding relationship. The multiple dimensions include at least two of the time domain, frequency domain, and spatial domain.

[0191] Correspondingly, the second device receives the first reference signal sent by the first device based on the first reference signal pattern.

[0192] For example, the first reference signal is DMRS, CSI-RS, or SRS, but this application does not limit the first reference signal.

[0193] Optionally, if the first reference signal is a downlink DMRS, the first device can be a network device and the second device can be a terminal. For an example, see the relevant content in Figure 4. If the first reference signal is a CSI-RS, the first device can be a network device and the second device can be a terminal. For an example, see the relevant content in Figure 6.

[0194] Optionally, the second model can be a neural network, or the second model includes multiple second sub-models, each corresponding to a different dimension, and the second processing order is the running order of the multiple second sub-models.

[0195] In this application, the structure of the first model is not related to the structure of the second model, and this application does not limit this. For example, the first model is a neural network, and the second model can be a neural network or may include multiple second sub-models. As another example, the second model is a neural network, and the first model can be a neural network or may include multiple third sub-models.

[0196] Optionally, the reverse of the first processing order is the second processing order.

[0197] For example, multiple dimensions are a first dimension, a second dimension, and a third dimension. The first processing order is the first dimension, the second dimension, and the third dimension, and the second processing order is the third dimension, the second dimension, and the first dimension; or, the first processing order is the first dimension and the second dimension processed simultaneously, and the third dimension is processed simultaneously, and the second processing order is the third dimension, the first dimension, and the second dimension processed simultaneously; or, the first processing order is the first dimension, the second dimension, and the third dimension processed simultaneously, and the second processing order is the second dimension and the third dimension processed simultaneously, and the first dimension is processed simultaneously.

[0198] For example, the first dimension is the time domain, the second dimension is the frequency domain, and the third dimension is the spatial domain.

[0199] If the first processing order is time domain, frequency domain, and spatial domain, then the second processing order can be spatial domain, frequency domain, and time domain.

[0200] Alternatively, if the first processing order is: first time domain and frequency domain are processed simultaneously, then spatial domain is processed, then the second processing order is: first spatial domain, then time domain and frequency domain are processed simultaneously.

[0201] Alternatively, if the first processing order is: first time domain, then frequency domain and spatial domain simultaneously, then the second processing order is: first frequency domain and spatial domain simultaneously, then time domain.

[0202] For example, the first dimension is the frequency domain, the second dimension is the time domain, and the third dimension is the spatial domain.

[0203] If the first processing order is frequency domain, time domain, and spatial domain, then the second processing order can be spatial domain, time domain, and frequency domain.

[0204] Alternatively, if the first processing order is: first process the frequency domain and time domain simultaneously, then process the spatial domain, then the second processing order is: first process the spatial domain, then process the frequency domain and time domain simultaneously.

[0205] Alternatively, if the first processing order is: first the frequency domain, then the time and spatial domains are processed simultaneously, then the second processing order is: first the time and spatial domains are processed simultaneously, then the frequency domain.

[0206] For example, the first dimension is the spatial domain, the second dimension is the time domain, and the third dimension is the frequency domain.

[0207] If the first processing order is spatial domain, time domain, frequency domain, then the second processing order can be frequency domain, time domain, spatial domain;

[0208] Alternatively, if the first processing order is: perform spatial and temporal domain operations simultaneously, then frequency domain operations, then the second processing order is: perform frequency domain operations first, then perform spatial and temporal domain operations simultaneously.

[0209] Alternatively, if the first processing order is: spatial domain first, then time and frequency domains simultaneously, then the second processing order is: time and frequency domains simultaneously, then spatial domain.

[0210] For example, the first dimension is the time domain, the second dimension is the spatial domain, and the third dimension is the frequency domain.

[0211] If the first processing order is time domain, spatial domain, frequency domain, then the second processing order can be frequency domain, spatial domain, time domain;

[0212] Alternatively, if the first processing order is: first process the time domain and spatial domain simultaneously, then process the frequency domain, then the second processing order is: first process the frequency domain, then process the time domain and spatial domain simultaneously.

[0213] Alternatively, if the first processing order is: first time domain, then spatial and frequency domains simultaneously, then the second processing order is: first spatial and frequency domains simultaneously, then time domain.

[0214] For example, the first dimension is the frequency domain, the second dimension is the spatial domain, and the third dimension is the time domain.

[0215] If the first processing order is frequency domain, spatial domain, and time domain, then the second processing order can be time domain, spatial domain, and frequency domain.

[0216] Alternatively, if the first processing order is: first process the frequency domain and spatial domain simultaneously, then process the time domain, then the second processing order is: first process the time domain, then process the frequency domain and spatial domain simultaneously.

[0217] Alternatively, if the first processing order is: first frequency domain, then spatial and time domains simultaneously, then the second processing order is: first spatial and time domains simultaneously, then frequency domain.

[0218] For example, the first dimension is the spatial domain, the second dimension is the frequency domain, and the third dimension is the time domain.

[0219] If the first processing order is spatial domain, frequency domain, and time domain, then the second processing order can be time domain, frequency domain, and spatial domain.

[0220] Alternatively, if the first processing order is: first the spatial domain and frequency domain are processed simultaneously, then the time domain is processed, then the second processing order is: first the time domain, then the spatial domain and frequency domain are processed simultaneously.

[0221] Alternatively, if the first processing order is: spatial domain first, then frequency domain and time domain simultaneously, then the second processing order is: frequency domain and time domain simultaneously, then spatial domain.

[0222] Step S303: The second device obtains the first channel information based on the first reference signal and the second model.

[0223] Optionally, the second device can determine the second model based on at least one of the following: data requirements, communication quality requirements, or channel environment characteristics, and a third piece of information. For example, if the data requirement is to reduce computation or save energy, the second device can choose a channel reconstruction model that only performs processing in the time and frequency domains as the second model. Alternatively, if the communication quality requirement is high, the second device can choose a channel reconstruction model that performs processing in the time, frequency, and spatial domains as the second model. Or, if the channel environment characteristic is that the channel is relatively stable in the frequency domain, the second device can choose a channel reconstruction model that does not perform processing in the frequency domain as the second model.

[0224] It should be noted that step S303 is an optional step.

[0225] In one implementation, the second device can perform channel estimation based on the received first reference signal to obtain second channel information; and reconstruct the complete channel using the second channel information through a second model to obtain first channel information.

[0226] Figure 3B illustrates an exemplary flowchart of obtaining first channel information. As shown in Figure 3B, a first device deploys a first model, and a second device deploys a second model. The process of obtaining first channel information may include the following steps: S1: The first device determines a first reference signal pattern based on the first model, such as determining the output of the trained first model as the first reference signal pattern. For details of the determination process, please refer to step S301; S2: The first device indicates the first reference signal pattern to the second device; S3: The second device receives the first reference signal based on the first reference signal pattern; performs channel estimation based on the first reference signal to obtain second channel information; S4: The second device inputs the second channel information into the second model to obtain the first channel information.

[0227] For example, the channel reconstruction method used in the second model can be linear interpolation, linear minimum mean square error (LMMSE) interpolation, or other channel reconstruction methods, and this application does not limit this.

[0228] In this application, the second model can be obtained by training the second initial neural network multiple times. That is to say, the neural network that has been trained is the second model. The input of the second model can be the second channel information mentioned above, and the output of the second model can be the first channel information mentioned above.

[0229] For example, the criteria for determining whether training is complete may be: the total number of iterations (i.e., the number of training iterations, or the number of epochs) reaches a second value; or the loss function value obtained based on the input and output reaches a second threshold; or other conditions, which are not limited in this application.

[0230] Optionally, the training of the second model can be performed by the first device or the second model, or by other devices (such as a server), and this application does not limit this.

[0231] Optionally, the second device may send a sixth message to the first device, and the first device receives the sixth message, which is used to indicate the first channel information. For example, the first reference signal is CSI-RS, and the first channel information can be CSI; the first reference signal can also be other reference signals, and the first channel information can also be channel information corresponding to other reference signals, which is not limited in this application.

[0232] For example, if the first device is a network device and the second device is a terminal, the embodiment shown in Figure 3A can be as follows: the network device sends first information to the terminal, the first information indicating a first reference signal pattern, the first reference signal pattern being determined based on a first model; the network device sends a first reference signal to the terminal based on the first reference signal pattern, the first reference signal and the second model being used for channel reconstruction; wherein, the first processing order used by the first model in multiple dimensions and the second processing order used by the second model in multiple dimensions have a corresponding relationship, the multiple dimensions including at least two of the time domain, frequency domain, and spatial domain; the terminal obtains first channel information based on the first reference signal and the second model. Specifically, the first device in the embodiment shown in Figure 3A can be replaced with a network device and the second device with a terminal, which will not be elaborated further here.

[0233] For example, if the first device is a terminal and the second device is a network device, then the embodiment shown in Figure 3A can be as follows: the terminal sends first information to the network device, the first information indicating a first reference signal pattern, the first reference signal pattern being determined based on a first model; the terminal sends a first reference signal to the network device based on the first reference signal pattern, the first reference signal and the second model being used for channel reconstruction; wherein, the first processing order used by the first model in multiple dimensions and the second processing order used by the second model in multiple dimensions have a corresponding relationship, the multiple dimensions including at least two of the time domain, frequency domain, and spatial domain; the network device obtains first channel information based on the first reference signal and the second model. Specifically, the first device in the embodiment shown in Figure 3A can be replaced with a terminal and the second device with a network device, which will not be elaborated further here.

[0234] The method embodiment shown in Figure 3A above includes many possible implementation schemes. Some of these implementation schemes will be illustrated below with reference to Figures 4 to 6. It should be noted that related concepts, operations or logical relationships not explained in Figures 4 to 6 can be referred to the corresponding descriptions in the embodiment shown in Figure 3A.

[0235] In this application, the embodiments shown in Figures 4 to 6 can be used as a single embodiment, and the embodiments shown in Figures 4 to 6 can all be independent of the technical solution in Figure 3A; some steps in the embodiments shown in Figures 4 to 6 can also be used as a single embodiment.

[0236] Figure 4 is a flowchart of another communication method provided in an embodiment of this application.

[0237] This application uses a network device as the first device and a terminal as the second device for illustration. In this application embodiment, the first reference signal can also be called a downlink reference signal or downlink pilot (as in downlink DMRS), and the pattern of the first reference signal can also be called a pilot pattern.

[0238] The functions performed by the network device in this application can also be performed by modules (e.g., chips) in the network device; the functions performed by the terminal in this application can also be performed by modules (e.g., chips) in the terminal.

[0239] As shown in Figure 4, the method may include the following steps:

[0240] S401: The network device indicates multiple options to the terminal.

[0241] S401 is an optional step; for example, the information involved in S401 (such as multiple selections) can be pre-configured.

[0242] For example, a network device may send third information to a terminal, which indicates multiple options.

[0243] Among them, the multiple options can be: the model identifier corresponding to each model in the multiple reference signal pattern design models, or the model identifier corresponding to each model in the multiple channel reconstruction models, or the model identifier corresponding to each model group in the multiple model groups, or the processing order corresponding to each model in the multiple reference signal pattern design models, or the processing order corresponding to each model in the multiple channel reconstruction models.

[0244] For example, multiple options can be found in Tables 1 and 2.

[0245] As shown in Table 1, the model identifier corresponding to each model in the multiple reference signal pattern design models may include: 1-1, 2-1, 3-1;

[0246] Alternatively, the model identifier corresponding to each model in multiple channel reconstruction models may include: 2-1, 2-2, 2-3;

[0247] Alternatively, the model identifier for each model group in multiple model groups may include: 1, 2, 3.

[0248] As shown in Table 2, the processing order for each model in the multiple reference signal pattern design models may include: spatial domain 1 time domain 2 frequency domain 3, spatial domain 1 time domain 3 frequency 2, spatial domain 2 time domain 1 frequency domain 1.

[0249] Alternatively, the processing order for each model in multiple channel reconstruction models may include: spatial domain 3, time domain 2, frequency domain 1; spatial domain 3, time domain 1, frequency 2; spatial domain 1, time domain 2, frequency domain 2.

[0250] S402: The terminal indicates a first choice to the network device, where the first choice is one of multiple choices.

[0251] In one implementation, the terminal determines a first selection from multiple options and sends second information to the network device, the second information indicating the first selection. For example, the terminal may select a first selection from multiple options that matches the aforementioned information based on its own hardware support, environmental characteristics, and other information.

[0252] For example, multiple selections are model identifiers corresponding to each model in multiple reference signal pattern design models, such as 1-1, 2-1, 3-1; if the terminal determines 1-1 as the first selection, the terminal sends second information to the network device, the second information being used to indicate that the model identifier of the adopted reference signal pattern design model (i.e., the first model) is 1-1.

[0253] For example, multiple selections are model identifiers corresponding to each model in multiple channel reconstruction models, such as 2-1, 2-2, and 2-3. If the terminal determines 2-1 as the first selection, the terminal sends second information to the network device. The second information is used to indicate that the model identifier of the channel reconstruction model (i.e., the second model) is 2-1.

[0254] For example, multiple choices are the processing order corresponding to each model in multiple channel reconstruction models, such as spatial domain 3, time domain 2, frequency domain 1, spatial domain 3, time domain 1, frequency domain 2, spatial domain 1, time domain 2, frequency domain 2; if the terminal determines spatial domain 1, time domain 2, frequency domain 2 as the first choice, the terminal sends second information to the network device. The second information is used to indicate that the channel reconstruction order (i.e., the second processing order) is spatial domain 1, time domain 2, frequency domain 2.

[0255] For example, multiple choices are the processing order corresponding to each model in multiple reference signal pattern design models, such as spatial domain 1, time domain 2, frequency domain 3, spatial domain 1, time domain 3, frequency 2, spatial domain 2, time domain 1, frequency domain 1; if the terminal determines spatial domain 2, time domain 1, frequency domain 1 as the first choice, the terminal sends second information to the network device. The second information is used to indicate that the processing order of the reference signal pattern design (i.e., the first processing order) is spatial domain 2, time domain 1, frequency domain 1.

[0256] S403: The network device determines the first model based on the first choice.

[0257] In one implementation, the network device can determine the reference signal pattern design model corresponding to the first selection selected by the terminal as the first model. The correspondence between the first selection and the reference signal pattern design model can be exemplarily seen in Tables 1 and 2, where information in the same row of Tables 1 and 2 has a corresponding relationship.

[0258] For example, if the first selection is used to indicate that the model identifier of the reference signal pattern design model is 1-1, and the terminal sends second information to the network device, the second information is used to indicate that the model identifier of the adopted reference signal pattern design model (i.e., the first model) is 1-1. Then, the network device can determine the reference signal pattern design model corresponding to the model identifier 1-1 as the first model.

[0259] For example, if the first selection is used to indicate the channel reconstruction model (i.e., the second model) with model identifier 2-1, and the terminal sends second information to the network device, the second information is used to indicate that the channel reconstruction model (i.e., the second model) with model identifier 2-1 is used. Then, the network device can determine the reference signal pattern design model with model identifier 1-1 as the first model based on Table 1.

[0260] For example, if the first selection indicates that the processing order of the reference signal pattern design (i.e., the first processing order) is spatial domain 2, time domain 1, and frequency domain 1, and the terminal sends second information to the network device, the second information indicates that the processing order of the reference signal pattern design (i.e., the first processing order) is spatial domain 2, time domain 1, and frequency domain 1. Then, the model in which the network device determines the processing order of the reference signal pattern design (i.e., the first processing order) as spatial domain 2, time domain 1, and frequency domain 1 is the first model.

[0261] For example, the first selection is used to indicate that the channel reconstruction order (i.e., the second processing order) is spatial domain 1, time domain 2, and frequency domain 2. If the terminal sends second information to the network device, the second information is used to indicate that the channel reconstruction order (i.e., the second processing order) is spatial domain 1, time domain 2, and frequency domain 2. Then, the network device can determine, based on Table 2, the model with the processing order (i.e., the first processing order) of the reference signal pattern design as spatial domain 2, time domain 1, and frequency domain 1 as the first model.

[0262] Optionally, the first model can be generated and trained after the terminal selects the first option, or it can be generated and trained in advance before the terminal selects the first option. There is no temporal order between the generation and training of the model and the selection of the first option by the terminal.

[0263] Optionally, the network device may also pre-store the correspondence between the above-mentioned multiple selections and multiple reference signal pattern design models. The above-mentioned multiple selections and multiple reference signal pattern design models may be in a one-to-one correspondence, or the terminal or other device may indicate the correspondence to the network device. For examples, please refer to the relevant description in step S302, which will not be repeated here.

[0264] S404: The terminal downloads the second model from the network device, and the first model corresponds to the second model.

[0265] In other words, the network device sends a second model to the terminal. For example, the network device sends a fourth piece of information to the terminal, which is the second model.

[0266] For example, a network device may determine a second model based on a first model or a first choice.

[0267] For example, if the first selection for the processing order of the reference signal pattern design (i.e., the first processing order) is spatial domain 2, time domain 1, and frequency domain 1, then the network device can determine the channel reconstruction model (i.e., the second model) with the channel reconstruction order of spatial domain 1, time domain 2, and frequency domain 2 based on the last row in Table 2.

[0268] S404 is an optional step. For example, if the terminal has a second model deployed, the terminal does not need to download the second model from the network device.

[0269] S405: The network device indicates a first reference signal pattern to the terminal, the first reference signal pattern being determined based on a first model.

[0270] For example, a network device can send first information to a terminal, which is used to indicate a first reference signal pattern.

[0271] The first information can be any combination of antenna port, time domain, and frequency domain. For example, the first reference signal pattern mentioned above can be represented by an index set I, where the index set I = {I... 1 ,I 2 ,…,I k}, where k is the number of pilot signals, k is a positive integer, and the index of the i-th pilot is...

[0272] S406: The network device sends a first reference signal to the terminal based on the first reference signal pattern.

[0273] Optionally, the process may also include data transfer.

[0274] S407: The terminal obtains the first channel information based on the first reference signal, the first reference signal pattern, and the second model.

[0275] For example, step S407 may include the following steps S4071 to S4073:

[0276] S4071: Based on the first reference signal pattern (I) i (Position) Obtain the first reference signal p′.

[0277] S4072: Channel estimation: Obtain channel information of the pilot position based on the first reference signal p′ and the channel estimation method f(·). Channel estimation methods f(·) include, but are not limited to, the minimum mean square error (MMSE) method.

[0278] S4073: Channel Reconfiguration: I i Channel information corresponding to the location Input the second model to obtain complete channel information. (i.e., first channel information).

[0279] S408: The terminal transmits data with the network device based on the first channel information.

[0280] Optionally, if the terminal changes its selection, such as changing from the first selection to the second selection, the terminal can report the second selection. For example, the second selection corresponds to another reference signal pattern network (referred to as network 1 for ease of description). Accordingly, the network device can determine network 1 based on the second selection, send the reference signal pattern corresponding to network 1 to the terminal, and send a reference signal to the terminal based on the reference signal pattern. Accordingly, the terminal obtains channel information 1 based on the received reference signal and reference signal pattern, and performs data transmission with the network device. This process can be exemplarily described in steps S402 to S408 above.

[0281] In this embodiment of the application, the first reference signal can be downlink DMRS. This embodiment of the application can provide a standard support for the interface and process in the downlink DMRS scenario for future reference signal pattern design and channel reconstruction using neural networks, under the 6G massive MIMO antenna port.

[0282] Figure 5 is a flowchart of another communication method provided in an embodiment of this application.

[0283] This application uses an example where the first device is a network device and the second device is a terminal.

[0284] The functions performed by the network device in this application can also be performed by modules (e.g., chips) in the network device; the functions performed by the terminal in this application can also be performed by modules (e.g., chips) in the terminal.

[0285] As shown in Figure 5, the method may include the following steps:

[0286] S501: Terminal reporting channel reconfiguration capability.

[0287] S501 is an optional step. For example, the information involved in S501 can be pre-configured. The network device is configured with the terminal's channel reconfiguration capability, and the terminal does not need to report the channel reconfiguration capability.

[0288] For example, the channel reconstruction capability can refer to the channel reconstruction model supported by the terminal, or the channel reconstruction sequence supported by the terminal. For instance, the terminal can send fifth information to the network device, which indicates the channel reconstruction model supported by the terminal, or the channel reconstruction sequence supported by the terminal.

[0289] For example, the channel reconstruction capability can also refer to the terminal supporting neural network-assisted reference signal pattern design and channel reconstruction. That is, the terminal supports channel reconstruction based on a reference signal pattern determined by a neural network (such as a first reference signal pattern obtained based on a first model), and / or, the terminal supports channel reconstruction based on a neural network (such as channel reconstruction based on a second model).

[0290] S502: Based on the aforementioned channel reconfiguration capability, the network device determines the first model.

[0291] For example, the network device selects a first model based on information such as the environment and the aforementioned channel reconstruction capabilities. For instance, the network device may select a channel reconstruction model that matches the channel environment from the aforementioned channel reconstruction capabilities (such as channel reconstruction models supported by the terminal), and determine that channel reconstruction model as the first model. As another example, the network device may select a channel reconstruction sequence that matches the channel environment from the aforementioned channel reconstruction capabilities (such as channel reconstruction sequences supported by the terminal), and determine the channel reconstruction model corresponding to that channel reconstruction sequence as the first model.

[0292] S503: The network device indicates the second model to the terminal, and the first model corresponds to the second model.

[0293] For example, the network device sends a fourth message to the terminal, which is used to indicate the second model.

[0294] For example, a network device may determine a second model based on a first model.

[0295] For example, the correspondence between the first model and the second model can be found above, such as in Table 1 or Table 2 or the relevant content of the embodiment in Figure 4.

[0296] S504: The network device indicates a first reference signal pattern to the terminal, the first reference signal pattern being determined based on a first model.

[0297] For example, a network device can send first information to a terminal, which is used to indicate a first reference signal pattern.

[0298] The first information can be any combination of antenna port, time domain, and frequency domain. For example, the first reference signal pattern mentioned above can be represented by an index set I, where the index set I = {I... 1 ,I 2,…,I k}, where k is the number of pilot signals, k is a positive integer, and the index of the i-th pilot is...

[0299] S505: The network device sends a first reference signal to the terminal based on the first reference signal pattern.

[0300] Optionally, the process may also include data transfer.

[0301] S506: The terminal obtains the first channel information based on the first reference signal, the first reference signal pattern, and the second model.

[0302] For example, step S506 may include the following steps S5061 to S5063:

[0303] S5061: Based on the first reference signal pattern (I) i (Position) Obtain the first reference signal p′.

[0304] S5062: Channel estimation: Based on the first reference signal p′ and the channel estimation method f(·), obtain the channel information of the pilot position. Channel estimation methods f(·) include, but are not limited to, the minimum mean square error (MMSE) method.

[0305] S5063: Channel Reconfiguration: I i Channel information corresponding to the location Input the second model to obtain complete channel information. (i.e., first channel information).

[0306] S507: The terminal transmits data with the network device based on the first channel information.

[0307] Optionally, if the terminal changes its selection, such as changing from the first selection to the second selection, the terminal can report the second selection. For example, the second selection corresponds to another reference signal pattern network (referred to as network 1 for ease of description). Accordingly, the network device can determine network 1 based on the second selection, send the reference signal pattern corresponding to network 1 to the terminal, and send a reference signal to the terminal based on the reference signal pattern. Accordingly, the terminal obtains channel information 1 based on the received reference signal and reference signal pattern, and performs data transmission with the network device. This process can be exemplarily described in steps S402 to S408 above.

[0308] In this embodiment, the first reference signal can be downlink DMRS. This embodiment can provide interface and process specifications for network devices to perform model selection in downlink DMRS scenarios under the 6G massive MIMO antenna port, in order to enable reference signal pattern design and channel reconstruction using neural networks in the future.

[0309] Figure 6 is a flowchart of another communication method provided in an embodiment of this application.

[0310] This application uses a first device as the terminal and a second device as a network device as an example for illustration.

[0311] This application uses CSI-RS as the first reference signal and CSI as the first channel information as an example for illustration.

[0312] The functions performed by the network device in this application can also be performed by modules (e.g., chips) in the network device; the functions performed by the terminal in this application can also be performed by modules (e.g., chips) in the terminal.

[0313] As shown in Figure 6, the method may include the following steps:

[0314] S601: The terminal indicates the second model to the network device.

[0315] In other words, the terminal indicates to the network device the channel reconstruction model adopted by the terminal or the channel reconstruction order adopted by the terminal in at least two of the time domain, frequency domain, or spatial domain.

[0316] For example, the terminal can also report channel reconstruction capability, which may refer to the terminal's support for neural network-assisted reference signal pattern design and channel reconstruction. That is, the terminal supports channel reconstruction based on a reference signal pattern determined by a neural network (such as a first reference signal pattern obtained based on a first model), and / or, the terminal supports channel reconstruction based on a neural network (such as channel reconstruction based on a second model).

[0317] S602: The network device determines the first model, and the first model corresponds to the second model.

[0318] For example, a network device may determine a first model based on a second model.

[0319] For example, the correspondence between the first model and the second model can be found above, such as in Table 1 or Table 2 or the relevant content of the embodiment in Figure 4.

[0320] S603: The network device indicates a first reference signal pattern to the terminal, the first reference signal pattern being determined based on a first model.

[0321] For example, a network device can send first information to a terminal, which is used to indicate a first reference signal pattern.

[0322] The first information can be any combination of antenna port, time domain, and frequency domain. For example, the first reference signal pattern mentioned above can be represented by an index set I, where the index set I = {I... 1 ,I 2 ,…,I k}, where k is the number of pilot signals, k is a positive integer, and the index of the i-th pilot is...

[0323] S604: The network device sends CSI-RS to the terminal based on the first reference signal pattern.

[0324] Optionally, the process may also include data transfer.

[0325] S605: The terminal obtains CSI based on CSI-RS, the first reference signal pattern, and the second model.

[0326] For example, step S605 may include the following steps S6051 to S6053:

[0327] S6051: Based on the first reference signal pattern (I) i (Location) Obtain CSI-RSp′.

[0328] S6052: Channel Estimation: Obtain channel information for the pilot positions based on CSI-RSp′ and channel estimation method f(·). Channel estimation methods f(·) include, but are not limited to, the minimum mean square error (MMSE) method.

[0329] S6053: Channel Reconfiguration: I i Channel information corresponding to the location Input the second model to obtain complete channel information. (i.e., CSI).

[0330] S606: Terminal reports CSI.

[0331] In other words, the terminal sends CSI to the network device.

[0332] S607: The terminal uses CSI to transmit data with network devices.

[0333] This application provides a standardized support for the interface and process of network devices performing model selection in downlink CSI-RS scenarios, specifically for future reference signal pattern design and channel reconstruction using neural networks, under the 6G massive MIMO antenna port.

[0334] It should be noted that the communication method provided in this application is also applicable to scenarios where the first device is a terminal and the second device is a network device. For example, in the embodiments shown in Figures 4 to 6 above, the terminal can be replaced with a network device, and vice versa. The communication method provided in this application is also applicable to D2D scenarios, that is, the first device can be a first terminal and the second device can be a second terminal. For example, in the embodiments shown in Figures 4 to 6 above, the terminal can be replaced with a first terminal and the network device can be replaced with a second terminal.

[0335] The following is a schematic diagram of a communication device according to an embodiment of this application. Referring to FIG7, the communication device can be used to execute the process performed by the first device in the embodiment shown in FIG3A, and for details, please refer to the relevant description in the foregoing method embodiments.

[0336] The communication device 900 includes a transceiver module 901 and a processing module 902.

[0337] The processing module 902 is used for data processing. The transceiver module 901 can implement the corresponding communication functions. The transceiver module 901 can also be called a communication interface or a communication module.

[0338] Optionally, the communication device 900 may further include a storage module, which can be used to store program code and / or program instructions and / or data. The processing module 902 can read the instructions and / or data in the storage module so that the communication device 900 can implement the aforementioned method embodiments.

[0339] The communication device 900 can be used to perform the actions performed by the first device in the above method embodiments. For example, it can be the first device, a communication module within the first device, or a circuit or chip in the first device responsible for communication functions. The communication device 900 can be the first device or a component configurable on the first device. The processing module 902 is used to perform processing-related operations on the first device side in the above method embodiments. The transceiver module 901 is used to perform receiving-related operations on the first device side in the above method embodiments.

[0340] Optionally, the transceiver module 901 may include a sending module and / or a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0341] It should be noted that the communication device 900 may include a transmitting module but not a receiving module. Alternatively, the communication device 900 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme performed by the communication device 900 includes both transmitting and receiving actions. For example, the communication device 900 is used to perform the actions performed by the first device in the embodiments shown in Figures 3A to 6. For details, please refer to the relevant descriptions in the embodiments shown in Figures 3A to 6, which will not be elaborated here. For example, the communication device 900 is used to perform the following scheme:

[0342] The transceiver module 901 is used to transmit first information, which is used to indicate a first reference signal pattern. The first reference signal pattern is determined based on a first model. Based on the first reference signal pattern, a first reference signal is transmitted. The first reference signal and a second model are used for channel reconstruction. The first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in multiple dimensions have a corresponding relationship. The multiple dimensions include at least two of the time domain, frequency domain, and spatial domain.

[0343] For other implementation methods, please refer to the relevant descriptions in the embodiments shown in Figures 3A to 6 above.

[0344] It should be understood that the specific procedures for each module to perform the above-mentioned corresponding processes have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0345] Optionally, when the communication device 900 is a first device or a communication module within a first device, the processing module 902 in the above embodiments can be implemented by at least one processor or processor-related circuitry. Specifically, the processor may include a modem chip, or a SoC chip or SIP chip containing a modem core. The transceiver module 901 can be implemented by a transceiver or transceiver-related circuitry. The transceiver module 901 may also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0346] Optionally, when the communication device 900 is a circuit or chip in the first device responsible for communication functions, such as a modem chip or a SoC chip or SIP chip containing a modem core, the function of the processing module 902 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processing cores. The function of the transceiver module 901 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0347] For example, the processing module 902 can be a circuit, chip, processor, processing core, or circuit system, such as a modem chip, a SoC chip containing a modem core, a SIP chip, or a circuit system of the aforementioned chips that includes one or more processors or processing cores; the transceiver module 901 can be a circuit, chip, interface circuit, or data transceiver circuit, such as a modem chip, a SoC chip containing a modem core, a SIP chip, or an interface circuit or data transceiver circuit on the aforementioned chips.

[0348] The following is a schematic diagram of another communication device according to an embodiment of this application. Referring to FIG8, the communication device can be used to execute the process performed by the second device in the embodiments shown in FIG3A to FIG6, and the details can be found in the relevant descriptions in the foregoing method embodiments.

[0349] The communication device 1000 includes a transceiver module 1001. Optionally, the communication device 1000 may also include a processing module 1002.

[0350] The processing module 1002 is used for data processing. The transceiver module 1001 can implement the corresponding communication functions. The transceiver module 1001 can also be called a communication interface or a communication module.

[0351] Optionally, the communication device 1000 may further include a storage module, which can be used to store program code, program instructions and / or data. The processing module 1002 can read the instructions and / or data in the storage module so that the communication device 1000 can implement the aforementioned method embodiments.

[0352] The communication device 1000 can be used to perform the actions performed by the second device in the above method embodiments. For example, it can be the second device, a communication module within the second device, or a circuit or chip in the second device responsible for communication functions. The communication device 1000 can be the second device or a component configurable on the second device. The processing module 1002 is used to perform processing-related operations on the second device side in the above method embodiments. The transceiver module 1001 is used to perform receiving-related operations on the second device side in the above method embodiments.

[0353] Optionally, the transceiver module 1001 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0354] It should be noted that the communication device 1000 may include a transmitting module but not a receiving module. Alternatively, the communication device 1000 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme executed by the communication device 1000 includes both transmitting and receiving actions. For example, the communication device 1000 is used to execute the actions performed by the second device in the embodiments shown in Figures 3A to 6. For details, please refer to the relevant descriptions in the embodiments shown in Figures 3A to 6, which will not be elaborated here. For example, the communication device 1000 is used to execute the following scheme:

[0355] The transceiver module 1001 is configured to: transmit first information, the first information being used to indicate a first reference signal pattern, the first reference signal pattern being determined based on a first model; and receive a first reference signal based on the first reference signal pattern, the first reference signal being used for channel reconstruction using a second model; wherein, the first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in multiple dimensions have a corresponding relationship, the multiple dimensions including at least two of the time domain, frequency domain, and spatial domain;

[0356] The processing module 1002 is used to obtain the first channel information based on the first reference signal and the second model.

[0357] For other implementation methods, please refer to the relevant descriptions in the embodiments shown in Figures 3A to 6 above.

[0358] It should be understood that the specific procedures for each module to perform the above-mentioned corresponding processes have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0359] The processing module 1002 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver module 1001 can be implemented by a transceiver or transceiver-related circuitry. The transceiver module 1001 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0360] Optionally, when the communication device 1000 is a second device or a communication module within a second device, the processing module 1002 in the above embodiments can be implemented by at least one processor or processor-related circuitry. Specifically, the processor may include a modem chip, or a SoC chip or SIP chip containing a modem core. The transceiver module 1001 can be implemented by a transceiver or transceiver-related circuitry. The transceiver module 1001 may also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0361] Optionally, when the communication device 1000 is a circuit or chip in the second device responsible for communication functions, such as a modem chip or a SoC chip or SIP chip containing a modem core, the function of the processing module 1002 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processing cores. The function of the transceiver module 1001 can be implemented by the interface circuit or data transceiver circuit on the aforementioned chip.

[0362] For example, the processing module 1002 can be a circuit, chip, processor, processing core, or circuit system, such as a modem chip, a SoC chip containing a modem core, a SIP chip, or a circuit system of the aforementioned chips that includes one or more processors or processing cores; the transceiver module 1001 can be a circuit, chip, interface circuit, or data transceiver circuit, such as a modem chip, a SoC chip containing a modem core, a SIP chip, or an interface circuit or data transceiver circuit on the aforementioned chips.

[0363] Figure 9 illustrates a possible structural schematic of a communication device. It will be understood that the communication device 110 includes means of the necessary form, such as modules, units, elements, circuits, or interfaces, appropriately configured together to perform this solution. The communication device 110 may be the first or second device described above, or a component (e.g., a chip) within these devices, used to implement the methods described in the above method embodiments.

[0364] The communication device 110 includes one or more processors 111. These processors 111 can be general-purpose processors or dedicated processors, such as baseband processors or central processing units. The baseband processor can process communication protocols and communication data, while the central processing unit can control the communication device (e.g., RAN node, terminal, or chip), execute software programs, and process data from the software programs.

[0365] Optionally, in one design, the processor 111 may include a program 113 (sometimes referred to as code or instructions) that can be run on the processor 111 to cause the communication device 110 to perform the methods described in the above embodiments.

[0366] Optionally, the communication device 110 may include one or more memories 112 storing a program 114 (sometimes referred to as code or instructions), which can be run on the processor 111 to cause the communication device 110 to perform the methods described in the above method embodiments.

[0367] Optionally, the processor 111 and / or memory 112 may include AI modules 117 and 118, which are used to implement AI-related functions. The AI ​​modules may be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a RAN intelligent controller (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0368] Optionally, the processor 111 and / or memory 112 may also store data. The processor and memory may be configured separately or integrated together.

[0369] Optionally, the communication device 110 may further include a transceiver 115 and / or an antenna 116. The processor 111, sometimes referred to as a processing unit, controls the communication device (e.g., a RAN node or terminal). The transceiver 115, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, is used to realize the transmission and reception functions of the communication device through the antenna 116.

[0370] In this application, when the first device is a terminal, the second device can be a network device; when the first device is a network device, the second device can be a terminal. The following provides exemplary descriptions of terminals and network devices.

[0371] This application also provides a communication device 1200, which can be a terminal, a processor in the terminal, or a chip. The communication device 1200 can be used to perform the operations performed by the terminal in the above method embodiments.

[0372] When the communication device 1200 is a terminal, Figure 10 shows a schematic diagram of the terminal structure. As shown in Figure 10, the terminal includes a processor, a memory, and a transceiver. The memory can store computer program code, and the transceiver includes a transmitter 1231, a receiver 1232, radio frequency circuitry (not shown in the figure), an antenna 1233, and input / output devices (not shown in the figure).

[0373] The processor is mainly used to process communication protocols and communication data; control terminals; execute software programs; and process data from software programs.

[0374] Memory is mainly used to store software programs and data.

[0375] Radio frequency (RF) circuits are mainly used for the conversion between baseband signals and RF signals, as well as for the processing of RF signals.

[0376] Antennas are primarily used for transmitting and receiving radio frequency signals in the form of electromagnetic waves.

[0377] Input / output devices can include touchscreens, displays, or keyboards. They are primarily used to receive user input and output data to the user. It should be noted that some types of terminals may not have input / output devices.

[0378] When data needs to be transmitted, the processor performs baseband processing on the data to be transmitted and outputs a baseband signal to the radio frequency (RF) circuit. The RF circuit then processes the baseband signal and transmits it outwards as electromagnetic waves via an antenna. When data is sent to the terminal, the RF circuit receives the RF signal through the antenna. The RF circuit converts the RF signal back into a baseband signal and outputs it to the processor. The processor converts the baseband signal back into data and processes that data. For ease of explanation, Figure 10 only shows one memory, processor, and transceiver. In actual terminal products, there may be one or more processors and one or more memories. Memory can also be called storage medium or storage device, etc. Memory can be independent of the processor or integrated with it; this embodiment does not limit this.

[0379] In the embodiments of this application, the antenna and radio frequency circuit with transceiver function can be regarded as the transceiver module of the terminal, and the processor with processing function can be regarded as the processing module of the terminal.

[0380] As shown in Figure 10, the terminal includes a processor 1210, a memory 1220, and a transceiver 1230. The processor 1210 can also be referred to as a processing unit, processing board, processing module, or processing device, etc. The transceiver 1230 can also be referred to as a transceiver unit, transceiver, or transceiver device, etc.

[0381] Optionally, the device in transceiver 1230 used to implement the receiving function can be considered a receiving module, and the device in transceiver 1230 used to implement the transmitting function can be considered a transmitting module. That is, transceiver 1230 includes a receiver and / or a transmitter. A transceiver may also be called a transceiver unit, transceiver module, or transceiver circuit, etc. A receiver may also be called a receiver unit, receiving module, or receiving circuit, etc. A transmitter may also be called a transmitter, transmitting module, or transmitting circuit, etc.

[0382] The processor 1210 is used to execute the terminal-side processing operations in the embodiments shown in Figures 3A to 6. The transceiver 1230 is used to execute the terminal-side transmission and reception operations in the embodiments shown in Figures 3A to 6.

[0383] It should be understood that Figure 10 is merely an example and not a limitation, and the terminal described above, including the transceiver module and the processing module, may not depend on the structure shown in Figure 7 or Figure 10.

[0384] When the communication device 1200 is a chip, the chip includes a processor, a memory, and a transceiver. The transceiver can be an input / output circuit or a communication interface. The processor can be a processing module integrated on the chip, a microprocessor, or an integrated circuit. In the above method embodiments, the terminal's sending operation can be understood as the chip's output, and the terminal's receiving operation in the above method embodiments can be understood as the chip's input.

[0385] This application also provides a communication device 1300, which can be an access network device or a chip. The communication device 1300 can be used to perform the operations performed by the network device in the embodiments shown in Figures 3A to 6.

[0386] When the communication device 1300 is a network device, such as a base station, Figure 11 shows a schematic diagram of a network device, which is a simplified base station structure. The base station includes parts 1310, 1320, and 1330.

[0387] The 1310 section is mainly used for baseband processing and base station control; the 1310 section is usually the control center of the base station, which can be called the processor, and is used to control the base station to perform the processing operations on the network device side in the above method embodiments.

[0388] Section 1320 is primarily used to store computer program code and data.

[0389] Section 1330 is primarily used for transmitting and receiving radio frequency (RF) signals, as well as converting RF signals to baseband signals. Section 1330 is commonly referred to as a transceiver module, transceiver, transceiver circuit, or transceiver unit. The transceiver module of section 1330, also known as a transceiver or transceiver unit, includes antenna 1333 and RF circuitry (not shown in the figure), where the RF circuitry is mainly used for RF processing. Optionally, the device in section 1330 that performs the receiving function can be considered a receiver, and the device that performs the transmitting function can be considered a transmitter; that is, section 1330 includes receiver 1332 and transmitter 1331. The receiver can also be called a receiving module, receiver circuit, or receiving circuit, and the transmitter can be called a transmitting module, transmitter, or transmitting circuit.

[0390] Sections 1310 and 1320 may include one or more circuit boards, each of which may include one or more processors and one or more memories. The processors are used to read and execute programs from the memories to implement baseband processing functions and control the base station. If multiple circuit boards exist, they can be interconnected to enhance processing capabilities. As an alternative implementation, multiple circuit boards may share one or more processors, multiple circuit boards may share one or more memories, or multiple circuit boards may simultaneously share one or more processors.

[0391] For example, in one implementation, the transceiver module of section 1330 is used to execute the transceiver-related processes performed by the network device in the embodiments shown in Figures 3A to 6. The processor of section 1310 is used to execute the processing-related processes performed by the network device in the embodiments shown in Figures 3A to 6.

[0392] It should be understood that Figure 11 is merely an example and not a limitation, and the network device described above, including the processor, memory, and transceiver, may not depend on the structure shown in Figure 8 or Figure 11.

[0393] When the communication device 1300 is a chip, the chip includes a processor, which may be an on-chip processor, a microprocessor, or an integrated circuit. Optionally, the communication device 1300 may also include a transceiver, which may be an input / output circuit or a communication interface. Further optionally, the communication device 1300 may also include a memory, which may be built into the chip or be an external memory. In the above method embodiments, the transmitting operation of the network device can be understood as the output of the chip, and the receiving operation of the network device in the above method embodiments can be understood as the input of the chip.

[0394] This application also provides a computer-readable storage medium having stored thereon a computer program or instructions for implementing the method executed by the first device or the second device in the above method embodiments.

[0395] For example, when the computer program is executed by a computer, it enables the computer to implement the method performed by the first device or the second device in the above method embodiments.

[0396] This application also provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the method described in the above method embodiments, executed by the first device or the second device.

[0397] This application also provides a communication system, which includes a first device and a second device. The first device is used to perform some or all of the operations performed by the first device in the embodiments shown in Figures 3A to 6, and the second device is used to perform some or all of the operations performed by the second device in the embodiments shown in Figures 3A to 6.

[0398] This application also provides a chip device, including a processor, for calling computer programs or computer instructions stored in the memory, so that the processor executes the methods provided in the embodiments shown in Figures 3A to 6 above.

[0399] In one possible implementation, the input of the chip device corresponds to the receiving operation in any one of the embodiments shown in Figures 3A to 6, and the output of the chip device corresponds to the transmitting operation in any one of the embodiments shown in Figures 3A to 6.

[0400] Optionally, the processor is coupled to the memory via an interface.

[0401] Optionally, the chip device may also include a memory that stores computer programs or computer instructions.

[0402] The processor mentioned above can be a general-purpose central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of a program for controlling the method provided in any of the embodiments shown in Figures 3A to 6. The memory mentioned above can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM).

[0403] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the explanations and beneficial effects of the relevant contents in any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, and will not be repeated here.

[0404] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0405] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0406] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0407] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the essential contribution of the technical solution of this application, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0408] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

A communication method, characterized in that, The method includes: Send first information, the first information being used to indicate a first reference signal pattern, the first reference signal pattern being determined based on a first model; Based on the first reference signal pattern, a first reference signal is transmitted, and the first reference signal and the second model are used for channel reconstruction. The first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in the same multiple dimensions correspond to each other. The multiple dimensions include at least two of the time domain, frequency domain, and spatial domain. The method according to claim 1, characterized in that, The method further includes: Receive second information, which is used to indicate the first model, or the second information is used to indicate the second model, or the second information is used to indicate a first model group, which includes the first model and the second model. The method according to claim 2, characterized in that, Before receiving the second information, the method further includes: Send a third message, the third message being used to indicate multiple reference signal pattern design models, or the third message being used to indicate multiple channel reconstruction models, or the third message being used to indicate multiple model groups; The plurality of reference signal pattern design models include the first model, the plurality of channel reconstruction models include the second model, and the plurality of model groups include the first model group. The method according to claim 1, characterized in that, The method further includes: Receive third information, the third information being used to indicate multiple reference signal pattern design models, or, the third information being used to indicate multiple channel reconstruction models, or, the third information being used to indicate multiple model groups, wherein the multiple reference signal pattern design models include the first model, the multiple channel reconstruction models include the second model, the multiple model groups include a first model group, and the first model group includes the first model and the second model; Based on the third information, the first model, the second model, or the first model group are determined. The method according to claim 4, characterized in that, The method further includes: Send a fourth message, which is used to indicate the second model or the fourth message is the second model. A communication method, characterized in that, The method includes: Receive first information, the first information being used to indicate a first reference signal pattern, the first reference signal pattern being determined based on a first model; Based on the first reference signal pattern, receive the first reference signal; Based on the first reference signal and the second model, the first channel information is obtained. The first processing order adopted by the first model in multiple dimensions and the second processing order adopted by the second model in multiple dimensions correspond to each other, wherein the multiple dimensions include at least two of the time domain, frequency domain, and spatial domain. The method according to claim 6, characterized in that, The method further includes: Send a second message, which is used to indicate the first model, or the second message is used to indicate the second model, or the second message is used to indicate a first model group, which includes the first model and the second model. The method according to claim 7, characterized in that, Before sending the second information, the method further includes: Receive third information, the third information being used to indicate multiple reference signal pattern design models, or the third information being used to indicate multiple channel reconstruction models, or the third information being used to indicate multiple model groups; The plurality of reference signal pattern design models include the first model, the plurality of channel reconstruction models include the second model, and the plurality of model groups include the first model group. The method according to claim 8, characterized in that, The method further includes: The second information is determined based on at least one of data requirements, communication quality requirements, or channel environment characteristics, and the third information. The method according to claim 6, characterized in that, The method further includes: Send a third message, the third message being used to indicate multiple reference signal pattern design models, or the third message being used to indicate multiple channel reconstruction models, or the third message being used to indicate multiple model groups, wherein the multiple reference signal pattern design models include the first model, the multiple channel reconstruction models include the second model, the multiple model groups include a first model group, and the first model group includes the first model and the second model. The method according to claim 10, characterized in that, The method further includes: Receive fourth information, which is used to indicate the second model or the fourth information is the second model. The method according to any one of claims 1-11, characterized in that, Prior to the method, it also includes: Sending or receiving fifth information, the fifth information being used to indicate a reference signal pattern employing a neural network. The method according to any one of claims 1-12 is characterized in that, The first model includes multiple first sub-models, and the second model includes multiple second sub-models. The multiple first sub-models correspond one-to-one with the multiple dimensions, and the multiple second sub-models correspond one-to-one with the multiple dimensions. Wherein, the first processing order is the running order of the plurality of first sub-models, and the second processing order is the running order of the plurality of second sub-models. The method according to any one of claims 1-13 is characterized in that, The second processing order is the reverse of the first processing order. The method according to any one of claims 1-14, characterized in that, The multiple dimensions are a first dimension, a second dimension, and a third dimension. The first processing order is the first dimension, the second dimension, and the third dimension. The second processing order is the third dimension, the second dimension, and the first dimension. Alternatively, the first processing order is that the first dimension and the second dimension are processed simultaneously, and the third dimension is processed simultaneously; the second processing order is that the third dimension, the first dimension, and the second dimension are processed simultaneously. Alternatively, the first processing order is that the first dimension, the second dimension, and the third dimension are processed simultaneously, and the second processing order is that the second dimension and the third dimension are processed simultaneously, and the first dimension is processed simultaneously. A communication device, characterized in that, Includes modules or units for performing the method according to any one of claims 1 to 15. A communication device, characterized in that, The device includes a processor and an interface circuit, wherein the interface circuit is used to receive signals from other communication devices and transmit them to the processor or to send signals from the processor to other communication devices, and the processor is used through logic circuits or executing code instructions to cause the communication device to implement the method as described in any one of claims 1 to 15. A readable storage medium, characterized in that, Used to store computer programs or instructions, which are executed by one or more processors, causing an apparatus including the one or more processors to perform the method as described in any one of claims 1 to 15. A computer program product, characterized in that, Includes program instructions that, when the computer program product is run on an electronic device, cause the electronic device to perform the method as described in any one of claims 1 to 15.

Images